Skip to content

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

feat(scrapeURL/summary): use gpt-5-mini (#2174)

Gergő Móriczaa42f4731913
diff --git a/apps/api/package.json b/apps/api/package.json
index 3031cac19..3cf01b00a 100644
--- a/apps/api/package.json
+++ b/apps/api/package.json
@@ -71,7 +71,7 @@
"@apidevtools/json-schema-ref-parser": "^11.7.3",
"@bull-board/api": "^6.11.2",
"@bull-board/express": "^6.11.2",
- "@dqbd/tiktoken": "^1.0.17",
+ "@dqbd/tiktoken": "^1.0.22",
"@google-cloud/storage": "^7.16.0",
"@mendable/firecrawl-rs": "workspace:*",
"@openrouter/ai-sdk-provider": "^0.4.5",
diff --git a/apps/api/pnpm-lock.yaml b/apps/api/pnpm-lock.yaml
index 9172b50b4..6b4dc99ac 100644
--- a/apps/api/pnpm-lock.yaml
+++ b/apps/api/pnpm-lock.yaml
@@ -43,8 +43,8 @@ importers:
specifier: ^6.11.2
version: 6.11.2
'@dqbd/tiktoken':
- specifier: ^1.0.17
- version: 1.0.17
+ specifier: ^1.0.22
+ version: 1.0.22
'@google-cloud/storage':
specifier: ^7.16.0
version: 7.16.0([email protected])
@@ -762,8 +762,8 @@ packages:
resolution: {integrity: sha512-hrlQOIi7hAfzsMqlGSFyVucrx38O+j6wiGOf//H2ecvIEqYN4ADBSS2iLMh5UFyDunCNniUIPk/q3riFv45xRA==}
- resolution: {integrity: sha512-v2gz0V6DiuR2TsALM32TkBThf6LdjLbxe6HS/nx9/KJxuDX0Z7SGX7N7PvQfqIvRyus42jI9poVUqezc/j/aQw==}
+ resolution: {integrity: sha512-RYhO8xeHkMNX5Ixqf4M1Ve3siCYJY/dI0yLnlX4M4oIEDOvjMIQ+E+3OUpAaZcWTaMtQJzGcDAghYfllpx3i/w==}
resolution: {integrity: sha512-t+iX+Wf5nRKyNzk8dviW3Ikb/280+aEJAnw9YXvCp2tYGPSkMki+NRY+8aNLmVFv3eNtMdvViPNOPxS8SZNP+w==}
@@ -1412,42 +1412,49 @@ packages:
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-yWjcPDgJ2nIL3KNvi4536dlT/CcCWO0DUyEOlBs/SacG7BeD6IjGh6yYzd3/X1Y3JItCbZoDoLUH8iB1lTXo3w==}
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-0XRhKuIU/9ZjT4WDIG/qnX7Xz7mSQHYZo9Gb3MP2gcvBgr6BA4zywQ9k3gmQaPn9ECE+CZg2V7DV7kT+x2pUMQ==}
engines: {node: '>= 10'}
cpu: [ppc64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-QrqDIPEUUB23GCpyQj/QFyMlr8SGxxyExeZz9OWFnHfb70kXdTLWrHS/hEI1Ru+lSbQ/6xRqeoGyQ4Aqdg+/RA==}
engines: {node: '>= 10'}
cpu: [riscv64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-k8RVM5aMhW86E9H0QXdquwojew4H3SwPxbRVbl49/COJQWCUjGi79X6mYruMnMPEznZinUiT1jgKbFo2A00NdA==}
engines: {node: '>= 10'}
cpu: [s390x]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-6rMtBgnIq2Wcl1rQdZsnM+rtCcVCbws1nF8S2NzaUsVaZv8bjrPiAa0lwg4Eqnn1d9lgwqT+cZgm5m+//K08Kw==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-eiadGBKi7Vd0bCArBUOO/qqRYPHt/VQVvGyYvDFt6C2ZSIjlD+HuOl+2oS1sjf4CFjK4eDIog6EdXnL0NE6iyQ==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-+VyHHlr68dvey6fXc2hehw9gHVFIW3TtGF1XkcbAu65qVXsA9D/T+uuoRVqhE+JCyFHFrO0ixRbZDRK1XJt1sA==}
@@ -1517,36 +1524,42 @@ packages:
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-L/y1/26q9L/uBqiW/JdOb/Dc94egFvNALUZV2WCGKQXc6UByPBMgdiEyW2dtoYxYYYYc+AKD+jr+wQPcvX2vrQ==}
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-EPE1K/80RQvPbLRJDJs1QmCIcH+7WRi0F73+oTe1582y9RtfGRuzAkzeBuAGRXAQEjRQw/RjtNqr6UTJ+8UuWQ==}
engines: {node: '>= 10'}
cpu: [ppc64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-B2jhWiB1ffw1nQBqLUP1h4+J1ovAxBOoe5N2IqDMOc63fsPZKNqF1PvO/dIem8z7LL4U4bsfmhy3gBfu547oNQ==}
engines: {node: '>= 10'}
cpu: [s390x]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-tbZDHnb9617lTnsDMGo/eAMZxnsQFnaRe+MszRqHguKfMwkisc9CCJnks/r1o84u5fECI+J/HOrKXgczq/3Oww==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-dV6cODlzbO8u6Anmv2N/ilQHq/AWz0xyltuXoLU3yUyXbZcnWYZuB2rL8OBGPmqNcD+x9NdScBNXh7vWN0naSQ==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-jIa9nb2HzOrfH0F8QQ9g3WE4aMH5vSI5/1NYVNm9ysCmNjCCtMXCAhlI3WKCdm/DwHf0zLqdrrtDFXODcNaqMw==}
@@ -1613,24 +1626,28 @@ packages:
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-jAasbIvjZXCgX0TCuEFQr+4D6Lla/3AAVx2LmDuMjgG4xoIXzjKWl7c4chuaD+TI+prWT0X6LJcdzFT+ROKGHQ==}
engines: {node: '>= 10'}
cpu: [arm64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-Plgk5rPqqK2nocBGajkMVbGm010Z7dnUgq0wtnYRZbzWWxwWcXfZMPa8EYxrK4eE8SzpI7VlZP1tdVsdjgGwMw==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [glibc]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-GW7AzGuWxtQkyHknHWYFdR0CHmW6is8rG2Rf4V6GNmMpmwtXt/ItWYWtBe4zqJWycMNazpfZKSw/BpT7/MVCXQ==}
engines: {node: '>= 10'}
cpu: [x64]
os: [linux]
+ libc: [musl]
'@napi-rs/[email protected]':
resolution: {integrity: sha512-/nQVSTrqSsn7YdAc2R7Ips/tnw5SPUcl3D7QrXCNGPqjbatIspnaexvaOYNyKMU6xPu+pc0BTnKVmqhlJJCPLA==}
@@ -2449,41 +2466,49 @@ packages:
resolution: {integrity: sha512-ukHZp9Vm07AlxqdOLFf8Bj4inzpt+ISbbODvwwHxX32GfcMLWYYJGAYWc13IGhWoElvWnI7D1M9ifDGyTNRGzg==}
cpu: [arm64]
os: [linux]
+ libc: [glibc]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-atkZ1OIt6t90kjQz1iqq6cN3OpfPG5zUJlO64Vd1ieYeqHRkOFeRgnWEobTePUHi34NlYr7mNZqIaAg7gjPUFg==}
cpu: [arm64]
os: [linux]
+ libc: [musl]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-HGgV4z3JwVF4Qvg2a1GhDnqn8mKLihy5Gp4rMfqNIAlERPSyIxo8oPQIL1XQKLYyyrkEEO99uwM+4cQGwhtbpQ==}
cpu: [ppc64]
os: [linux]
+ libc: [glibc]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-+vCO7iOR1s6VGefV02R2a702IASNWhSNm/MrR8RcWjKChmU0G+d1iC0oToUrGC4ovAEfstx2/O8EkROnfcLgrA==}
cpu: [riscv64]
os: [linux]
+ libc: [glibc]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-3folNmS5gYNFy/9HYzLcdeThqAGvDJU0gQKrhHn7RPWQa58yZ0ZPpBMk6KRSSO61+wkchkL+0sdcLsoe5wZW8g==}
cpu: [riscv64]
os: [linux]
+ libc: [musl]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-Ceo4z6g8vqPUKADROFL0b7MoyXlUdOBYCxTDu/fhd/5I3Ydk2S6bxkjJdzpBdlu+h2Z+eS9lTHFvkwkaORMPzw==}
cpu: [s390x]
os: [linux]
+ libc: [glibc]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-QyFW5e43imQLxiBpCImhOiP4hY9coWGjroEm8elDqGNNaA7vXooaMQS2N3avMQawSaKhsb/3RemxaZ852XG38Q==}
cpu: [x64]
os: [linux]
+ libc: [glibc]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-JhuCqCqktqQyQVc37V+eDiP3buCIuyCLpb92tUEyAP8nY3dy2b/ojMrH1ZNnJUlfY/67AqoZPL6nQGAB2WA3Sg==}
cpu: [x64]
os: [linux]
+ libc: [musl]
'@oxc-resolver/[email protected]':
resolution: {integrity: sha512-sMXm5Z2rfBwkCUespZBJCPhCVbgh/fpYQ23BQs0PmnvWoXrGQHWvnvg1p/GYmleN+nwe8strBjfutirZFiC5lA==}
@@ -2519,21 +2544,25 @@ packages:
resolution: {integrity: sha512-N1FqdKfwhVWPpMElv8qlGqdEefTbDYaRVhdGWOjs/2f7FESa5vX0cvA7ToqzkoXyXZI5DqByWiPML33njK30Kg==}
cpu: [arm64]
os: [linux]
+ libc: [glibc]
'@oxlint/[email protected]':
resolution: {integrity: sha512-v/BPuiateLBb7Gz1STb69EWjkgKdlPQ1NM56z+QQur21ly2hiMkBX2n0zEhqfu9PQVRUizu6AlsYuzcPY/zsIQ==}
cpu: [arm64]
os: [linux]
+ libc: [musl]
'@oxlint/[email protected]':
resolution: {integrity: sha512-gUTp8KIrSYt97dn+tRRC3LKnH4xlHKCwrPwiDcGmLbCxojuN9/H5mnIhPKEfwNuZNdoKGS/ABuq3neVyvRCRtQ==}
cpu: [x64]
os: [linux]
+ libc: [glibc]
'@oxlint/[email protected]':
resolution: {integrity: sha512-DpN6cW2HPjYXeENG0JBbmubO8LtfKt6qJqEMBw9gUevbyBaX+k+Jn7sYgh6S23wGOkzmTNphBsf/7ulj4nIVYA==}
cpu: [x64]
os: [linux]
+ libc: [musl]
'@oxlint/[email protected]':
resolution: {integrity: sha512-oXxJksnUTUMgJ0NvjKS1mrCXAy1ttPgIVacRSlxQ+1XHy+aJDMM7I8fsCtoKoEcTIpPaD98eqUqlLYs0H2MGjA==}
@@ -7522,7 +7551,7 @@ snapshots:
enabled: 2.0.0
kuler: 2.0.0
- '@dqbd/[email protected]': {}
+ '@dqbd/[email protected]': {}
dependencies:
@@ -10824,17 +10853,17 @@ snapshots:
dependencies:
'@types/yargs-parser': 21.0.3
dependencies:
'@safe-global/safe-apps-provider': 0.18.6([email protected])([email protected])([email protected])([email protected])
cbw-sdk: '@coinbase/[email protected]'
optionalDependencies:
typescript: 5.8.3
transitivePeerDependencies:
@@ -10866,11 +10895,11 @@ snapshots:
- utf-8-validate
- zod
dependencies:
eventemitter3: 5.0.1
mipd: 0.0.7([email protected])
optionalDependencies:
'@tanstack/query-core': 5.83.1
@@ -11420,6 +11449,11 @@ snapshots:
typescript: 5.8.3
zod: 3.22.4
+ optionalDependencies:
+ typescript: 5.8.3
+ zod: 3.24.2
+
optionalDependencies:
typescript: 5.8.3
@@ -13883,6 +13917,21 @@ snapshots:
transitivePeerDependencies:
- zod
+ dependencies:
+ '@adraffy/ens-normalize': 1.11.0
+ '@noble/ciphers': 1.3.0
+ '@noble/curves': 1.9.6
+ '@noble/hashes': 1.8.0
+ '@scure/bip32': 1.7.0
+ '@scure/bip39': 1.6.0
+ eventemitter3: 5.0.1
+ optionalDependencies:
+ typescript: 5.8.3
+ transitivePeerDependencies:
+ - zod
+
dependencies:
'@adraffy/ens-normalize': 1.11.0
@@ -15016,6 +15065,23 @@ snapshots:
- utf-8-validate
- zod
+ dependencies:
+ '@noble/curves': 1.9.2
+ '@noble/hashes': 1.8.0
+ '@scure/bip32': 1.7.0
+ '@scure/bip39': 1.6.0
+ optionalDependencies:
+ typescript: 5.8.3
+ transitivePeerDependencies:
+ - bufferutil
+ - utf-8-validate
+ - zod
+
dependencies:
'@noble/curves': 1.9.2
@@ -15040,11 +15106,11 @@ snapshots:
dependencies:
'@tanstack/react-query': 5.84.1([email protected])
react: 18.3.1
use-sync-external-store: 1.4.0([email protected])
optionalDependencies:
typescript: 5.8.3
transitivePeerDependencies:
@@ -15249,7 +15315,7 @@ snapshots:
zod: 3.25.76
transitivePeerDependencies:
diff --git a/apps/api/src/lib/extract/usage/model-prices.ts b/apps/api/src/lib/extract/usage/model-prices.ts
index 2a28c4fed..a5d183a85 100644
--- a/apps/api/src/lib/extract/usage/model-prices.ts
+++ b/apps/api/src/lib/extract/usage/model-prices.ts
@@ -7,39 +7,42 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
- input_cost_per_token_batches: 1.25e-6,
- output_cost_per_token_batches: 5e-6,
- cache_read_input_token_cost: 1.25e-6,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-audio-preview": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
+ input_cost_per_token: 0.0000025,
input_cost_per_audio_token: 0.0001,
- output_cost_per_token: 1e-5,
+ output_cost_per_token: 0.00001,
output_cost_per_audio_token: 0.0002,
litellm_provider: "openai",
mode: "chat",
@@ -48,14 +51,15 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-audio-preview-2024-10-01": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
+ input_cost_per_token: 0.0000025,
input_cost_per_audio_token: 0.0001,
- output_cost_per_token: 1e-5,
+ output_cost_per_token: 0.00001,
output_cost_per_audio_token: 0.0002,
litellm_provider: "openai",
mode: "chat",
@@ -64,6 +68,7 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-mini": {
max_tokens: 16384,
@@ -76,12 +81,14 @@ export const modelPrices = {
cache_read_input_token_cost: 7.5e-8,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-mini-2024-07-18": {
max_tokens: 16384,
@@ -94,416 +101,470 @@ export const modelPrices = {
cache_read_input_token_cost: 7.5e-8,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.025,
+ search_context_size_medium: 0.0275,
+ search_context_size_high: 0.03,
+ },
},
"o1-mini": {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
litellm_provider: "openai",
mode: "chat",
supports_vision: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
},
"o1-mini-2024-09-12": {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
+ cache_read_input_token_cost: 0.0000015,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_vision: true,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"o1-preview": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_vision: true,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"o1-preview-2024-09-12": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_vision: true,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"chatgpt-4o-latest": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-2024-05-13": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
- input_cost_per_token_batches: 2.5e-6,
- output_cost_per_token_batches: 7.5e-6,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
+ input_cost_per_token_batches: 0.0000025,
+ output_cost_per_token_batches: 0.0000075,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-2024-08-06": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
- input_cost_per_token_batches: 1.25e-6,
- output_cost_per_token_batches: 5e-6,
- cache_read_input_token_cost: 1.25e-6,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-turbo-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-0314": {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-0613": {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ deprecation_date: "2025-06-06",
+ supports_tool_choice: true,
},
"gpt-4-32k": {
max_tokens: 4096,
max_input_tokens: 32768,
max_output_tokens: 4096,
- input_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00006,
output_cost_per_token: 0.00012,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-32k-0314": {
max_tokens: 4096,
max_input_tokens: 32768,
max_output_tokens: 4096,
- input_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00006,
output_cost_per_token: 0.00012,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-32k-0613": {
max_tokens: 4096,
max_input_tokens: 32768,
max_output_tokens: 4096,
- input_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00006,
output_cost_per_token: 0.00012,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-turbo": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-turbo-2024-04-09": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-1106-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-0125-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4-vision-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
supports_vision: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ deprecation_date: "2024-12-06",
+ supports_tool_choice: true,
},
"gpt-4-1106-vision-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "openai",
mode: "chat",
supports_vision: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ deprecation_date: "2024-12-06",
+ supports_tool_choice: true,
},
"gpt-3.5-turbo": {
max_tokens: 4097,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-0301": {
max_tokens: 4097,
max_input_tokens: 4097,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-0613": {
max_tokens: 4097,
max_input_tokens: 4097,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-1106": {
max_tokens: 16385,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-0125": {
max_tokens: 16385,
max_input_tokens: 16385,
max_output_tokens: 4096,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-16k": {
max_tokens: 16385,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-3.5-turbo-16k-0613": {
max_tokens: 16385,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
litellm_provider: "openai",
mode: "chat",
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-3.5-turbo": {
max_tokens: 4096,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 6e-6,
- input_cost_per_token_batches: 1.5e-6,
- output_cost_per_token_batches: 3e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
+ input_cost_per_token_batches: 0.0000015,
+ output_cost_per_token_batches: 0.000003,
litellm_provider: "openai",
mode: "chat",
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-3.5-turbo-0125": {
max_tokens: 4096,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
litellm_provider: "openai",
mode: "chat",
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-3.5-turbo-1106": {
max_tokens: 4096,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
litellm_provider: "openai",
mode: "chat",
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-3.5-turbo-0613": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
litellm_provider: "openai",
mode: "chat",
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-4-0613": {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
source:
"OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing",
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-4o-2024-08-06": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 3.75e-6,
- output_cost_per_token: 1.5e-5,
- input_cost_per_token_batches: 1.875e-6,
- output_cost_per_token_batches: 7.5e-6,
+ input_cost_per_token: 0.00000375,
+ output_cost_per_token: 0.000015,
+ input_cost_per_token_batches: 0.000001875,
+ output_cost_per_token_batches: 0.0000075,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-4o-mini-2024-07-18": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
input_cost_per_token: 3e-7,
- output_cost_per_token: 1.2e-6,
+ output_cost_per_token: 0.0000012,
input_cost_per_token_batches: 1.5e-7,
output_cost_per_token_batches: 6e-7,
cache_read_input_token_cost: 1.5e-7,
@@ -513,17 +574,19 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:davinci-002": {
max_tokens: 16384,
max_input_tokens: 16384,
max_output_tokens: 4096,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 2e-6,
- input_cost_per_token_batches: 1e-6,
- output_cost_per_token_batches: 1e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000001,
litellm_provider: "text-completion-openai",
mode: "completion",
},
@@ -543,9 +606,9 @@ export const modelPrices = {
max_input_tokens: 8191,
output_vector_size: 3072,
input_cost_per_token: 1.3e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
input_cost_per_token_batches: 6.5e-8,
- output_cost_per_token_batches: 0.0,
+ output_cost_per_token_batches: 0,
litellm_provider: "openai",
mode: "embedding",
},
@@ -554,9 +617,9 @@ export const modelPrices = {
max_input_tokens: 8191,
output_vector_size: 1536,
input_cost_per_token: 2e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
input_cost_per_token_batches: 1e-8,
- output_cost_per_token_batches: 0.0,
+ output_cost_per_token_batches: 0,
litellm_provider: "openai",
mode: "embedding",
},
@@ -565,7 +628,7 @@ export const modelPrices = {
max_input_tokens: 8191,
output_vector_size: 1536,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
mode: "embedding",
},
@@ -573,9 +636,9 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
input_cost_per_token_batches: 5e-8,
- output_cost_per_token_batches: 0.0,
+ output_cost_per_token_batches: 0,
litellm_provider: "openai",
mode: "embedding",
},
@@ -583,112 +646,115 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
- mode: "moderations",
+ mode: "moderation",
},
"text-moderation-007": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
- mode: "moderations",
+ mode: "moderation",
},
"text-moderation-latest": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
- mode: "moderations",
+ mode: "moderation",
},
"256-x-256/dall-e-2": {
mode: "image_generation",
input_cost_per_pixel: 2.4414e-7,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"512-x-512/dall-e-2": {
mode: "image_generation",
input_cost_per_pixel: 6.86e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"1024-x-1024/dall-e-2": {
mode: "image_generation",
input_cost_per_pixel: 1.9e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"hd/1024-x-1792/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 6.539e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"hd/1792-x-1024/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 6.539e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"hd/1024-x-1024/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 7.629e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"standard/1024-x-1792/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 4.359e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"standard/1792-x-1024/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 4.359e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"standard/1024-x-1024/dall-e-3": {
mode: "image_generation",
input_cost_per_pixel: 3.81469e-8,
- output_cost_per_pixel: 0.0,
+ output_cost_per_pixel: 0,
litellm_provider: "openai",
},
"whisper-1": {
mode: "audio_transcription",
- input_cost_per_second: 0,
+ input_cost_per_second: 0.0001,
output_cost_per_second: 0.0001,
litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
},
"tts-1": {
mode: "audio_speech",
- input_cost_per_character: 1.5e-5,
+ input_cost_per_character: 0.000015,
litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/speech"],
},
"tts-1-hd": {
mode: "audio_speech",
- input_cost_per_character: 3e-5,
+ input_cost_per_character: 0.00003,
litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/speech"],
},
"azure/tts-1": {
mode: "audio_speech",
- input_cost_per_character: 1.5e-5,
+ input_cost_per_character: 0.000015,
litellm_provider: "azure",
},
"azure/tts-1-hd": {
mode: "audio_speech",
- input_cost_per_character: 3e-5,
+ input_cost_per_character: 0.00003,
litellm_provider: "azure",
},
"azure/whisper-1": {
mode: "audio_transcription",
- input_cost_per_second: 0,
+ input_cost_per_second: 0.0001,
output_cost_per_second: 0.0001,
litellm_provider: "azure",
},
@@ -696,78 +762,86 @@ export const modelPrices = {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.00000121,
+ output_cost_per_token: 0.00000484,
+ cache_read_input_token_cost: 6.05e-7,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"azure/o1-mini-2024-09-12": {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"azure/o1-preview": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"azure/o1-preview-2024-09-12": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "azure",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_reasoning: true,
supports_prompt_caching: true,
},
"azure/gpt-4o": {
- max_tokens: 4096,
+ max_tokens: 16384,
max_input_tokens: 128000,
- max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
- cache_read_input_token_cost: 1.25e-6,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure/gpt-4o-2024-08-06": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.75e-6,
- output_cost_per_token: 1.1e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
@@ -775,26 +849,29 @@ export const modelPrices = {
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure/gpt-4o-2024-05-13": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure/global-standard/gpt-4o-2024-08-06": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
@@ -802,6 +879,8 @@ export const modelPrices = {
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-08-20",
},
"azure/global-standard/gpt-4o-mini": {
max_tokens: 16384,
@@ -815,6 +894,7 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"azure/gpt-4o-mini": {
max_tokens: 16384,
@@ -830,202 +910,223 @@ export const modelPrices = {
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-turbo-2024-04-09": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-0125-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-1106-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-0613": {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-32k-0613": {
max_tokens: 4096,
max_input_tokens: 32768,
max_output_tokens: 4096,
- input_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00006,
output_cost_per_token: 0.00012,
litellm_provider: "azure",
mode: "chat",
+ supports_tool_choice: true,
},
"azure/gpt-4-32k": {
max_tokens: 4096,
max_input_tokens: 32768,
max_output_tokens: 4096,
- input_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00006,
output_cost_per_token: 0.00012,
litellm_provider: "azure",
mode: "chat",
+ supports_tool_choice: true,
},
"azure/gpt-4": {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-turbo": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-4-turbo-vision-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
litellm_provider: "azure",
mode: "chat",
supports_vision: true,
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-16k-0613": {
max_tokens: 4096,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-1106": {
max_tokens: 4096,
max_input_tokens: 16384,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ deprecation_date: "2025-03-31",
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-0613": {
max_tokens: 4097,
max_input_tokens: 4097,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ deprecation_date: "2025-02-13",
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-0301": {
max_tokens: 4097,
max_input_tokens: 4097,
max_output_tokens: 4096,
input_cost_per_token: 2e-7,
- output_cost_per_token: 2e-6,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ deprecation_date: "2025-02-13",
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-0125": {
max_tokens: 4096,
max_input_tokens: 16384,
max_output_tokens: 4096,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
+ deprecation_date: "2025-05-31",
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo-16k": {
max_tokens: 4096,
max_input_tokens: 16385,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
litellm_provider: "azure",
mode: "chat",
+ supports_tool_choice: true,
},
"azure/gpt-35-turbo": {
max_tokens: 4096,
max_input_tokens: 4097,
max_output_tokens: 4096,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"azure/gpt-3.5-turbo-instruct-0914": {
max_tokens: 4097,
max_input_tokens: 4097,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure_text",
mode: "completion",
},
"azure/gpt-35-turbo-instruct": {
max_tokens: 4097,
max_input_tokens: 4097,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure_text",
mode: "completion",
},
"azure/gpt-35-turbo-instruct-0914": {
max_tokens: 4097,
max_input_tokens: 4097,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "azure_text",
mode: "completion",
},
"azure/mistral-large-latest": {
max_tokens: 32000,
max_input_tokens: 32000,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
@@ -1033,8 +1134,8 @@ export const modelPrices = {
"azure/mistral-large-2402": {
max_tokens: 32000,
max_input_tokens: 32000,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
@@ -1043,8 +1144,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
@@ -1053,7 +1154,7 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "embedding",
},
@@ -1061,7 +1162,7 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "embedding",
},
@@ -1069,7 +1170,7 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
input_cost_per_token: 1.3e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "embedding",
},
@@ -1077,49 +1178,49 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
input_cost_per_token: 2e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "embedding",
},
"azure/standard/1024-x-1024/dall-e-3": {
input_cost_per_pixel: 3.81469e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/hd/1024-x-1024/dall-e-3": {
input_cost_per_pixel: 7.629e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/standard/1024-x-1792/dall-e-3": {
input_cost_per_pixel: 4.359e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/standard/1792-x-1024/dall-e-3": {
input_cost_per_pixel: 4.359e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/hd/1024-x-1792/dall-e-3": {
input_cost_per_pixel: 6.539e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/hd/1792-x-1024/dall-e-3": {
input_cost_per_pixel: 6.539e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
"azure/standard/1024-x-1024/dall-e-2": {
- input_cost_per_pixel: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_pixel: 0,
+ output_cost_per_token: 0,
litellm_provider: "azure",
mode: "image_generation",
},
@@ -1131,35 +1232,39 @@ export const modelPrices = {
output_cost_per_token: 7e-7,
litellm_provider: "azure_ai",
mode: "chat",
+ supports_tool_choice: true,
},
"azure_ai/mistral-large": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 4e-6,
- output_cost_per_token: 1.2e-5,
+ input_cost_per_token: 0.000004,
+ output_cost_per_token: 0.000012,
litellm_provider: "azure_ai",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"azure_ai/mistral-small": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
litellm_provider: "azure_ai",
supports_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
},
"azure_ai/Meta-Llama-3-70B-Instruct": {
max_tokens: 2048,
max_input_tokens: 8192,
max_output_tokens: 2048,
- input_cost_per_token: 1.1e-6,
+ input_cost_per_token: 0.0000011,
output_cost_per_token: 3.7e-7,
litellm_provider: "azure_ai",
mode: "chat",
+ supports_tool_choice: true,
},
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
max_tokens: 2048,
@@ -1171,37 +1276,40 @@ export const modelPrices = {
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
+ supports_tool_choice: true,
},
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
max_tokens: 2048,
max_input_tokens: 128000,
max_output_tokens: 2048,
- input_cost_per_token: 2.68e-6,
- output_cost_per_token: 3.54e-6,
+ input_cost_per_token: 0.00000268,
+ output_cost_per_token: 0.00000354,
litellm_provider: "azure_ai",
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
+ supports_tool_choice: true,
},
"azure_ai/Meta-Llama-3.1-405B-Instruct": {
max_tokens: 2048,
max_input_tokens: 128000,
max_output_tokens: 2048,
- input_cost_per_token: 5.33e-6,
- output_cost_per_token: 1.6e-5,
+ input_cost_per_token: 0.00000533,
+ output_cost_per_token: 0.000016,
litellm_provider: "azure_ai",
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
+ supports_tool_choice: true,
},
"azure_ai/cohere-rerank-v3-multilingual": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure_ai",
mode: "rerank",
},
@@ -1210,9 +1318,9 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure_ai",
mode: "rerank",
},
@@ -1221,9 +1329,10 @@ export const modelPrices = {
max_input_tokens: 512,
output_vector_size: 1024,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure_ai",
mode: "embedding",
+ supports_embedding_image_input: true,
source:
"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
},
@@ -1232,9 +1341,10 @@ export const modelPrices = {
max_input_tokens: 512,
output_vector_size: 1024,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "azure_ai",
mode: "embedding",
+ supports_embedding_image_input: true,
source:
"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
},
@@ -1251,8 +1361,8 @@ export const modelPrices = {
max_tokens: 16384,
max_input_tokens: 16384,
max_output_tokens: 4096,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
litellm_provider: "text-completion-openai",
mode: "completion",
},
@@ -1260,8 +1370,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 8192,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "text-completion-openai",
mode: "completion",
},
@@ -1269,8 +1379,8 @@ export const modelPrices = {
max_tokens: 4097,
max_input_tokens: 8192,
max_output_tokens: 4097,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "text-completion-openai",
mode: "completion",
},
@@ -1278,8 +1388,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 1.63e-6,
- output_cost_per_token: 5.51e-6,
+ input_cost_per_token: 0.00000163,
+ output_cost_per_token: 0.00000551,
litellm_provider: "anthropic",
mode: "chat",
},
@@ -1292,91 +1402,110 @@ export const modelPrices = {
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-small": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
litellm_provider: "mistral",
supports_function_calling: true,
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-small-latest": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
litellm_provider: "mistral",
supports_function_calling: true,
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-medium": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 2.7e-6,
- output_cost_per_token: 8.1e-6,
+ input_cost_per_token: 0.0000027,
+ output_cost_per_token: 0.0000081,
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-medium-latest": {
max_tokens: 8191,
- max_input_tokens: 32000,
+ max_input_tokens: 131072,
max_output_tokens: 8191,
- input_cost_per_token: 2.7e-6,
- output_cost_per_token: 8.1e-6,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.000002,
litellm_provider: "mistral",
mode: "chat",
+ supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-medium-2312": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 2.7e-6,
- output_cost_per_token: 8.1e-6,
+ input_cost_per_token: 0.0000027,
+ output_cost_per_token: 0.0000081,
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-large-latest": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-large-2402": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 4e-6,
- output_cost_per_token: 1.2e-5,
+ input_cost_per_token: 0.000004,
+ output_cost_per_token: 0.000012,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/mistral-large-2407": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 9e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000009,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/pixtral-12b-2409": {
max_tokens: 128000,
@@ -1389,6 +1518,8 @@ export const modelPrices = {
supports_function_calling: true,
supports_assistant_prefill: true,
supports_vision: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-mistral-7b": {
max_tokens: 8191,
@@ -1399,6 +1530,8 @@ export const modelPrices = {
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-mixtral-8x7b": {
max_tokens: 8191,
@@ -1410,37 +1543,45 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-mixtral-8x22b": {
max_tokens: 8191,
- max_input_tokens: 64000,
+ max_input_tokens: 65336,
max_output_tokens: 8191,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/codestral-latest": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/codestral-2405": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
litellm_provider: "mistral",
mode: "chat",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-mistral-nemo": {
max_tokens: 128000,
@@ -1452,6 +1593,8 @@ export const modelPrices = {
mode: "chat",
source: "https://mistral.ai/technology/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-mistral-nemo-2407": {
max_tokens: 128000,
@@ -1463,6 +1606,8 @@ export const modelPrices = {
mode: "chat",
source: "https://mistral.ai/technology/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/open-codestral-mamba": {
max_tokens: 256000,
@@ -1474,6 +1619,7 @@ export const modelPrices = {
mode: "chat",
source: "https://mistral.ai/technology/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"mistral/codestral-mamba-latest": {
max_tokens: 256000,
@@ -1485,6 +1631,7 @@ export const modelPrices = {
mode: "chat",
source: "https://mistral.ai/technology/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"mistral/mistral-embed": {
max_tokens: 8192,
@@ -1511,30 +1658,32 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "codestral",
mode: "chat",
source: "https://docs.mistral.ai/capabilities/code_generation/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"codestral/codestral-2405": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "codestral",
mode: "chat",
source: "https://docs.mistral.ai/capabilities/code_generation/",
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"text-completion-codestral/codestral-latest": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "text-completion-codestral",
mode: "completion",
source: "https://docs.mistral.ai/capabilities/code_generation/",
@@ -1543,8 +1692,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "text-completion-codestral",
mode: "completion",
source: "https://docs.mistral.ai/capabilities/code_generation/",
@@ -1573,6 +1722,7 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/llama3-8b-8192": {
max_tokens: 8192,
@@ -1582,8 +1732,7 @@ export const modelPrices = {
output_cost_per_token: 8e-8,
litellm_provider: "groq",
mode: "chat",
- supports_function_calling: true,
- supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/llama3-70b-8192": {
max_tokens: 8192,
@@ -1593,12 +1742,12 @@ export const modelPrices = {
output_cost_per_token: 7.9e-7,
litellm_provider: "groq",
mode: "chat",
- supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/llama-3.1-8b-instant": {
max_tokens: 8192,
- max_input_tokens: 8192,
+ max_input_tokens: 128000,
max_output_tokens: 8192,
input_cost_per_token: 5e-8,
output_cost_per_token: 8e-8,
@@ -1606,6 +1755,7 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/llama-3.1-70b-versatile": {
max_tokens: 8192,
@@ -1617,6 +1767,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-01-24",
},
"groq/llama-3.1-405b-reasoning": {
max_tokens: 8192,
@@ -1628,6 +1780,7 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/mixtral-8x7b-32768": {
max_tokens: 32768,
@@ -1639,6 +1792,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-03-20",
},
"groq/gemma-7b-it": {
max_tokens: 8192,
@@ -1650,6 +1805,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2024-12-18",
},
"groq/gemma2-9b-it": {
max_tokens: 8192,
@@ -1659,8 +1816,9 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "groq",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
+ supports_tool_choice: false,
},
"groq/llama3-groq-70b-8192-tool-use-preview": {
max_tokens: 8192,
@@ -1672,6 +1830,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-01-06",
},
"groq/llama3-groq-8b-8192-tool-use-preview": {
max_tokens: 8192,
@@ -1683,6 +1843,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-01-06",
},
"cerebras/llama3.1-8b": {
max_tokens: 128000,
@@ -1693,6 +1855,7 @@ export const modelPrices = {
litellm_provider: "cerebras",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"cerebras/llama3.1-70b": {
max_tokens: 128000,
@@ -1703,6 +1866,7 @@ export const modelPrices = {
litellm_provider: "cerebras",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"friendliai/mixtral-8x7b-instruct-v0-1": {
max_tokens: 32768,
@@ -1742,13 +1906,14 @@ export const modelPrices = {
output_cost_per_token: 5.51e-7,
litellm_provider: "anthropic",
mode: "chat",
+ supports_tool_choice: true,
},
"claude-2": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "anthropic",
mode: "chat",
},
@@ -1756,17 +1921,18 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 200000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "anthropic",
mode: "chat",
+ supports_tool_choice: true,
},
"claude-3-haiku-20240307": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
cache_creation_input_token_cost: 3e-7,
cache_read_input_token_cost: 3e-8,
litellm_provider: "anthropic",
@@ -1777,13 +1943,15 @@ export const modelPrices = {
supports_assistant_prefill: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-03-01",
+ supports_tool_choice: true,
},
"claude-3-haiku-latest": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
cache_creation_input_token_cost: 3e-7,
cache_read_input_token_cost: 3e-8,
litellm_provider: "anthropic",
@@ -1798,10 +1966,10 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
- cache_creation_input_token_cost: 1.875e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
@@ -1810,15 +1978,17 @@ export const modelPrices = {
supports_assistant_prefill: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-03-01",
+ supports_tool_choice: true,
},
"claude-3-opus-latest": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
- cache_creation_input_token_cost: 1.875e-5,
- cache_read_input_token_cost: 1.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
@@ -1826,13 +1996,16 @@ export const modelPrices = {
tool_use_system_prompt_tokens: 395,
supports_assistant_prefill: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2025-03-01",
+ supports_tool_choice: true,
},
"claude-3-sonnet-20240229": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
@@ -1841,14 +2014,16 @@ export const modelPrices = {
supports_assistant_prefill: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-07-21",
+ supports_tool_choice: true,
},
"claude-3-5-sonnet-20240620": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
- cache_creation_input_token_cost: 3.75e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
cache_read_input_token_cost: 3e-7,
litellm_provider: "anthropic",
mode: "chat",
@@ -1856,17 +2031,26 @@ export const modelPrices = {
supports_vision: true,
tool_use_system_prompt_tokens: 159,
supports_assistant_prefill: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-06-01",
+ supports_tool_choice: true,
},
"claude-3-5-sonnet-20241022": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
- cache_creation_input_token_cost: 3.75e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
cache_read_input_token_cost: 3e-7,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
@@ -1876,22 +2060,36 @@ export const modelPrices = {
supports_pdf_input: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-10-01",
+ supports_tool_choice: true,
+ supports_web_search: true,
},
"claude-3-5-sonnet-latest": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
- cache_creation_input_token_cost: 3.75e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
cache_read_input_token_cost: 3e-7,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
tool_use_system_prompt_tokens: 159,
supports_assistant_prefill: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2025-06-01",
+ supports_tool_choice: true,
+ supports_web_search: true,
},
"text-bison": {
max_tokens: 2048,
@@ -1956,8 +2154,8 @@ export const modelPrices = {
max_tokens: 1024,
max_input_tokens: 8192,
max_output_tokens: 1024,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 2.8e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.000028,
litellm_provider: "vertex_ai-text-models",
mode: "completion",
source:
@@ -1967,8 +2165,8 @@ export const modelPrices = {
max_tokens: 1024,
max_input_tokens: 8192,
max_output_tokens: 1024,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 2.8e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.000028,
litellm_provider: "vertex_ai-text-models",
mode: "completion",
source:
@@ -1986,6 +2184,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"chat-bison@001": {
max_tokens: 4096,
@@ -1999,6 +2198,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"chat-bison@002": {
max_tokens: 4096,
@@ -2012,6 +2212,8 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-04-09",
+ supports_tool_choice: true,
},
"chat-bison-32k": {
max_tokens: 8192,
@@ -2025,6 +2227,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"chat-bison-32k@002": {
max_tokens: 8192,
@@ -2038,6 +2241,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"code-bison": {
max_tokens: 1024,
@@ -2051,6 +2255,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"code-bison@001": {
max_tokens: 1024,
@@ -2160,6 +2365,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"codechat-bison": {
max_tokens: 1024,
@@ -2173,6 +2379,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"codechat-bison@001": {
max_tokens: 1024,
@@ -2186,6 +2393,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"codechat-bison@002": {
max_tokens: 1024,
@@ -2199,6 +2407,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"codechat-bison-32k": {
max_tokens: 8192,
@@ -2212,6 +2421,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"codechat-bison-32k@002": {
max_tokens: 8192,
@@ -2225,6 +2435,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"gemini-pro": {
max_tokens: 8192,
@@ -2234,12 +2445,14 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
+ supports_parallel_function_calling: true,
source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_tool_choice: true,
},
"gemini-1.0-pro": {
max_tokens: 8192,
@@ -2249,13 +2462,15 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
+ supports_parallel_function_calling: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models",
+ supports_tool_choice: true,
},
"gemini-1.0-pro-001": {
max_tokens: 8192,
@@ -2265,13 +2480,16 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-04-09",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.0-ultra": {
max_tokens: 8192,
@@ -2281,13 +2499,15 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
source:
"As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.0-ultra-001": {
max_tokens: 8192,
@@ -2297,13 +2517,15 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
source:
"As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.0-pro-002": {
max_tokens: 8192,
@@ -2313,32 +2535,35 @@ export const modelPrices = {
input_cost_per_video_per_second: 0.002,
input_cost_per_token: 5e-7,
input_cost_per_character: 1.25e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
output_cost_per_character: 3.75e-7,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-04-09",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro": {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
- input_cost_per_token: 1.25e-6,
+ input_cost_per_token: 0.00000125,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
- input_cost_per_token_above_128k_tokens: 2.5e-6,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
+ input_cost_per_token_above_128k_tokens: 0.0000025,
input_cost_per_character_above_128k_tokens: 6.25e-7,
- output_cost_per_token: 5e-6,
- output_cost_per_character: 1.25e-6,
- output_cost_per_token_above_128k_tokens: 1e-5,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_token: 0.000005,
+ output_cost_per_character: 0.00000125,
+ output_cost_per_token_above_128k_tokens: 0.00001,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_vision: true,
@@ -2349,25 +2574,26 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro-002": {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
- input_cost_per_token: 1.25e-6,
+ input_cost_per_token: 0.00000125,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
- input_cost_per_token_above_128k_tokens: 2.5e-6,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
+ input_cost_per_token_above_128k_tokens: 0.0000025,
input_cost_per_character_above_128k_tokens: 6.25e-7,
- output_cost_per_token: 5e-6,
- output_cost_per_character: 1.25e-6,
- output_cost_per_token_above_128k_tokens: 1e-5,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_token: 0.000005,
+ output_cost_per_character: 0.00000125,
+ output_cost_per_token_above_128k_tokens: 0.00001,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_vision: true,
@@ -2377,25 +2603,27 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro",
+ deprecation_date: "2025-09-24",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro-001": {
max_tokens: 8192,
max_input_tokens: 1000000,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
- input_cost_per_token: 1.25e-6,
+ input_cost_per_token: 0.00000125,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
- input_cost_per_token_above_128k_tokens: 2.5e-6,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
+ input_cost_per_token_above_128k_tokens: 0.0000025,
input_cost_per_character_above_128k_tokens: 6.25e-7,
- output_cost_per_token: 5e-6,
- output_cost_per_character: 1.25e-6,
- output_cost_per_token_above_128k_tokens: 1e-5,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_token: 0.000005,
+ output_cost_per_character: 0.00000125,
+ output_cost_per_token_above_128k_tokens: 0.00001,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_vision: true,
@@ -2405,25 +2633,27 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-05-24",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro-preview-0514": {
max_tokens: 8192,
max_input_tokens: 1000000,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
input_cost_per_token: 7.8125e-8,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
input_cost_per_token_above_128k_tokens: 1.5625e-7,
input_cost_per_character_above_128k_tokens: 6.25e-7,
output_cost_per_token: 3.125e-7,
- output_cost_per_character: 1.25e-6,
+ output_cost_per_character: 0.00000125,
output_cost_per_token_above_128k_tokens: 6.25e-7,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_system_messages: true,
@@ -2432,25 +2662,26 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro-preview-0215": {
max_tokens: 8192,
max_input_tokens: 1000000,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
input_cost_per_token: 7.8125e-8,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
input_cost_per_token_above_128k_tokens: 1.5625e-7,
input_cost_per_character_above_128k_tokens: 6.25e-7,
output_cost_per_token: 3.125e-7,
- output_cost_per_character: 1.25e-6,
+ output_cost_per_character: 0.00000125,
output_cost_per_token_above_128k_tokens: 6.25e-7,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_system_messages: true,
@@ -2459,25 +2690,26 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-pro-preview-0409": {
max_tokens: 8192,
max_input_tokens: 1000000,
max_output_tokens: 8192,
input_cost_per_image: 0.00032875,
- input_cost_per_audio_per_second: 3.125e-5,
+ input_cost_per_audio_per_second: 0.00003125,
input_cost_per_video_per_second: 0.00032875,
input_cost_per_token: 7.8125e-8,
input_cost_per_character: 3.125e-7,
input_cost_per_image_above_128k_tokens: 0.0006575,
input_cost_per_video_per_second_above_128k_tokens: 0.0006575,
- input_cost_per_audio_per_second_above_128k_tokens: 6.25e-5,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.0000625,
input_cost_per_token_above_128k_tokens: 1.5625e-7,
input_cost_per_character_above_128k_tokens: 6.25e-7,
output_cost_per_token: 3.125e-7,
- output_cost_per_character: 1.25e-6,
+ output_cost_per_character: 0.00000125,
output_cost_per_token_above_128k_tokens: 6.25e-7,
- output_cost_per_character_above_128k_tokens: 2.5e-6,
+ output_cost_per_character_above_128k_tokens: 0.0000025,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
supports_function_calling: true,
@@ -2485,6 +2717,7 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_parallel_function_calling: true,
},
"gemini-1.5-flash": {
max_tokens: 8192,
@@ -2496,16 +2729,16 @@ export const modelPrices = {
max_audio_length_hours: 8.4,
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
- input_cost_per_image: 2e-5,
- input_cost_per_video_per_second: 2e-5,
- input_cost_per_audio_per_second: 2e-6,
+ input_cost_per_image: 0.00002,
+ input_cost_per_video_per_second: 0.00002,
+ input_cost_per_audio_per_second: 0.000002,
input_cost_per_token: 7.5e-8,
input_cost_per_character: 1.875e-8,
- input_cost_per_token_above_128k_tokens: 1e-6,
+ input_cost_per_token_above_128k_tokens: 0.000001,
input_cost_per_character_above_128k_tokens: 2.5e-7,
- input_cost_per_image_above_128k_tokens: 4e-5,
- input_cost_per_video_per_second_above_128k_tokens: 4e-5,
- input_cost_per_audio_per_second_above_128k_tokens: 4e-6,
+ input_cost_per_image_above_128k_tokens: 0.00004,
+ input_cost_per_video_per_second_above_128k_tokens: 0.00004,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.000004,
output_cost_per_token: 3e-7,
output_cost_per_character: 7.5e-8,
output_cost_per_token_above_128k_tokens: 6e-7,
@@ -2518,6 +2751,8 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.5-flash-exp-0827": {
max_tokens: 8192,
@@ -2529,16 +2764,16 @@ export const modelPrices = {
max_audio_length_hours: 8.4,
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
- input_cost_per_image: 2e-5,
- input_cost_per_video_per_second: 2e-5,
- input_cost_per_audio_per_second: 2e-6,
+ input_cost_per_image: 0.00002,
+ input_cost_per_video_per_second: 0.00002,
+ input_cost_per_audio_per_second: 0.000002,
input_cost_per_token: 4.688e-9,
input_cost_per_character: 1.875e-8,
- input_cost_per_token_above_128k_tokens: 1e-6,
+ input_cost_per_token_above_128k_tokens: 0.000001,
input_cost_per_character_above_128k_tokens: 2.5e-7,
- input_cost_per_image_above_128k_tokens: 4e-5,
- input_cost_per_video_per_second_above_128k_tokens: 4e-5,
- input_cost_per_audio_per_second_above_128k_tokens: 4e-6,
+ input_cost_per_image_above_128k_tokens: 0.00004,
+ input_cost_per_video_per_second_above_128k_tokens: 0.00004,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.000004,
output_cost_per_token: 4.6875e-9,
output_cost_per_character: 1.875e-8,
output_cost_per_token_above_128k_tokens: 9.375e-9,
@@ -2551,6 +2786,8 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.5-flash-002": {
max_tokens: 8192,
@@ -2562,16 +2799,16 @@ export const modelPrices = {
max_audio_length_hours: 8.4,
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
- input_cost_per_image: 2e-5,
- input_cost_per_video_per_second: 2e-5,
- input_cost_per_audio_per_second: 2e-6,
+ input_cost_per_image: 0.00002,
+ input_cost_per_video_per_second: 0.00002,
+ input_cost_per_audio_per_second: 0.000002,
input_cost_per_token: 7.5e-8,
input_cost_per_character: 1.875e-8,
- input_cost_per_token_above_128k_tokens: 1e-6,
+ input_cost_per_token_above_128k_tokens: 0.000001,
input_cost_per_character_above_128k_tokens: 2.5e-7,
- input_cost_per_image_above_128k_tokens: 4e-5,
- input_cost_per_video_per_second_above_128k_tokens: 4e-5,
- input_cost_per_audio_per_second_above_128k_tokens: 4e-6,
+ input_cost_per_image_above_128k_tokens: 0.00004,
+ input_cost_per_video_per_second_above_128k_tokens: 0.00004,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.000004,
output_cost_per_token: 3e-7,
output_cost_per_character: 7.5e-8,
output_cost_per_token_above_128k_tokens: 6e-7,
@@ -2584,6 +2821,9 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash",
+ deprecation_date: "2025-09-24",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.5-flash-001": {
max_tokens: 8192,
@@ -2595,16 +2835,16 @@ export const modelPrices = {
max_audio_length_hours: 8.4,
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
- input_cost_per_image: 2e-5,
- input_cost_per_video_per_second: 2e-5,
- input_cost_per_audio_per_second: 2e-6,
+ input_cost_per_image: 0.00002,
+ input_cost_per_video_per_second: 0.00002,
+ input_cost_per_audio_per_second: 0.000002,
input_cost_per_token: 7.5e-8,
input_cost_per_character: 1.875e-8,
- input_cost_per_token_above_128k_tokens: 1e-6,
+ input_cost_per_token_above_128k_tokens: 0.000001,
input_cost_per_character_above_128k_tokens: 2.5e-7,
- input_cost_per_image_above_128k_tokens: 4e-5,
- input_cost_per_video_per_second_above_128k_tokens: 4e-5,
- input_cost_per_audio_per_second_above_128k_tokens: 4e-6,
+ input_cost_per_image_above_128k_tokens: 0.00004,
+ input_cost_per_video_per_second_above_128k_tokens: 0.00004,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.000004,
output_cost_per_token: 3e-7,
output_cost_per_character: 7.5e-8,
output_cost_per_token_above_128k_tokens: 6e-7,
@@ -2617,6 +2857,9 @@ export const modelPrices = {
supports_response_schema: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-05-24",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.5-flash-preview-0514": {
max_tokens: 8192,
@@ -2628,16 +2871,16 @@ export const modelPrices = {
max_audio_length_hours: 8.4,
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
- input_cost_per_image: 2e-5,
- input_cost_per_video_per_second: 2e-5,
- input_cost_per_audio_per_second: 2e-6,
+ input_cost_per_image: 0.00002,
+ input_cost_per_video_per_second: 0.00002,
+ input_cost_per_audio_per_second: 0.000002,
input_cost_per_token: 7.5e-8,
input_cost_per_character: 1.875e-8,
- input_cost_per_token_above_128k_tokens: 1e-6,
+ input_cost_per_token_above_128k_tokens: 0.000001,
input_cost_per_character_above_128k_tokens: 2.5e-7,
- input_cost_per_image_above_128k_tokens: 4e-5,
- input_cost_per_video_per_second_above_128k_tokens: 4e-5,
- input_cost_per_audio_per_second_above_128k_tokens: 4e-6,
+ input_cost_per_image_above_128k_tokens: 0.00004,
+ input_cost_per_video_per_second_above_128k_tokens: 0.00004,
+ input_cost_per_audio_per_second_above_128k_tokens: 0.000004,
output_cost_per_token: 4.6875e-9,
output_cost_per_character: 1.875e-8,
output_cost_per_token_above_128k_tokens: 9.375e-9,
@@ -2649,6 +2892,8 @@ export const modelPrices = {
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-pro-experimental": {
max_tokens: 8192,
@@ -2664,6 +2909,7 @@ export const modelPrices = {
supports_tool_choice: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental",
+ supports_parallel_function_calling: true,
},
"gemini-flash-experimental": {
max_tokens: 8192,
@@ -2679,6 +2925,7 @@ export const modelPrices = {
supports_tool_choice: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental",
+ supports_parallel_function_calling: true,
},
"gemini-pro-vision": {
max_tokens: 2048,
@@ -2687,15 +2934,18 @@ export const modelPrices = {
max_images_per_prompt: 16,
max_videos_per_prompt: 1,
max_video_length: 2,
- input_cost_per_token: 2.5e-7,
- output_cost_per_token: 5e-7,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ input_cost_per_image: 0.0025,
litellm_provider: "vertex_ai-vision-models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
- },
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ },
"gemini-1.0-pro-vision": {
max_tokens: 2048,
max_input_tokens: 16384,
@@ -2703,14 +2953,17 @@ export const modelPrices = {
max_images_per_prompt: 16,
max_videos_per_prompt: 1,
max_video_length: 2,
- input_cost_per_token: 2.5e-7,
- output_cost_per_token: 5e-7,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ input_cost_per_image: 0.0025,
litellm_provider: "vertex_ai-vision-models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"gemini-1.0-pro-vision-001": {
max_tokens: 2048,
@@ -2719,162 +2972,186 @@ export const modelPrices = {
max_images_per_prompt: 16,
max_videos_per_prompt: 1,
max_video_length: 2,
- input_cost_per_token: 2.5e-7,
- output_cost_per_token: 5e-7,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ input_cost_per_image: 0.0025,
litellm_provider: "vertex_ai-vision-models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ deprecation_date: "2025-04-09",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
},
"medlm-medium": {
max_tokens: 8192,
max_input_tokens: 32768,
max_output_tokens: 8192,
input_cost_per_character: 5e-7,
- output_cost_per_character: 1e-6,
+ output_cost_per_character: 0.000001,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"medlm-large": {
max_tokens: 1024,
max_input_tokens: 8192,
max_output_tokens: 1024,
- input_cost_per_character: 5e-6,
- output_cost_per_character: 1.5e-5,
+ input_cost_per_character: 0.000005,
+ output_cost_per_character: 0.000015,
litellm_provider: "vertex_ai-language-models",
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-sonnet@20240229": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-5-sonnet@20240620": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-5-sonnet-v2@20241022": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-haiku@20240307": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-opus@20240229": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/meta/llama3-405b-instruct-maas": {
max_tokens: 32000,
max_input_tokens: 32000,
max_output_tokens: 32000,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "vertex_ai-llama_models",
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
},
"vertex_ai/meta/llama3-70b-instruct-maas": {
max_tokens: 32000,
max_input_tokens: 32000,
max_output_tokens: 32000,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "vertex_ai-llama_models",
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
},
"vertex_ai/meta/llama3-8b-instruct-maas": {
max_tokens: 32000,
max_input_tokens: 32000,
max_output_tokens: 32000,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "vertex_ai-llama_models",
mode: "chat",
source:
"https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
},
"vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 2048,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "vertex_ai-llama_models",
mode: "chat",
supports_system_messages: true,
supports_vision: true,
source:
"https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
+ supports_tool_choice: true,
+ metadata: {
+ notes:
+ "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA.",
+ },
},
"vertex_ai/mistral-large@latest": {
max_tokens: 8191,
max_input_tokens: 128000,
max_output_tokens: 8191,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/mistral-large@2407": {
max_tokens: 8191,
max_input_tokens: 128000,
max_output_tokens: 8191,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/mistral-nemo@latest": {
max_tokens: 128000,
@@ -2885,6 +3162,7 @@ export const modelPrices = {
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/jamba-1.5-mini@001": {
max_tokens: 256000,
@@ -2894,15 +3172,17 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "vertex_ai-ai21_models",
mode: "chat",
+ supports_tool_choice: true,
},
"vertex_ai/jamba-1.5-large@001": {
max_tokens: 256000,
max_input_tokens: 256000,
max_output_tokens: 256000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 8e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
litellm_provider: "vertex_ai-ai21_models",
mode: "chat",
+ supports_tool_choice: true,
},
"vertex_ai/jamba-1.5": {
max_tokens: 256000,
@@ -2912,6 +3192,7 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "vertex_ai-ai21_models",
mode: "chat",
+ supports_tool_choice: true,
},
"vertex_ai/jamba-1.5-mini": {
max_tokens: 256000,
@@ -2921,25 +3202,28 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "vertex_ai-ai21_models",
mode: "chat",
+ supports_tool_choice: true,
},
"vertex_ai/jamba-1.5-large": {
max_tokens: 256000,
max_input_tokens: 256000,
max_output_tokens: 256000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 8e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
litellm_provider: "vertex_ai-ai21_models",
mode: "chat",
+ supports_tool_choice: true,
},
"vertex_ai/mistral-nemo@2407": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000003,
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/codestral@latest": {
max_tokens: 128000,
@@ -2950,6 +3234,7 @@ export const modelPrices = {
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/codestral@2405": {
max_tokens: 128000,
@@ -2960,6 +3245,7 @@ export const modelPrices = {
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/imagegeneration@006": {
output_cost_per_image: 0.02,
@@ -3162,7 +3448,7 @@ export const modelPrices = {
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
cache_read_input_token_cost: 1.875e-8,
- cache_creation_input_token_cost: 1e-6,
+ cache_creation_input_token_cost: 0.000001,
input_cost_per_token: 7.5e-8,
input_cost_per_token_above_128k_tokens: 1.5e-7,
output_cost_per_token: 3e-7,
@@ -3177,6 +3463,8 @@ export const modelPrices = {
tpm: 4000000,
rpm: 2000,
source: "https://ai.google.dev/pricing",
+ deprecation_date: "2025-09-24",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash-001": {
max_tokens: 8192,
@@ -3189,7 +3477,7 @@ export const modelPrices = {
max_audio_per_prompt: 1,
max_pdf_size_mb: 30,
cache_read_input_token_cost: 1.875e-8,
- cache_creation_input_token_cost: 1e-6,
+ cache_creation_input_token_cost: 0.000001,
input_cost_per_token: 7.5e-8,
input_cost_per_token_above_128k_tokens: 1.5e-7,
output_cost_per_token: 3e-7,
@@ -3204,6 +3492,8 @@ export const modelPrices = {
tpm: 4000000,
rpm: 2000,
source: "https://ai.google.dev/pricing",
+ deprecation_date: "2025-05-24",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash": {
max_tokens: 8192,
@@ -3228,6 +3518,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 2000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash-latest": {
max_tokens: 8192,
@@ -3253,6 +3544,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 2000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash-8b-exp-0924": {
max_tokens: 8192,
@@ -3278,6 +3570,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 4000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash-exp-0827": {
max_tokens: 8192,
@@ -3302,6 +3595,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 2000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-flash-8b-exp-0827": {
max_tokens: 8192,
@@ -3326,6 +3620,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 4000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-pro": {
max_tokens: 8192,
@@ -3333,8 +3628,8 @@ export const modelPrices = {
max_output_tokens: 8192,
input_cost_per_token: 3.5e-7,
input_cost_per_token_above_128k_tokens: 7e-7,
- output_cost_per_token: 1.05e-6,
- output_cost_per_token_above_128k_tokens: 2.1e-6,
+ output_cost_per_token: 0.00000105,
+ output_cost_per_token_above_128k_tokens: 0.0000021,
litellm_provider: "gemini",
mode: "chat",
supports_function_calling: true,
@@ -3342,15 +3637,16 @@ export const modelPrices = {
tpm: 120000,
rpm: 360,
source: "https://ai.google.dev/gemini-api/docs/models/gemini",
+ supports_tool_choice: true,
},
"gemini/gemini-1.5-pro": {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
- input_cost_per_token: 3.5e-6,
- input_cost_per_token_above_128k_tokens: 7e-6,
- output_cost_per_token: 1.05e-5,
- output_cost_per_token_above_128k_tokens: 2.1e-5,
+ input_cost_per_token: 0.0000035,
+ input_cost_per_token_above_128k_tokens: 0.000007,
+ output_cost_per_token: 0.0000105,
+ output_cost_per_token_above_128k_tokens: 0.000021,
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
@@ -3366,10 +3662,10 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
- input_cost_per_token: 3.5e-6,
- input_cost_per_token_above_128k_tokens: 7e-6,
- output_cost_per_token: 1.05e-5,
- output_cost_per_token_above_128k_tokens: 2.1e-5,
+ input_cost_per_token: 0.0000035,
+ input_cost_per_token_above_128k_tokens: 0.000007,
+ output_cost_per_token: 0.0000105,
+ output_cost_per_token_above_128k_tokens: 0.000021,
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
@@ -3381,15 +3677,16 @@ export const modelPrices = {
tpm: 4000000,
rpm: 1000,
source: "https://ai.google.dev/pricing",
+ deprecation_date: "2025-09-24",
},
"gemini/gemini-1.5-pro-001": {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
- input_cost_per_token: 3.5e-6,
- input_cost_per_token_above_128k_tokens: 7e-6,
- output_cost_per_token: 1.05e-5,
- output_cost_per_token_above_128k_tokens: 2.1e-5,
+ input_cost_per_token: 0.0000035,
+ input_cost_per_token_above_128k_tokens: 0.000007,
+ output_cost_per_token: 0.0000105,
+ output_cost_per_token_above_128k_tokens: 0.000021,
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
@@ -3401,15 +3698,16 @@ export const modelPrices = {
tpm: 4000000,
rpm: 1000,
source: "https://ai.google.dev/pricing",
+ deprecation_date: "2025-05-24",
},
"gemini/gemini-1.5-pro-exp-0801": {
max_tokens: 8192,
max_input_tokens: 2097152,
max_output_tokens: 8192,
- input_cost_per_token: 3.5e-6,
- input_cost_per_token_above_128k_tokens: 7e-6,
- output_cost_per_token: 1.05e-5,
- output_cost_per_token_above_128k_tokens: 2.1e-5,
+ input_cost_per_token: 0.0000035,
+ input_cost_per_token_above_128k_tokens: 0.000007,
+ output_cost_per_token: 0.0000105,
+ output_cost_per_token_above_128k_tokens: 0.000021,
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
@@ -3444,10 +3742,10 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 1048576,
max_output_tokens: 8192,
- input_cost_per_token: 3.5e-6,
- input_cost_per_token_above_128k_tokens: 7e-6,
- output_cost_per_token: 1.05e-6,
- output_cost_per_token_above_128k_tokens: 2.1e-5,
+ input_cost_per_token: 0.0000035,
+ input_cost_per_token_above_128k_tokens: 0.000007,
+ output_cost_per_token: 0.00000105,
+ output_cost_per_token_above_128k_tokens: 0.000021,
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
@@ -3465,8 +3763,8 @@ export const modelPrices = {
max_output_tokens: 2048,
input_cost_per_token: 3.5e-7,
input_cost_per_token_above_128k_tokens: 7e-7,
- output_cost_per_token: 1.05e-6,
- output_cost_per_token_above_128k_tokens: 2.1e-6,
+ output_cost_per_token: 0.00000105,
+ output_cost_per_token_above_128k_tokens: 0.0000021,
litellm_provider: "gemini",
mode: "chat",
supports_function_calling: true,
@@ -3476,30 +3774,33 @@ export const modelPrices = {
rpm: 360,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"gemini/gemini-gemma-2-27b-it": {
max_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 3.5e-7,
- output_cost_per_token: 1.05e-6,
+ output_cost_per_token: 0.00000105,
litellm_provider: "gemini",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"gemini/gemini-gemma-2-9b-it": {
max_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 3.5e-7,
- output_cost_per_token: 1.05e-6,
+ output_cost_per_token: 0.00000105,
litellm_provider: "gemini",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+ supports_tool_choice: true,
},
"command-r": {
max_tokens: 4096,
@@ -3510,6 +3811,7 @@ export const modelPrices = {
litellm_provider: "cohere_chat",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"command-r-08-2024": {
max_tokens: 4096,
@@ -3520,6 +3822,7 @@ export const modelPrices = {
litellm_provider: "cohere_chat",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"command-light": {
max_tokens: 4096,
@@ -3529,33 +3832,36 @@ export const modelPrices = {
output_cost_per_token: 6e-7,
litellm_provider: "cohere_chat",
mode: "chat",
+ supports_tool_choice: true,
},
"command-r-plus": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
litellm_provider: "cohere_chat",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"command-r-plus-08-2024": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
litellm_provider: "cohere_chat",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"command-nightly": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000002,
litellm_provider: "cohere",
mode: "completion",
},
@@ -3563,8 +3869,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000002,
litellm_provider: "cohere",
mode: "completion",
},
@@ -3573,9 +3879,9 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "rerank",
},
@@ -3584,9 +3890,9 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "rerank",
},
@@ -3595,9 +3901,9 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "rerank",
},
@@ -3606,9 +3912,9 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "rerank",
},
@@ -3617,7 +3923,7 @@ export const modelPrices = {
max_input_tokens: 1024,
input_cost_per_token: 1e-7,
input_cost_per_image: 0.0001,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "embedding",
supports_image_input: true,
@@ -3631,7 +3937,7 @@ export const modelPrices = {
max_tokens: 1024,
max_input_tokens: 1024,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "embedding",
},
@@ -3639,15 +3945,16 @@ export const modelPrices = {
max_tokens: 1024,
max_input_tokens: 1024,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
+ supports_embedding_image_input: true,
mode: "embedding",
},
"embed-english-v2.0": {
max_tokens: 4096,
max_input_tokens: 4096,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "embedding",
},
@@ -3655,7 +3962,7 @@ export const modelPrices = {
max_tokens: 1024,
max_input_tokens: 1024,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "embedding",
},
@@ -3663,7 +3970,7 @@ export const modelPrices = {
max_tokens: 768,
max_input_tokens: 768,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "embedding",
},
@@ -3675,6 +3982,7 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-2-13b-chat": {
max_tokens: 4096,
@@ -3684,24 +3992,27 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-2-70b": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 6.5e-7,
- output_cost_per_token: 2.75e-6,
+ output_cost_per_token: 0.00000275,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-2-70b-chat": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 6.5e-7,
- output_cost_per_token: 2.75e-6,
+ output_cost_per_token: 0.00000275,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-2-7b": {
max_tokens: 4096,
@@ -3711,6 +4022,7 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-2-7b-chat": {
max_tokens: 4096,
@@ -3720,24 +4032,27 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-3-70b": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 6.5e-7,
- output_cost_per_token: 2.75e-6,
+ output_cost_per_token: 0.00000275,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-3-70b-instruct": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 6.5e-7,
- output_cost_per_token: 2.75e-6,
+ output_cost_per_token: 0.00000275,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-3-8b": {
max_tokens: 8086,
@@ -3747,6 +4062,7 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/meta/llama-3-8b-instruct": {
max_tokens: 8086,
@@ -3756,6 +4072,7 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/mistralai/mistral-7b-v0.1": {
max_tokens: 4096,
@@ -3765,6 +4082,7 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/mistralai/mistral-7b-instruct-v0.2": {
max_tokens: 4096,
@@ -3774,15 +4092,17 @@ export const modelPrices = {
output_cost_per_token: 2.5e-7,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"replicate/mistralai/mixtral-8x7b-instruct-v0.1": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 3e-7,
- output_cost_per_token: 1e-6,
+ output_cost_per_token: 0.000001,
litellm_provider: "replicate",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/deepseek/deepseek-coder": {
max_tokens: 8192,
@@ -3793,25 +4113,28 @@ export const modelPrices = {
litellm_provider: "openrouter",
supports_prompt_caching: true,
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/microsoft/wizardlm-2-8x22b:nitro": {
max_tokens: 65536,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/google/gemini-pro-1.5": {
max_tokens: 8192,
max_input_tokens: 1000000,
max_output_tokens: 8192,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 7.5e-6,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.0000075,
input_cost_per_image: 0.00265,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/mistralai/mixtral-8x22b-instruct": {
max_tokens: 65536,
@@ -3819,13 +4142,15 @@ export const modelPrices = {
output_cost_per_token: 6.5e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/cohere/command-r-plus": {
max_tokens: 128000,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/databricks/dbrx-instruct": {
max_tokens: 32768,
@@ -3833,36 +4158,39 @@ export const modelPrices = {
output_cost_per_token: 6e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-haiku": {
max_tokens: 200000,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
input_cost_per_image: 0.0004,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-haiku-20240307": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
tool_use_system_prompt_tokens: 264,
+ supports_tool_choice: true,
},
"anthropic/claude-3-5-sonnet-20241022": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
- cache_creation_input_token_cost: 3.75e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
cache_read_input_token_cost: 3e-7,
litellm_provider: "anthropic",
mode: "chat",
@@ -3876,9 +4204,9 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
- cache_creation_input_token_cost: 3.75e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
cache_read_input_token_cost: 3e-7,
litellm_provider: "anthropic",
mode: "chat",
@@ -3889,46 +4217,52 @@ export const modelPrices = {
supports_prompt_caching: true,
},
"openrouter/anthropic/claude-3.5-sonnet": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
tool_use_system_prompt_tokens: 159,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3.5-sonnet:beta": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
tool_use_system_prompt_tokens: 159,
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-sonnet": {
max_tokens: 200000,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
input_cost_per_image: 0.0048,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/mistralai/mistral-large": {
max_tokens: 32000,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/cognitivecomputations/dolphin-mixtral-8x7b": {
max_tokens: 32769,
@@ -3936,6 +4270,7 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/google/gemini-pro-vision": {
max_tokens: 45875,
@@ -3946,6 +4281,7 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/fireworks/firellava-13b": {
max_tokens: 4096,
@@ -3953,20 +4289,23 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-3-8b-instruct:free": {
max_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-3-8b-instruct:extended": {
max_tokens: 16384,
input_cost_per_token: 2.25e-7,
- output_cost_per_token: 2.25e-6,
+ output_cost_per_token: 0.00000225,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-3-70b-instruct:nitro": {
max_tokens: 8192,
@@ -3974,6 +4313,7 @@ export const modelPrices = {
output_cost_per_token: 9e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-3-70b-instruct": {
max_tokens: 8192,
@@ -3981,137 +4321,151 @@ export const modelPrices = {
output_cost_per_token: 7.9e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/openai/o1-mini": {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_tool_choice: true,
},
"openrouter/openai/o1-mini-2024-09-12": {
max_tokens: 65536,
max_input_tokens: 128000,
max_output_tokens: 65536,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.2e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_tool_choice: true,
},
"openrouter/openai/o1-preview": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_tool_choice: true,
},
"openrouter/openai/o1-preview-2024-09-12": {
max_tokens: 32768,
max_input_tokens: 128000,
max_output_tokens: 32768,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: false,
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-4o": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-4o-2024-05-13": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-4-vision-preview": {
max_tokens: 130000,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 3e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
input_cost_per_image: 0.01445,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-3.5-turbo": {
max_tokens: 4095,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-3.5-turbo-16k": {
max_tokens: 16383,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/openai/gpt-4": {
max_tokens: 8192,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 6e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-instant-v1": {
max_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 1.63e-6,
- output_cost_per_token: 5.51e-6,
+ input_cost_per_token: 0.00000163,
+ output_cost_per_token: 0.00000551,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-2": {
max_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 1.102e-5,
- output_cost_per_token: 3.268e-5,
+ input_cost_per_token: 0.00001102,
+ output_cost_per_token: 0.00003268,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-opus": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
tool_use_system_prompt_tokens: 395,
+ supports_tool_choice: true,
},
"openrouter/google/palm-2-chat-bison": {
max_tokens: 25804,
@@ -4119,6 +4473,7 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/google/palm-2-codechat-bison": {
max_tokens: 20070,
@@ -4126,6 +4481,7 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-2-13b-chat": {
max_tokens: 4096,
@@ -4133,13 +4489,15 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/llama-2-70b-chat": {
max_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 1.5e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.0000015,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/meta-llama/codellama-34b-instruct": {
max_tokens: 8192,
@@ -4147,6 +4505,7 @@ export const modelPrices = {
output_cost_per_token: 5e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/nousresearch/nous-hermes-llama2-13b": {
max_tokens: 4096,
@@ -4154,41 +4513,47 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/mancer/weaver": {
max_tokens: 8000,
- input_cost_per_token: 5.625e-6,
- output_cost_per_token: 5.625e-6,
+ input_cost_per_token: 0.000005625,
+ output_cost_per_token: 0.000005625,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/gryphe/mythomax-l2-13b": {
max_tokens: 8192,
- input_cost_per_token: 1.875e-6,
- output_cost_per_token: 1.875e-6,
+ input_cost_per_token: 0.000001875,
+ output_cost_per_token: 0.000001875,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/jondurbin/airoboros-l2-70b-2.1": {
max_tokens: 4096,
- input_cost_per_token: 1.3875e-5,
- output_cost_per_token: 1.3875e-5,
+ input_cost_per_token: 0.000013875,
+ output_cost_per_token: 0.000013875,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/undi95/remm-slerp-l2-13b": {
max_tokens: 6144,
- input_cost_per_token: 1.875e-6,
- output_cost_per_token: 1.875e-6,
+ input_cost_per_token: 0.000001875,
+ output_cost_per_token: 0.000001875,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/pygmalionai/mythalion-13b": {
max_tokens: 4096,
- input_cost_per_token: 1.875e-6,
- output_cost_per_token: 1.875e-6,
+ input_cost_per_token: 0.000001875,
+ output_cost_per_token: 0.000001875,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/mistralai/mistral-7b-instruct": {
max_tokens: 8192,
@@ -4196,20 +4561,22 @@ export const modelPrices = {
output_cost_per_token: 1.3e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/mistralai/mistral-7b-instruct:free": {
max_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"j2-ultra": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000015,
litellm_provider: "ai21",
mode: "completion",
},
@@ -4221,15 +4588,17 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "ai21",
mode: "chat",
+ supports_tool_choice: true,
},
"jamba-1.5-large@001": {
max_tokens: 256000,
max_input_tokens: 256000,
max_output_tokens: 256000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 8e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
litellm_provider: "ai21",
mode: "chat",
+ supports_tool_choice: true,
},
"jamba-1.5": {
max_tokens: 256000,
@@ -4239,6 +4608,7 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "ai21",
mode: "chat",
+ supports_tool_choice: true,
},
"jamba-1.5-mini": {
max_tokens: 256000,
@@ -4248,22 +4618,24 @@ export const modelPrices = {
output_cost_per_token: 4e-7,
litellm_provider: "ai21",
mode: "chat",
+ supports_tool_choice: true,
},
"jamba-1.5-large": {
max_tokens: 256000,
max_input_tokens: 256000,
max_output_tokens: 256000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 8e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
litellm_provider: "ai21",
mode: "chat",
+ supports_tool_choice: true,
},
"j2-mid": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 1e-5,
- output_cost_per_token: 1e-5,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00001,
litellm_provider: "ai21",
mode: "completion",
},
@@ -4271,8 +4643,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000003,
litellm_provider: "ai21",
mode: "completion",
},
@@ -4296,29 +4668,29 @@ export const modelPrices = {
},
"luminous-base": {
max_tokens: 2048,
- input_cost_per_token: 3e-5,
- output_cost_per_token: 3.3e-5,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.000033,
litellm_provider: "aleph_alpha",
mode: "completion",
},
"luminous-base-control": {
max_tokens: 2048,
- input_cost_per_token: 3.75e-5,
- output_cost_per_token: 4.125e-5,
+ input_cost_per_token: 0.0000375,
+ output_cost_per_token: 0.00004125,
litellm_provider: "aleph_alpha",
mode: "chat",
},
"luminous-extended": {
max_tokens: 2048,
- input_cost_per_token: 4.5e-5,
- output_cost_per_token: 4.95e-5,
+ input_cost_per_token: 0.000045,
+ output_cost_per_token: 0.0000495,
litellm_provider: "aleph_alpha",
mode: "completion",
},
"luminous-extended-control": {
max_tokens: 2048,
- input_cost_per_token: 5.625e-5,
- output_cost_per_token: 6.1875e-5,
+ input_cost_per_token: 0.00005625,
+ output_cost_per_token: 0.000061875,
litellm_provider: "aleph_alpha",
mode: "chat",
},
@@ -4340,8 +4712,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
max_output_tokens: 8191,
- input_cost_per_token: 1.25e-5,
- output_cost_per_token: 1.25e-5,
+ input_cost_per_token: 0.0000125,
+ output_cost_per_token: 0.0000125,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4349,8 +4721,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 8191,
max_output_tokens: 8191,
- input_cost_per_token: 1.88e-5,
- output_cost_per_token: 1.88e-5,
+ input_cost_per_token: 0.0000188,
+ output_cost_per_token: 0.0000188,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4377,8 +4749,8 @@ export const modelPrices = {
max_tokens: 8000,
max_input_tokens: 42000,
max_output_tokens: 8000,
- input_cost_per_token: 1.3e-6,
- output_cost_per_token: 1.7e-6,
+ input_cost_per_token: 0.0000013,
+ output_cost_per_token: 0.0000017,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4387,7 +4759,7 @@ export const modelPrices = {
max_input_tokens: 42000,
max_output_tokens: 32000,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4396,7 +4768,7 @@ export const modelPrices = {
max_input_tokens: 8192,
output_vector_size: 1536,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "bedrock",
mode: "embedding",
},
@@ -4405,7 +4777,7 @@ export const modelPrices = {
max_input_tokens: 8192,
output_vector_size: 1024,
input_cost_per_token: 2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "bedrock",
mode: "embedding",
},
@@ -4417,6 +4789,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"mistral.mixtral-8x7b-instruct-v0:1": {
max_tokens: 8191,
@@ -4426,13 +4799,14 @@ export const modelPrices = {
output_cost_per_token: 7e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"mistral.mistral-large-2402-v1:0": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -4441,18 +4815,19 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 128000,
max_output_tokens: 8191,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 9e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000009,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"mistral.mistral-small-2402-v1:0": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -4465,6 +4840,7 @@ export const modelPrices = {
output_cost_per_token: 7e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": {
max_tokens: 8191,
@@ -4474,6 +4850,7 @@ export const modelPrices = {
output_cost_per_token: 7e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": {
max_tokens: 8191,
@@ -4483,6 +4860,7 @@ export const modelPrices = {
output_cost_per_token: 9.1e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": {
max_tokens: 8191,
@@ -4492,6 +4870,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": {
max_tokens: 8191,
@@ -4501,6 +4880,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": {
max_tokens: 8191,
@@ -4510,22 +4890,24 @@ export const modelPrices = {
output_cost_per_token: 2.6e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/mistral.mistral-large-2402-v1:0": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_function_calling: true,
},
"bedrock/us-west-2/mistral.mistral-large-2402-v1:0": {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -4534,8 +4916,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 32000,
max_output_tokens: 8191,
- input_cost_per_token: 1.04e-5,
- output_cost_per_token: 3.12e-5,
+ input_cost_per_token: 0.0000104,
+ output_cost_per_token: 0.0000312,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -4544,43 +4926,55 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_pdf_input: true,
supports_assistant_prefill: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"anthropic.claude-3-5-sonnet-latest-v2:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -4591,141 +4985,180 @@ export const modelPrices = {
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"anthropic.claude-3-opus-20240229-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-sonnet-20240229-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-5-sonnet-20240620-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_pdf_input: true,
supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-haiku-20240307-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-opus-20240229-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-sonnet-20240229-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-5-sonnet-20240620-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_pdf_input: true,
supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-haiku-20240307-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-opus-20240229-v1:0": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
},
"anthropic.claude-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4733,28 +5166,31 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/anthropic.claude-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/anthropic.claude-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": {
max_tokens: 8191,
@@ -4778,8 +5214,8 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -4841,37 +5277,41 @@ export const modelPrices = {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/anthropic.claude-v2": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/anthropic.claude-v2": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/anthropic.claude-v2": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4881,6 +5321,7 @@ export const modelPrices = {
output_cost_per_second: 0.0455,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4890,15 +5331,17 @@ export const modelPrices = {
output_cost_per_second: 0.02527,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/anthropic.claude-v2": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4908,6 +5351,7 @@ export const modelPrices = {
output_cost_per_second: 0.0415,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4917,6 +5361,7 @@ export const modelPrices = {
output_cost_per_second: 0.02305,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/1-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4926,6 +5371,7 @@ export const modelPrices = {
output_cost_per_second: 0.0175,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/6-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4935,6 +5381,7 @@ export const modelPrices = {
output_cost_per_second: 0.00972,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/1-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4944,6 +5391,7 @@ export const modelPrices = {
output_cost_per_second: 0.0175,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/6-month-commitment/anthropic.claude-v2": {
max_tokens: 8191,
@@ -4953,42 +5401,47 @@ export const modelPrices = {
output_cost_per_second: 0.00972,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"anthropic.claude-v2:1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/anthropic.claude-v2:1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/anthropic.claude-v2:1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/anthropic.claude-v2:1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -4998,6 +5451,7 @@ export const modelPrices = {
output_cost_per_second: 0.0455,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5007,15 +5461,17 @@ export const modelPrices = {
output_cost_per_second: 0.02527,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/anthropic.claude-v2:1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 8e-6,
- output_cost_per_token: 2.4e-5,
+ input_cost_per_token: 0.000008,
+ output_cost_per_token: 0.000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5025,6 +5481,7 @@ export const modelPrices = {
output_cost_per_second: 0.0415,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5034,6 +5491,7 @@ export const modelPrices = {
output_cost_per_second: 0.02305,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5043,6 +5501,7 @@ export const modelPrices = {
output_cost_per_second: 0.0175,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5052,6 +5511,7 @@ export const modelPrices = {
output_cost_per_second: 0.00972,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5061,6 +5521,7 @@ export const modelPrices = {
output_cost_per_second: 0.0175,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": {
max_tokens: 8191,
@@ -5070,24 +5531,27 @@ export const modelPrices = {
output_cost_per_second: 0.00972,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"anthropic.claude-instant-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 1.63e-6,
- output_cost_per_token: 5.51e-6,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.0000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/anthropic.claude-instant-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
input_cost_per_token: 8e-7,
- output_cost_per_token: 2.4e-6,
+ output_cost_per_token: 0.0000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5097,6 +5561,7 @@ export const modelPrices = {
output_cost_per_second: 0.011,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5106,6 +5571,7 @@ export const modelPrices = {
output_cost_per_second: 0.00611,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5115,6 +5581,7 @@ export const modelPrices = {
output_cost_per_second: 0.011,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5124,24 +5591,27 @@ export const modelPrices = {
output_cost_per_second: 0.00611,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/us-west-2/anthropic.claude-instant-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
input_cost_per_token: 8e-7,
- output_cost_per_token: 2.4e-6,
+ output_cost_per_token: 0.0000024,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/anthropic.claude-instant-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 2.23e-6,
- output_cost_per_token: 7.55e-6,
+ input_cost_per_token: 0.00000223,
+ output_cost_per_token: 0.00000755,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5151,6 +5621,7 @@ export const modelPrices = {
output_cost_per_second: 0.01475,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5160,15 +5631,17 @@ export const modelPrices = {
output_cost_per_second: 0.008194,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/anthropic.claude-instant-v1": {
max_tokens: 8191,
max_input_tokens: 100000,
max_output_tokens: 8191,
- input_cost_per_token: 2.48e-6,
- output_cost_per_token: 8.38e-6,
+ input_cost_per_token: 0.00000248,
+ output_cost_per_token: 0.00000838,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5178,6 +5651,7 @@ export const modelPrices = {
output_cost_per_second: 0.01635,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": {
max_tokens: 8191,
@@ -5187,15 +5661,17 @@ export const modelPrices = {
output_cost_per_second: 0.009083,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"cohere.command-text-v14": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/*/1-month-commitment/cohere.command-text-v14": {
max_tokens: 4096,
@@ -5205,6 +5681,7 @@ export const modelPrices = {
output_cost_per_second: 0.011,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/*/6-month-commitment/cohere.command-text-v14": {
max_tokens: 4096,
@@ -5214,6 +5691,7 @@ export const modelPrices = {
output_cost_per_second: 0.0066027,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"cohere.command-light-text-v14": {
max_tokens: 4096,
@@ -5223,6 +5701,7 @@ export const modelPrices = {
output_cost_per_token: 6e-7,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/*/1-month-commitment/cohere.command-light-text-v14": {
max_tokens: 4096,
@@ -5232,6 +5711,7 @@ export const modelPrices = {
output_cost_per_second: 0.001902,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"bedrock/*/6-month-commitment/cohere.command-light-text-v14": {
max_tokens: 4096,
@@ -5241,47 +5721,52 @@ export const modelPrices = {
output_cost_per_second: 0.0011416,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"cohere.command-r-plus-v1:0": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"cohere.command-r-v1:0": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.5e-6,
+ output_cost_per_token: 0.0000015,
litellm_provider: "bedrock",
mode: "chat",
+ supports_tool_choice: true,
},
"cohere.embed-english-v3": {
max_tokens: 512,
max_input_tokens: 512,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "bedrock",
mode: "embedding",
+ supports_embedding_image_input: true,
},
"cohere.embed-multilingual-v3": {
max_tokens: 512,
max_input_tokens: 512,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "bedrock",
mode: "embedding",
+ supports_embedding_image_input: true,
},
"meta.llama2-13b-chat-v1": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 7.5e-7,
- output_cost_per_token: 1e-6,
+ output_cost_per_token: 0.000001,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5289,8 +5774,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1.95e-6,
- output_cost_per_token: 2.56e-6,
+ input_cost_per_token: 0.00000195,
+ output_cost_per_token: 0.00000256,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5362,7 +5847,7 @@ export const modelPrices = {
max_input_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 5e-7,
- output_cost_per_token: 1.01e-6,
+ output_cost_per_token: 0.00000101,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5370,8 +5855,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 2.65e-6,
- output_cost_per_token: 3.5e-6,
+ input_cost_per_token: 0.00000265,
+ output_cost_per_token: 0.0000035,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5379,8 +5864,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 2.65e-6,
- output_cost_per_token: 3.5e-6,
+ input_cost_per_token: 0.00000265,
+ output_cost_per_token: 0.0000035,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5388,8 +5873,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 2.65e-6,
- output_cost_per_token: 3.5e-6,
+ input_cost_per_token: 0.00000265,
+ output_cost_per_token: 0.0000035,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5397,8 +5882,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 3.18e-6,
- output_cost_per_token: 4.2e-6,
+ input_cost_per_token: 0.00000318,
+ output_cost_per_token: 0.0000042,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5406,8 +5891,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 3.05e-6,
- output_cost_per_token: 4.03e-6,
+ input_cost_per_token: 0.00000305,
+ output_cost_per_token: 0.00000403,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5415,8 +5900,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 2.86e-6,
- output_cost_per_token: 3.78e-6,
+ input_cost_per_token: 0.00000286,
+ output_cost_per_token: 0.00000378,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5424,8 +5909,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 3.45e-6,
- output_cost_per_token: 4.55e-6,
+ input_cost_per_token: 0.00000345,
+ output_cost_per_token: 0.00000455,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5433,8 +5918,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 4.45e-6,
- output_cost_per_token: 5.88e-6,
+ input_cost_per_token: 0.00000445,
+ output_cost_per_token: 0.00000588,
litellm_provider: "bedrock",
mode: "chat",
},
@@ -5464,8 +5949,8 @@ export const modelPrices = {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5.32e-6,
- output_cost_per_token: 1.6e-5,
+ input_cost_per_token: 0.00000532,
+ output_cost_per_token: 0.000016,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -5547,6 +6032,7 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_tool_choice: false,
+ supports_vision: true,
},
"us.meta.llama3-2-11b-instruct-v1:0": {
max_tokens: 128000,
@@ -5558,28 +6044,31 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_tool_choice: false,
+ supports_vision: true,
},
"meta.llama3-2-90b-instruct-v1:0": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
supports_tool_choice: false,
+ supports_vision: true,
},
"us.meta.llama3-2-90b-instruct-v1:0": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 2e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
supports_tool_choice: false,
+ supports_vision: true,
},
"512-x-512/50-steps/stability.stable-diffusion-xl-v0": {
max_tokens: 77,
@@ -5627,8 +6116,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "completion",
},
@@ -5636,8 +6125,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "chat",
},
@@ -5645,8 +6134,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "completion",
},
@@ -5654,8 +6143,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "chat",
},
@@ -5663,8 +6152,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "completion",
},
@@ -5672,8 +6161,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "sagemaker",
mode: "chat",
},
@@ -5709,20 +6198,20 @@ export const modelPrices = {
mode: "chat",
},
"together-ai-81.1b-110b": {
- input_cost_per_token: 1.8e-6,
- output_cost_per_token: 1.8e-6,
+ input_cost_per_token: 0.0000018,
+ output_cost_per_token: 0.0000018,
litellm_provider: "together_ai",
mode: "chat",
},
"together-ai-embedding-up-to-150m": {
input_cost_per_token: 8e-9,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "together_ai",
mode: "embedding",
},
"together-ai-embedding-151m-to-350m": {
input_cost_per_token: 1.6e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "together_ai",
mode: "embedding",
},
@@ -5734,6 +6223,7 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
mode: "chat",
+ supports_tool_choice: true,
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.1": {
litellm_provider: "together_ai",
@@ -5741,19 +6231,21 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
mode: "chat",
+ supports_tool_choice: true,
},
"together_ai/togethercomputer/CodeLlama-34b-Instruct": {
litellm_provider: "together_ai",
supports_function_calling: true,
supports_parallel_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
},
"ollama/codegemma": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
},
@@ -5761,8 +6253,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
supports_function_calling: false,
@@ -5771,8 +6263,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
supports_function_calling: true,
@@ -5781,8 +6273,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
supports_function_calling: true,
@@ -5791,8 +6283,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
supports_function_calling: true,
@@ -5801,8 +6293,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
supports_function_calling: true,
@@ -5811,8 +6303,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
supports_function_calling: true,
@@ -5821,8 +6313,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5830,8 +6322,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5839,8 +6331,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5848,8 +6340,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5857,8 +6349,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
},
@@ -5866,8 +6358,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5875,8 +6367,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5884,8 +6376,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
},
@@ -5893,8 +6385,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
supports_function_calling: true,
@@ -5903,62 +6395,68 @@ export const modelPrices = {
max_tokens: 65536,
max_input_tokens: 65536,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
+ supports_function_calling: true,
},
"ollama/mistral": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
+ supports_function_calling: true,
},
"ollama/mistral-7B-Instruct-v0.1": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
+ supports_function_calling: true,
},
"ollama/mistral-7B-Instruct-v0.2": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 32768,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
+ supports_function_calling: true,
},
"ollama/mixtral-8x7B-Instruct-v0.1": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 32768,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
+ supports_function_calling: true,
},
"ollama/mixtral-8x22B-Instruct-v0.1": {
max_tokens: 65536,
max_input_tokens: 65536,
max_output_tokens: 65536,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "chat",
+ supports_function_calling: true,
},
"ollama/codellama": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
},
@@ -5966,8 +6464,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
},
@@ -5975,8 +6473,8 @@ export const modelPrices = {
max_tokens: 2048,
max_input_tokens: 2048,
max_output_tokens: 2048,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "ollama",
mode: "completion",
},
@@ -5984,46 +6482,51 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 7e-7,
- output_cost_per_token: 9e-7,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 4e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: false,
},
"deepinfra/Gryphe/MythoMax-L2-13b": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 2.2e-7,
- output_cost_per_token: 2.2e-7,
+ input_cost_per_token: 7.2e-8,
+ output_cost_per_token: 7.2e-8,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/mistralai/Mistral-7B-Instruct-v0.1": {
- max_tokens: 8191,
+ max_tokens: 32768,
max_input_tokens: 32768,
- max_output_tokens: 8191,
- input_cost_per_token: 1.3e-7,
- output_cost_per_token: 1.3e-7,
+ max_output_tokens: 32768,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Llama-2-70b-chat-hf": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 7e-7,
- output_cost_per_token: 9e-7,
+ input_cost_per_token: 6.4e-7,
+ output_cost_per_token: 8e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b": {
- max_tokens: 8191,
+ max_tokens: 32768,
max_input_tokens: 32768,
- max_output_tokens: 8191,
- input_cost_per_token: 2.7e-7,
- output_cost_per_token: 2.7e-7,
+ max_output_tokens: 32768,
+ input_cost_per_token: 2.4e-7,
+ output_cost_per_token: 2.4e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/codellama/CodeLlama-34b-Instruct-hf": {
max_tokens: 4096,
@@ -6033,6 +6536,7 @@ export const modelPrices = {
output_cost_per_token: 6e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/deepinfra/mixtral": {
max_tokens: 4096,
@@ -6045,21 +6549,23 @@ export const modelPrices = {
},
"deepinfra/Phind/Phind-CodeLlama-34B-v2": {
max_tokens: 4096,
- max_input_tokens: 16384,
+ max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 6e-7,
output_cost_per_token: 6e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": {
- max_tokens: 8191,
+ max_tokens: 32768,
max_input_tokens: 32768,
- max_output_tokens: 8191,
- input_cost_per_token: 2.7e-7,
- output_cost_per_token: 2.7e-7,
+ max_output_tokens: 32768,
+ input_cost_per_token: 8e-8,
+ output_cost_per_token: 2.4e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/deepinfra/airoboros-70b": {
max_tokens: 4096,
@@ -6069,6 +6575,7 @@ export const modelPrices = {
output_cost_per_token: 9e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/01-ai/Yi-34B-Chat": {
max_tokens: 4096,
@@ -6078,6 +6585,7 @@ export const modelPrices = {
output_cost_per_token: 6e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/01-ai/Yi-6B-200K": {
max_tokens: 4096,
@@ -6096,15 +6604,17 @@ export const modelPrices = {
output_cost_per_token: 9e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Llama-2-13b-chat-hf": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 2.2e-7,
- output_cost_per_token: 2.2e-7,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 1.3e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/amazon/MistralLite": {
max_tokens: 8191,
@@ -6114,6 +6624,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Llama-2-7b-chat-hf": {
max_tokens: 4096,
@@ -6123,24 +6634,27 @@ export const modelPrices = {
output_cost_per_token: 1.3e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": {
- max_tokens: 8191,
- max_input_tokens: 8191,
- max_output_tokens: 4096,
- input_cost_per_token: 8e-8,
- output_cost_per_token: 8e-8,
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3e-8,
+ output_cost_per_token: 6e-8,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": {
- max_tokens: 8191,
- max_input_tokens: 8191,
- max_output_tokens: 4096,
- input_cost_per_token: 5.9e-7,
- output_cost_per_token: 7.9e-7,
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 4e-7,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/01-ai/Yi-34B-200K": {
max_tokens: 4096,
@@ -6152,20 +6666,21 @@ export const modelPrices = {
mode: "completion",
},
"deepinfra/openchat/openchat_3.5": {
- max_tokens: 4096,
- max_input_tokens: 4096,
- max_output_tokens: 4096,
- input_cost_per_token: 1.3e-7,
- output_cost_per_token: 1.3e-7,
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
litellm_provider: "deepinfra",
mode: "chat",
+ supports_tool_choice: true,
},
"perplexity/codellama-34b-instruct": {
max_tokens: 16384,
max_input_tokens: 16384,
max_output_tokens: 16384,
input_cost_per_token: 3.5e-7,
- output_cost_per_token: 1.4e-6,
+ output_cost_per_token: 0.0000014,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6174,7 +6689,7 @@ export const modelPrices = {
max_input_tokens: 16384,
max_output_tokens: 16384,
input_cost_per_token: 7e-7,
- output_cost_per_token: 2.8e-6,
+ output_cost_per_token: 0.0000028,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6182,8 +6697,8 @@ export const modelPrices = {
max_tokens: 131072,
max_input_tokens: 131072,
max_output_tokens: 131072,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6200,28 +6715,31 @@ export const modelPrices = {
max_tokens: 127072,
max_input_tokens: 127072,
max_output_tokens: 127072,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000005,
litellm_provider: "perplexity",
mode: "chat",
+ deprecation_date: "2025-02-22",
},
"perplexity/llama-3.1-sonar-large-128k-online": {
max_tokens: 127072,
max_input_tokens: 127072,
max_output_tokens: 127072,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "perplexity",
mode: "chat",
+ deprecation_date: "2025-02-22",
},
"perplexity/llama-3.1-sonar-large-128k-chat": {
max_tokens: 131072,
max_input_tokens: 131072,
max_output_tokens: 131072,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "perplexity",
mode: "chat",
+ deprecation_date: "2025-02-22",
},
"perplexity/llama-3.1-sonar-small-128k-chat": {
max_tokens: 131072,
@@ -6231,6 +6749,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "perplexity",
mode: "chat",
+ deprecation_date: "2025-02-22",
},
"perplexity/llama-3.1-sonar-small-128k-online": {
max_tokens: 127072,
@@ -6240,6 +6759,7 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "perplexity",
mode: "chat",
+ deprecation_date: "2025-02-22",
},
"perplexity/pplx-7b-chat": {
max_tokens: 8192,
@@ -6255,7 +6775,7 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 7e-7,
- output_cost_per_token: 2.8e-6,
+ output_cost_per_token: 0.0000028,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6263,7 +6783,7 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
output_cost_per_token: 2.8e-7,
input_cost_per_request: 0.005,
litellm_provider: "perplexity",
@@ -6273,8 +6793,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 0.0,
- output_cost_per_token: 2.8e-6,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0.0000028,
input_cost_per_request: 0.005,
litellm_provider: "perplexity",
mode: "chat",
@@ -6284,7 +6804,7 @@ export const modelPrices = {
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 7e-7,
- output_cost_per_token: 2.8e-6,
+ output_cost_per_token: 0.0000028,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6330,7 +6850,7 @@ export const modelPrices = {
max_input_tokens: 16384,
max_output_tokens: 16384,
input_cost_per_token: 6e-7,
- output_cost_per_token: 1.8e-6,
+ output_cost_per_token: 0.0000018,
litellm_provider: "perplexity",
mode: "chat",
},
@@ -6339,7 +6859,7 @@ export const modelPrices = {
max_input_tokens: 12000,
max_output_tokens: 12000,
input_cost_per_token: 0,
- output_cost_per_token: 1.8e-6,
+ output_cost_per_token: 0.0000018,
input_cost_per_request: 0.005,
litellm_provider: "perplexity",
mode: "chat",
@@ -6352,9 +6872,10 @@ export const modelPrices = {
output_cost_per_token: 1e-7,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": {
max_tokens: 16384,
@@ -6364,9 +6885,10 @@ export const modelPrices = {
output_cost_per_token: 1e-7,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
max_tokens: 16384,
@@ -6376,10 +6898,11 @@ export const modelPrices = {
output_cost_per_token: 2e-7,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_vision: true,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
max_tokens: 16384,
@@ -6405,18 +6928,20 @@ export const modelPrices = {
supports_function_calling: true,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: true,
},
"fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": {
max_tokens: 65536,
max_input_tokens: 65536,
max_output_tokens: 65536,
- input_cost_per_token: 1.2e-6,
- output_cost_per_token: 1.2e-6,
+ input_cost_per_token: 0.0000012,
+ output_cost_per_token: 0.0000012,
litellm_provider: "fireworks_ai",
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: true,
},
"fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": {
max_tokens: 32768,
@@ -6426,39 +6951,42 @@ export const modelPrices = {
output_cost_per_token: 9e-7,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"fireworks_ai/accounts/fireworks/models/yi-large": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 32768,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000003,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": {
max_tokens: 65536,
max_input_tokens: 65536,
- max_output_tokens: 8192,
- input_cost_per_token: 1.2e-6,
- output_cost_per_token: 1.2e-6,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.0000012,
+ output_cost_per_token: 0.0000012,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"fireworks_ai/nomic-ai/nomic-embed-text-v1.5": {
max_tokens: 8192,
max_input_tokens: 8192,
input_cost_per_token: 8e-9,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
mode: "embedding",
source: "https://fireworks.ai/pricing",
@@ -6467,7 +6995,7 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
input_cost_per_token: 8e-9,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
mode: "embedding",
source: "https://fireworks.ai/pricing",
@@ -6476,7 +7004,7 @@ export const modelPrices = {
max_tokens: 512,
max_input_tokens: 512,
input_cost_per_token: 1.6e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
mode: "embedding",
source: "https://fireworks.ai/pricing",
@@ -6485,7 +7013,7 @@ export const modelPrices = {
max_tokens: 512,
max_input_tokens: 512,
input_cost_per_token: 1.6e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
mode: "embedding",
source: "https://fireworks.ai/pricing",
@@ -6494,7 +7022,7 @@ export const modelPrices = {
max_tokens: 512,
max_input_tokens: 512,
input_cost_per_token: 8e-9,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
mode: "embedding",
source: "https://fireworks.ai/pricing",
@@ -6515,23 +7043,23 @@ export const modelPrices = {
litellm_provider: "fireworks_ai",
},
"fireworks-ai-56b-to-176b": {
- input_cost_per_token: 1.2e-6,
- output_cost_per_token: 1.2e-6,
+ input_cost_per_token: 0.0000012,
+ output_cost_per_token: 0.0000012,
litellm_provider: "fireworks_ai",
},
"fireworks-ai-default": {
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai",
},
"fireworks-ai-embedding-up-to-150m": {
input_cost_per_token: 8e-9,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
},
"fireworks-ai-embedding-150m-to-350m": {
input_cost_per_token: 1.6e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "fireworks_ai-embedding-models",
},
"anyscale/mistralai/Mistral-7B-Instruct-v0.1": {
@@ -6612,8 +7140,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "anyscale",
mode: "chat",
},
@@ -6621,8 +7149,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "anyscale",
mode: "chat",
},
@@ -6630,8 +7158,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "anyscale",
mode: "chat",
source:
@@ -6652,8 +7180,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 1e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
litellm_provider: "anyscale",
mode: "chat",
source:
@@ -6663,8 +7191,8 @@ export const modelPrices = {
max_tokens: 3072,
max_input_tokens: 3072,
max_output_tokens: 3072,
- input_cost_per_token: 1.923e-6,
- output_cost_per_token: 1.923e-6,
+ input_cost_per_token: 0.000001923,
+ output_cost_per_token: 0.000001923,
litellm_provider: "cloudflare",
mode: "chat",
},
@@ -6672,8 +7200,8 @@ export const modelPrices = {
max_tokens: 2048,
max_input_tokens: 2048,
max_output_tokens: 2048,
- input_cost_per_token: 1.923e-6,
- output_cost_per_token: 1.923e-6,
+ input_cost_per_token: 0.000001923,
+ output_cost_per_token: 0.000001923,
litellm_provider: "cloudflare",
mode: "chat",
},
@@ -6681,8 +7209,8 @@ export const modelPrices = {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
- input_cost_per_token: 1.923e-6,
- output_cost_per_token: 1.923e-6,
+ input_cost_per_token: 0.000001923,
+ output_cost_per_token: 0.000001923,
litellm_provider: "cloudflare",
mode: "chat",
},
@@ -6690,8 +7218,8 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
- input_cost_per_token: 1.923e-6,
- output_cost_per_token: 1.923e-6,
+ input_cost_per_token: 0.000001923,
+ output_cost_per_token: 0.000001923,
litellm_provider: "cloudflare",
mode: "chat",
},
@@ -6699,7 +7227,7 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6707,7 +7235,7 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 4096,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6715,7 +7243,7 @@ export const modelPrices = {
max_tokens: 16000,
max_input_tokens: 16000,
input_cost_per_token: 1.2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6723,7 +7251,7 @@ export const modelPrices = {
max_tokens: 16000,
max_input_tokens: 16000,
input_cost_per_token: 1.2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6731,7 +7259,7 @@ export const modelPrices = {
max_tokens: 16000,
max_input_tokens: 16000,
input_cost_per_token: 1.2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6739,7 +7267,7 @@ export const modelPrices = {
max_tokens: 4000,
max_input_tokens: 4000,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6747,7 +7275,7 @@ export const modelPrices = {
max_tokens: 4000,
max_input_tokens: 4000,
input_cost_per_token: 1e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6755,7 +7283,7 @@ export const modelPrices = {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 1.2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -6763,9 +7291,9 @@ export const modelPrices = {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 5e-6,
- input_dbu_cost_per_token: 7.1429e-5,
- output_cost_per_token: 1.500002e-5,
+ input_cost_per_token: 0.000005,
+ input_dbu_cost_per_token: 0.000071429,
+ output_cost_per_token: 0.00001500002,
output_db_cost_per_token: 0.000214286,
litellm_provider: "databricks",
mode: "chat",
@@ -6775,15 +7303,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-meta-llama-3-1-70b-instruct": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 1.00002e-6,
- input_dbu_cost_per_token: 1.4286e-5,
- output_cost_per_token: 2.99999e-6,
- output_dbu_cost_per_token: 4.2857e-5,
+ input_cost_per_token: 0.00000100002,
+ input_dbu_cost_per_token: 0.000014286,
+ output_cost_per_token: 0.00000299999,
+ output_dbu_cost_per_token: 0.000042857,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6792,15 +7321,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-dbrx-instruct": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 32768,
input_cost_per_token: 7.4998e-7,
- input_dbu_cost_per_token: 1.0714e-5,
- output_cost_per_token: 2.24901e-6,
- output_dbu_cost_per_token: 3.2143e-5,
+ input_dbu_cost_per_token: 0.000010714,
+ output_cost_per_token: 0.00000224901,
+ output_dbu_cost_per_token: 0.000032143,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6809,15 +7339,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-meta-llama-3-70b-instruct": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 1.00002e-6,
- input_dbu_cost_per_token: 1.4286e-5,
- output_cost_per_token: 2.99999e-6,
- output_dbu_cost_per_token: 4.2857e-5,
+ input_cost_per_token: 0.00000100002,
+ input_dbu_cost_per_token: 0.000014286,
+ output_cost_per_token: 0.00000299999,
+ output_dbu_cost_per_token: 0.000042857,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6826,15 +7357,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-llama-2-70b-chat": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 5.0001e-7,
- input_dbu_cost_per_token: 7.143e-6,
- output_cost_per_token: 1.5e-6,
- output_dbu_cost_per_token: 2.1429e-5,
+ input_dbu_cost_per_token: 0.000007143,
+ output_cost_per_token: 0.0000015,
+ output_dbu_cost_per_token: 0.000021429,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6843,15 +7375,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-mixtral-8x7b-instruct": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
input_cost_per_token: 5.0001e-7,
- input_dbu_cost_per_token: 7.143e-6,
+ input_dbu_cost_per_token: 0.000007143,
output_cost_per_token: 9.9902e-7,
- output_dbu_cost_per_token: 1.4286e-5,
+ output_dbu_cost_per_token: 0.000014286,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6860,15 +7393,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-mpt-30b-instruct": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 9.9902e-7,
- input_dbu_cost_per_token: 1.4286e-5,
+ input_dbu_cost_per_token: 0.000014286,
output_cost_per_token: 9.9902e-7,
- output_dbu_cost_per_token: 1.4286e-5,
+ output_dbu_cost_per_token: 0.000014286,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6877,15 +7411,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-mpt-7b-instruct": {
max_tokens: 8192,
max_input_tokens: 8192,
max_output_tokens: 8192,
input_cost_per_token: 5.0001e-7,
- input_dbu_cost_per_token: 7.143e-6,
- output_cost_per_token: 0.0,
- output_dbu_cost_per_token: 0.0,
+ input_dbu_cost_per_token: 0.000007143,
+ output_cost_per_token: 0,
+ output_dbu_cost_per_token: 0,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -6894,15 +7429,16 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"databricks/databricks-bge-large-en": {
max_tokens: 512,
max_input_tokens: 512,
output_vector_size: 1024,
input_cost_per_token: 1.0003e-7,
- input_dbu_cost_per_token: 1.429e-6,
- output_cost_per_token: 0.0,
- output_dbu_cost_per_token: 0.0,
+ input_dbu_cost_per_token: 0.000001429,
+ output_cost_per_token: 0,
+ output_dbu_cost_per_token: 0,
litellm_provider: "databricks",
mode: "embedding",
source:
@@ -6917,9 +7453,9 @@ export const modelPrices = {
max_input_tokens: 8192,
output_vector_size: 1024,
input_cost_per_token: 1.2999e-7,
- input_dbu_cost_per_token: 1.857e-6,
- output_cost_per_token: 0.0,
- output_dbu_cost_per_token: 0.0,
+ input_dbu_cost_per_token: 0.000001857,
+ output_cost_per_token: 0,
+ output_dbu_cost_per_token: 0,
litellm_provider: "databricks",
mode: "embedding",
source:
@@ -6943,14 +7479,15 @@ export const modelPrices = {
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"amazon.titan-embed-image-v1": {
max_tokens: 128,
max_input_tokens: 128,
output_vector_size: 1024,
input_cost_per_token: 8e-7,
- input_cost_per_image: 6e-5,
- output_cost_per_token: 0.0,
+ input_cost_per_image: 0.00006,
+ output_cost_per_token: 0,
litellm_provider: "bedrock",
supports_image_input: true,
supports_embedding_image_input: true,
@@ -6966,13 +7503,14 @@ export const modelPrices = {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "azure_ai",
supports_function_calling: true,
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
+ supports_tool_choice: true,
},
"azure_ai/ministral-3b": {
max_tokens: 4096,
@@ -6985,6 +7523,7 @@ export const modelPrices = {
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
+ supports_tool_choice: true,
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
max_tokens: 2048,
@@ -6998,19 +7537,21 @@ export const modelPrices = {
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
+ supports_tool_choice: true,
},
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
max_tokens: 2048,
max_input_tokens: 128000,
max_output_tokens: 2048,
- input_cost_per_token: 2.04e-6,
- output_cost_per_token: 2.04e-6,
+ input_cost_per_token: 0.00000204,
+ output_cost_per_token: 0.00000204,
litellm_provider: "azure_ai",
supports_function_calling: true,
supports_vision: true,
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3.5-mini-instruct": {
max_tokens: 4096,
@@ -7022,6 +7563,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3.5-vision-instruct": {
max_tokens: 4096,
@@ -7033,6 +7575,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: true,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3.5-MoE-instruct": {
max_tokens: 4096,
@@ -7044,6 +7587,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-mini-4k-instruct": {
max_tokens: 4096,
@@ -7055,6 +7599,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-mini-128k-instruct": {
max_tokens: 4096,
@@ -7066,6 +7611,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-small-8k-instruct": {
max_tokens: 4096,
@@ -7077,6 +7623,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-small-128k-instruct": {
max_tokens: 4096,
@@ -7088,6 +7635,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-medium-4k-instruct": {
max_tokens: 4096,
@@ -7099,6 +7647,7 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"azure_ai/Phi-3-medium-128k-instruct": {
max_tokens: 4096,
@@ -7110,96 +7659,129 @@ export const modelPrices = {
mode: "chat",
supports_vision: false,
source: "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
+ supports_tool_choice: true,
},
"xai/grok-beta": {
max_tokens: 131072,
max_input_tokens: 131072,
max_output_tokens: 131072,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
litellm_provider: "xai",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
},
"claude-3-5-haiku-20241022": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
- cache_creation_input_token_cost: 1.25e-6,
- cache_read_input_token_cost: 1e-7,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.000004,
+ cache_creation_input_token_cost: 0.000001,
+ cache_read_input_token_cost: 8e-8,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
litellm_provider: "anthropic",
mode: "chat",
supports_function_calling: true,
+ supports_vision: true,
tool_use_system_prompt_tokens: 264,
supports_assistant_prefill: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_response_schema: true,
+ deprecation_date: "2025-10-01",
+ supports_tool_choice: true,
+ supports_web_search: true,
},
"vertex_ai/claude-3-5-haiku@20241022": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-5-haiku": {
max_tokens: 200000,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"openrouter/anthropic/claude-3-5-haiku-20241022": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
tool_use_system_prompt_tokens: 264,
+ supports_tool_choice: true,
},
"anthropic.claude-3-5-haiku-20241022-v1:0": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.000004,
+ cache_creation_input_token_cost: 0.000001,
+ cache_read_input_token_cost: 8e-8,
litellm_provider: "bedrock",
mode: "chat",
supports_assistant_prefill: true,
+ supports_pdf_input: true,
supports_function_calling: true,
+ supports_response_schema: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"us.anthropic.claude-3-5-haiku-20241022-v1:0": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.000004,
+ cache_creation_input_token_cost: 0.000001,
+ cache_read_input_token_cost: 8e-8,
litellm_provider: "bedrock",
mode: "chat",
supports_assistant_prefill: true,
+ supports_pdf_input: true,
supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.00000125,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"stability.sd3-large-v1:0": {
max_tokens: 77,
@@ -7212,61 +7794,71 @@ export const modelPrices = {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
- input_cost_per_token_batches: 1.25e-6,
- output_cost_per_token_batches: 5e-6,
- cache_read_input_token_cost: 1.25e-6,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"ft:gpt-4o-2024-11-20": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 3.75e-6,
- cache_creation_input_token_cost: 1.875e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.00000375,
+ cache_creation_input_token_cost: 0.000001875,
+ output_cost_per_token: 0.000015,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"azure/gpt-4o-2024-11-20": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.75e-6,
- output_cost_per_token: 1.1e-5,
+ input_cost_per_token: 0.00000275,
+ output_cost_per_token: 0.000011,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure/global-standard/gpt-4o-2024-11-20": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- output_cost_per_token: 1e-5,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-12-20",
},
"groq/llama-3.2-1b-preview": {
max_tokens: 8192,
@@ -7278,6 +7870,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-04-14",
},
"groq/llama-3.2-3b-preview": {
max_tokens: 8192,
@@ -7289,6 +7883,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-04-14",
},
"groq/llama-3.2-11b-text-preview": {
max_tokens: 8192,
@@ -7300,6 +7896,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2024-10-28",
},
"groq/llama-3.2-11b-vision-preview": {
max_tokens: 8192,
@@ -7312,6 +7910,8 @@ export const modelPrices = {
supports_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-04-14",
},
"groq/llama-3.2-90b-text-preview": {
max_tokens: 8192,
@@ -7323,6 +7923,8 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
supports_response_schema: true,
+ supports_tool_choice: true,
+ deprecation_date: "2024-11-25",
},
"groq/llama-3.2-90b-vision-preview": {
max_tokens: 8192,
@@ -7335,77 +7937,90 @@ export const modelPrices = {
supports_function_calling: true,
supports_response_schema: true,
supports_vision: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-04-14",
},
"vertex_ai/claude-3-sonnet": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-5-sonnet": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-5-sonnet-v2": {
+ supports_computer_use: true,
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 3e-6,
- output_cost_per_token: 1.5e-5,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-haiku": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
input_cost_per_token: 2.5e-7,
- output_cost_per_token: 1.25e-6,
+ output_cost_per_token: 0.00000125,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-5-haiku": {
max_tokens: 8192,
max_input_tokens: 200000,
max_output_tokens: 8192,
- input_cost_per_token: 1e-6,
- output_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
+ supports_pdf_input: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"vertex_ai/claude-3-opus": {
max_tokens: 4096,
max_input_tokens: 200000,
max_output_tokens: 4096,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 7.5e-5,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
litellm_provider: "vertex_ai-anthropic_models",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
},
"gemini/gemini-exp-1114": {
max_tokens: 8192,
@@ -7424,6 +8039,7 @@ export const modelPrices = {
litellm_provider: "gemini",
mode: "chat",
supports_system_messages: true,
+ supports_tool_choice: true,
supports_function_calling: true,
supports_vision: true,
supports_response_schema: true,
@@ -7433,6 +8049,7 @@ export const modelPrices = {
metadata: {
notes:
"Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.",
+ supports_tool_choice: true,
},
},
"openrouter/qwen/qwen-2.5-coder-32b-instruct": {
@@ -7443,6 +8060,7 @@ export const modelPrices = {
output_cost_per_token: 1.8e-7,
litellm_provider: "openrouter",
mode: "chat",
+ supports_tool_choice: true,
},
"us.meta.llama3-1-8b-instruct-v1:0": {
max_tokens: 128000,
@@ -7470,8 +8088,8 @@ export const modelPrices = {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5.32e-6,
- output_cost_per_token: 1.6e-5,
+ input_cost_per_token: 0.00000532,
+ output_cost_per_token: 0.000016,
litellm_provider: "bedrock",
mode: "chat",
supports_function_calling: true,
@@ -7492,16 +8110,17 @@ export const modelPrices = {
output_cost_per_token: 9e-7,
litellm_provider: "fireworks_ai",
mode: "chat",
- supports_function_calling: true,
+ supports_function_calling: false,
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"omni-moderation-latest": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
mode: "moderation",
},
@@ -7509,8 +8128,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
mode: "moderation",
},
@@ -7518,8 +8137,8 @@ export const modelPrices = {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 0,
- input_cost_per_token: 0.0,
- output_cost_per_token: 0.0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
litellm_provider: "openai",
mode: "moderation",
},
@@ -7527,10 +8146,10 @@ export const modelPrices = {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
- input_cost_per_token: 2.5e-6,
- input_cost_per_audio_token: 4e-5,
- output_cost_per_token: 1e-5,
- output_cost_per_audio_token: 8e-5,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7538,15 +8157,16 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-mini-audio-preview-2024-12-17": {
max_tokens: 16384,
max_input_tokens: 128000,
max_output_tokens: 16384,
input_cost_per_token: 1.5e-7,
- input_cost_per_audio_token: 1e-5,
+ input_cost_per_audio_token: 0.00001,
output_cost_per_token: 6e-7,
- output_cost_per_audio_token: 2e-5,
+ output_cost_per_audio_token: 0.00002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7554,48 +8174,55 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
o1: {
max_tokens: 100000,
max_input_tokens: 200000,
max_output_tokens: 100000,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
+ supports_pdf_input: true,
supports_prompt_caching: true,
supports_system_messages: true,
supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
},
"o1-2024-12-17": {
max_tokens: 100000,
max_input_tokens: 200000,
max_output_tokens: 100000,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "openai",
mode: "chat",
+ supports_pdf_input: true,
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
supports_prompt_caching: true,
supports_system_messages: true,
supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
},
"gpt-4o-realtime-preview-2024-10-01": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
+ input_cost_per_token: 0.000005,
input_cost_per_audio_token: 0.0001,
- cache_read_input_token_cost: 2.5e-6,
- cache_creation_input_audio_token_cost: 2e-5,
- output_cost_per_token: 2e-5,
+ cache_read_input_token_cost: 0.0000025,
+ cache_creation_input_audio_token_cost: 0.00002,
+ output_cost_per_token: 0.00002,
output_cost_per_audio_token: 0.0002,
litellm_provider: "openai",
mode: "chat",
@@ -7604,16 +8231,17 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-realtime-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- input_cost_per_audio_token: 4e-5,
- cache_read_input_token_cost: 2.5e-6,
- output_cost_per_token: 2e-5,
- output_cost_per_audio_token: 8e-5,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7621,16 +8249,17 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-realtime-preview-2024-12-17": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
- input_cost_per_token: 5e-6,
- input_cost_per_audio_token: 4e-5,
- cache_read_input_token_cost: 2.5e-6,
- output_cost_per_token: 2e-5,
- output_cost_per_audio_token: 8e-5,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7638,17 +8267,18 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-mini-realtime-preview": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
input_cost_per_token: 6e-7,
- input_cost_per_audio_token: 1e-5,
+ input_cost_per_audio_token: 0.00001,
cache_read_input_token_cost: 3e-7,
cache_creation_input_audio_token_cost: 3e-7,
- output_cost_per_token: 2.4e-6,
- output_cost_per_audio_token: 2e-5,
+ output_cost_per_token: 0.0000024,
+ output_cost_per_audio_token: 0.00002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7656,17 +8286,18 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"gpt-4o-mini-realtime-preview-2024-12-17": {
max_tokens: 4096,
max_input_tokens: 128000,
max_output_tokens: 4096,
input_cost_per_token: 6e-7,
- input_cost_per_audio_token: 1e-5,
+ input_cost_per_audio_token: 0.00001,
cache_read_input_token_cost: 3e-7,
cache_creation_input_audio_token_cost: 3e-7,
- output_cost_per_token: 2.4e-6,
- output_cost_per_audio_token: 2e-5,
+ output_cost_per_token: 0.0000024,
+ output_cost_per_audio_token: 0.00002,
litellm_provider: "openai",
mode: "chat",
supports_function_calling: true,
@@ -7674,20 +8305,23 @@ export const modelPrices = {
supports_audio_input: true,
supports_audio_output: true,
supports_system_messages: true,
+ supports_tool_choice: true,
},
"azure/o1": {
max_tokens: 100000,
max_input_tokens: 200000,
max_output_tokens: 100000,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "azure",
mode: "chat",
supports_function_calling: true,
supports_parallel_function_calling: true,
supports_vision: true,
+ supports_reasoning: true,
supports_prompt_caching: true,
+ supports_tool_choice: true,
},
"azure_ai/Llama-3.3-70B-Instruct": {
max_tokens: 2048,
@@ -7700,51 +8334,58 @@ export const modelPrices = {
mode: "chat",
source:
"https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
+ supports_tool_choice: true,
},
"mistral/mistral-large-2411": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/pixtral-large-latest": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
supports_vision: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"mistral/pixtral-large-2411": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "mistral",
mode: "chat",
supports_function_calling: true,
supports_assistant_prefill: true,
supports_vision: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
},
"deepseek/deepseek-chat": {
- max_tokens: 4096,
- max_input_tokens: 128000,
- max_output_tokens: 4096,
- input_cost_per_token: 1.4e-7,
- input_cost_per_token_cache_hit: 1.4e-8,
- cache_read_input_token_cost: 1.4e-8,
- cache_creation_input_token_cost: 0.0,
- output_cost_per_token: 2.8e-7,
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2.7e-7,
+ input_cost_per_token_cache_hit: 7e-8,
+ cache_read_input_token_cost: 7e-8,
+ cache_creation_input_token_cost: 0,
+ output_cost_per_token: 0.0000011,
litellm_provider: "deepseek",
mode: "chat",
supports_function_calling: true,
@@ -7767,13 +8408,16 @@ export const modelPrices = {
supports_prompt_caching: true,
},
"groq/llama-3.3-70b-versatile": {
- max_tokens: 8192,
+ max_tokens: 32768,
max_input_tokens: 128000,
- max_output_tokens: 8192,
+ max_output_tokens: 32768,
input_cost_per_token: 5.9e-7,
output_cost_per_token: 7.9e-7,
litellm_provider: "groq",
mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
},
"groq/llama-3.3-70b-specdec": {
max_tokens: 8192,
@@ -7783,6 +8427,8 @@ export const modelPrices = {
output_cost_per_token: 9.9e-7,
litellm_provider: "groq",
mode: "chat",
+ supports_tool_choice: true,
+ deprecation_date: "2025-04-14",
},
"friendliai/meta-llama-3.1-8b-instruct": {
max_tokens: 8192,
@@ -7796,6 +8442,7 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_system_messages: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"friendliai/meta-llama-3.1-70b-instruct": {
max_tokens: 8192,
@@ -7809,6 +8456,7 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_system_messages: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"gemini-2.0-flash-exp": {
max_tokens: 8192,
@@ -7823,14 +8471,14 @@ export const modelPrices = {
input_cost_per_image: 0,
input_cost_per_video_per_second: 0,
input_cost_per_audio_per_second: 0,
- input_cost_per_token: 0,
+ input_cost_per_token: 1.5e-7,
input_cost_per_character: 0,
input_cost_per_token_above_128k_tokens: 0,
input_cost_per_character_above_128k_tokens: 0,
input_cost_per_image_above_128k_tokens: 0,
input_cost_per_video_per_second_above_128k_tokens: 0,
input_cost_per_audio_per_second_above_128k_tokens: 0,
- output_cost_per_token: 0,
+ output_cost_per_token: 6e-7,
output_cost_per_character: 0,
output_cost_per_token_above_128k_tokens: 0,
output_cost_per_character_above_128k_tokens: 0,
@@ -7841,8 +8489,14 @@ export const modelPrices = {
supports_vision: true,
supports_response_schema: true,
supports_audio_output: true,
- source:
- "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.75e-8,
+ supports_prompt_caching: true,
},
"gemini/gemini-2.0-flash-exp": {
max_tokens: 8192,
@@ -7877,28 +8531,36 @@ export const modelPrices = {
supports_audio_output: true,
tpm: 4000000,
rpm: 10,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
source:
"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
},
"vertex_ai/mistral-large@2411-001": {
max_tokens: 8191,
max_input_tokens: 128000,
max_output_tokens: 8191,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"vertex_ai/mistral-large-2411": {
max_tokens: 8191,
max_input_tokens: 128000,
max_output_tokens: 8191,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 6e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
litellm_provider: "vertex_ai-mistral_models",
mode: "chat",
supports_function_calling: true,
+ supports_tool_choice: true,
},
"text-embedding-005": {
max_tokens: 2048,
@@ -7936,6 +8598,7 @@ export const modelPrices = {
tpm: 4000000,
rpm: 4000,
source: "https://ai.google.dev/pricing",
+ supports_tool_choice: true,
},
"gemini/gemini-exp-1206": {
max_tokens: 8192,
@@ -7955,6 +8618,7 @@ export const modelPrices = {
mode: "chat",
supports_system_messages: true,
supports_function_calling: true,
+ supports_tool_choice: true,
supports_vision: true,
supports_response_schema: true,
tpm: 4000000,
@@ -7963,6 +8627,7 @@ export const modelPrices = {
metadata: {
notes:
"Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.",
+ supports_tool_choice: true,
},
},
"command-r7b-12-2024": {
@@ -7975,35 +8640,37 @@ export const modelPrices = {
mode: "chat",
supports_function_calling: true,
source: "https://docs.cohere.com/v2/docs/command-r7b",
+ supports_tool_choice: true,
},
"rerank-v3.5": {
max_tokens: 4096,
max_input_tokens: 4096,
max_output_tokens: 4096,
max_query_tokens: 2048,
- input_cost_per_token: 0.0,
+ input_cost_per_token: 0,
input_cost_per_query: 0.002,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "cohere",
mode: "rerank",
},
"openrouter/deepseek/deepseek-chat": {
max_tokens: 8192,
- max_input_tokens: 66000,
- max_output_tokens: 4096,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
input_cost_per_token: 1.4e-7,
output_cost_per_token: 2.8e-7,
litellm_provider: "openrouter",
supports_prompt_caching: true,
mode: "chat",
+ supports_tool_choice: true,
},
"openrouter/openai/o1": {
max_tokens: 100000,
max_input_tokens: 200000,
max_output_tokens: 100000,
- input_cost_per_token: 1.5e-5,
- output_cost_per_token: 6e-5,
- cache_read_input_token_cost: 7.5e-6,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
litellm_provider: "openrouter",
mode: "chat",
supports_function_calling: true,
@@ -8012,22 +8679,24 @@ export const modelPrices = {
supports_prompt_caching: true,
supports_system_messages: true,
supports_response_schema: true,
+ supports_tool_choice: true,
},
"amazon.nova-micro-v1:0": {
- max_tokens: 4096,
- max_input_tokens: 300000,
- max_output_tokens: 4096,
+ max_tokens: 10000,
+ max_input_tokens: 128000,
+ max_output_tokens: 10000,
input_cost_per_token: 3.5e-8,
output_cost_per_token: 1.4e-7,
litellm_provider: "bedrock_converse",
mode: "chat",
supports_function_calling: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
},
"amazon.nova-lite-v1:0": {
- max_tokens: 4096,
- max_input_tokens: 128000,
- max_output_tokens: 4096,
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
input_cost_per_token: 6e-8,
output_cost_per_token: 2.4e-7,
litellm_provider: "bedrock_converse",
@@ -8036,19 +8705,21 @@ export const modelPrices = {
supports_vision: true,
supports_pdf_input: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
},
"amazon.nova-pro-v1:0": {
- max_tokens: 4096,
+ max_tokens: 10000,
max_input_tokens: 300000,
- max_output_tokens: 4096,
+ max_output_tokens: 10000,
input_cost_per_token: 8e-7,
- output_cost_per_token: 3.2e-6,
+ output_cost_per_token: 0.0000032,
litellm_provider: "bedrock_converse",
mode: "chat",
supports_function_calling: true,
supports_vision: true,
supports_pdf_input: true,
supports_prompt_caching: true,
+ supports_response_schema: true,
},
"meta.llama3-3-70b-instruct-v1:0": {
max_tokens: 4096,
@@ -8058,6 +8729,8 @@ export const modelPrices = {
output_cost_per_token: 7.2e-7,
litellm_provider: "bedrock_converse",
mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
},
"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
input_cost_per_token: 1.8e-7,
@@ -8067,6 +8740,7 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
mode: "chat",
+ supports_tool_choice: true,
},
"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
input_cost_per_token: 8.8e-7,
@@ -8076,25 +8750,26 @@ export const modelPrices = {
supports_parallel_function_calling: true,
supports_response_schema: true,
mode: "chat",
+ supports_tool_choice: true,
},
"together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
- input_cost_per_token: 3.5e-6,
- output_cost_per_token: 3.5e-6,
+ input_cost_per_token: 0.0000035,
+ output_cost_per_token: 0.0000035,
litellm_provider: "together_ai",
supports_function_calling: true,
supports_parallel_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
},
"deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct": {
max_tokens: 32768,
max_input_tokens: 32768,
max_output_tokens: 32768,
- input_cost_per_token: 9e-7,
- output_cost_per_token: 9e-7,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 8e-7,
litellm_provider: "deepinfra",
mode: "chat",
- supports_function_calling: true,
- supports_parallel_function_calling: true,
+ supports_tool_choice: true,
},
"fireworks_ai/accounts/fireworks/models/deepseek-v3": {
max_tokens: 8192,
@@ -8106,12 +8781,13 @@ export const modelPrices = {
mode: "chat",
supports_response_schema: true,
source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
},
"voyage/voyage-3-large": {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 1.8e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -8119,7 +8795,7 @@ export const modelPrices = {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 6e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -8127,7 +8803,7 @@ export const modelPrices = {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 2e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -8135,7 +8811,7 @@ export const modelPrices = {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 1.8e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -8143,7 +8819,7 @@ export const modelPrices = {
max_tokens: 32000,
max_input_tokens: 32000,
input_cost_per_token: 1.2e-7,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "embedding",
},
@@ -8154,7 +8830,7 @@ export const modelPrices = {
max_query_tokens: 16000,
input_cost_per_token: 5e-8,
input_cost_per_query: 5e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "rerank",
},
@@ -8165,7 +8841,7 @@ export const modelPrices = {
max_query_tokens: 8000,
input_cost_per_token: 2e-8,
input_cost_per_query: 2e-8,
- output_cost_per_token: 0.0,
+ output_cost_per_token: 0,
litellm_provider: "voyage",
mode: "rerank",
},
@@ -8173,10 +8849,10 @@ export const modelPrices = {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
- input_cost_per_token: 1.00002e-6,
- input_dbu_cost_per_token: 1.4286e-5,
- output_cost_per_token: 2.99999e-6,
- output_dbu_cost_per_token: 4.2857e-5,
+ input_cost_per_token: 0.00000100002,
+ input_dbu_cost_per_token: 0.000014286,
+ output_cost_per_token: 0.00000299999,
+ output_dbu_cost_per_token: 0.000042857,
litellm_provider: "databricks",
mode: "chat",
source:
@@ -8185,75 +8861,13530 @@ export const modelPrices = {
notes:
"Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
},
+ supports_tool_choice: true,
},
"sambanova/Meta-Llama-3.1-8B-Instruct": {
- max_tokens: 16000,
- max_input_tokens: 16000,
- max_output_tokens: 16000,
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
input_cost_per_token: 1e-7,
output_cost_per_token: 2e-7,
litellm_provider: "sambanova",
- supports_function_calling: true,
mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
},
"sambanova/Meta-Llama-3.1-70B-Instruct": {
max_tokens: 128000,
max_input_tokens: 128000,
max_output_tokens: 128000,
input_cost_per_token: 6e-7,
- output_cost_per_token: 1.2e-6,
+ output_cost_per_token: 0.0000012,
litellm_provider: "sambanova",
supports_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
},
"sambanova/Meta-Llama-3.1-405B-Instruct": {
- max_tokens: 16000,
- max_input_tokens: 16000,
- max_output_tokens: 16000,
- input_cost_per_token: 5e-6,
- output_cost_per_token: 1e-5,
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.00001,
litellm_provider: "sambanova",
- supports_function_calling: true,
mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
},
"sambanova/Meta-Llama-3.2-1B-Instruct": {
- max_tokens: 16000,
- max_input_tokens: 16000,
- max_output_tokens: 16000,
- input_cost_per_token: 4e-7,
- output_cost_per_token: 8e-7,
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 4e-8,
+ output_cost_per_token: 8e-8,
litellm_provider: "sambanova",
- supports_function_calling: true,
mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
},
"sambanova/Meta-Llama-3.2-3B-Instruct": {
- max_tokens: 4000,
- max_input_tokens: 4000,
- max_output_tokens: 4000,
- input_cost_per_token: 8e-7,
- output_cost_per_token: 1.6e-6,
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 8e-8,
+ output_cost_per_token: 1.6e-7,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/Meta-Llama-3.3-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.0000012,
litellm_provider: "sambanova",
- supports_function_calling: true,
mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
},
"sambanova/Qwen2.5-Coder-32B-Instruct": {
max_tokens: 8000,
max_input_tokens: 8000,
max_output_tokens: 8000,
- input_cost_per_token: 1.5e-6,
- output_cost_per_token: 3e-6,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000003,
litellm_provider: "sambanova",
supports_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
},
"sambanova/Qwen2.5-72B-Instruct": {
max_tokens: 8000,
max_input_tokens: 8000,
max_output_tokens: 8000,
- input_cost_per_token: 2e-6,
- output_cost_per_token: 4e-6,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000004,
litellm_provider: "sambanova",
supports_function_calling: true,
mode: "chat",
+ supports_tool_choice: true,
+ },
+ "o3-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "o3-mini-2025-01-31": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/o3-mini-2025-01-31": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/o3-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "azure/o1-2024-12-17": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure_ai/deepseek-r1": {
+ max_tokens: 8192,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.00000135,
+ output_cost_per_token: 0.0000054,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source:
+ "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367",
+ },
+ "deepseek/deepseek-reasoner": {
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.5e-7,
+ input_cost_per_token_cache_hit: 1.4e-7,
+ output_cost_per_token: 0.00000219,
+ litellm_provider: "deepseek",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ },
+ "xai/grok-2-vision-1212": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ input_cost_per_image: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-2-vision-latest": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ input_cost_per_image: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-2-vision": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ input_cost_per_image: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-vision-beta": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000005,
+ input_cost_per_image: 0.000005,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-2-1212": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-2": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "xai/grok-2-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "groq/deepseek-r1-distill-llama-70b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 7.5e-7,
+ output_cost_per_token: 9.9e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "gemini/gemini-2.0-flash": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_audio_input: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ supports_tool_choice: true,
+ source: "https://ai.google.dev/pricing#2_0flash",
+ supports_web_search: true,
+ supports_url_context: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-001": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ deprecation_date: "2026-02-05",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.75e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ max_tokens: 65536,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65536,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: false,
+ supports_vision: true,
+ supports_response_schema: false,
+ supports_audio_output: false,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-001": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source: "https://ai.google.dev/pricing#2_0flash",
+ supports_web_search: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-lite-preview-02-05": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7.5e-8,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 60000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite",
+ supports_web_search: true,
+ cache_read_input_token_cost: 1.875e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-thinking-exp": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65536,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ tpm: 4000000,
+ rpm: 10,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "vertex_ai/codestral-2501": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "vertex_ai-mistral_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/deepseek/deepseek-r1": {
+ max_tokens: 8192,
+ max_input_tokens: 65336,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.5e-7,
+ input_cost_per_token_cache_hit: 1.4e-7,
+ output_cost_per_token: 0.00000219,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_prompt_caching: true,
+ },
+ "ai21.jamba-1-5-large-v1:0": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "ai21.jamba-1-5-mini-v1:0": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "us.amazon.nova-micro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 128000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 3.5e-8,
+ output_cost_per_token: 1.4e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "us.amazon.nova-lite-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 2.4e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "us.amazon.nova-pro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.0000032,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "stability.sd3-5-large-v1:0": {
+ max_tokens: 77,
+ max_input_tokens: 77,
+ output_cost_per_image: 0.08,
+ litellm_provider: "bedrock",
+ mode: "image_generation",
+ },
+ "stability.stable-image-core-v1:0": {
+ max_tokens: 77,
+ max_input_tokens: 77,
+ output_cost_per_image: 0.04,
+ litellm_provider: "bedrock",
+ mode: "image_generation",
+ },
+ "stability.stable-image-core-v1:1": {
+ max_tokens: 77,
+ max_input_tokens: 77,
+ output_cost_per_image: 0.04,
+ litellm_provider: "bedrock",
+ mode: "image_generation",
+ },
+ "stability.stable-image-ultra-v1:1": {
+ max_tokens: 77,
+ max_input_tokens: 77,
+ output_cost_per_image: 0.14,
+ litellm_provider: "bedrock",
+ mode: "image_generation",
+ },
+ "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ input_cost_per_token: 8.8e-7,
+ output_cost_per_token: 8.8e-7,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": {
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: false,
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ },
+ "assemblyai/nano": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00010278,
+ output_cost_per_second: 0,
+ litellm_provider: "assemblyai",
+ },
+ "assemblyai/best": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00003333,
+ output_cost_per_second: 0,
+ litellm_provider: "assemblyai",
+ },
+ "azure/gpt-3.5-turbo-0125": {
+ max_tokens: 4096,
+ max_input_tokens: 16384,
+ max_output_tokens: 4096,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ deprecation_date: "2025-03-31",
+ supports_tool_choice: true,
+ },
+ "azure/gpt-3.5-turbo": {
+ max_tokens: 4096,
+ max_input_tokens: 4097,
+ max_output_tokens: 4096,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ max_tokens: 8192,
+ max_input_tokens: 2097152,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "us.meta.llama3-3-70b-instruct-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ },
+ "perplexity/sonar": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
+ litellm_provider: "perplexity",
+ mode: "chat",
+ search_context_cost_per_query: {
+ search_context_size_low: 0.005,
+ search_context_size_medium: 0.008,
+ search_context_size_high: 0.012,
+ },
+ supports_web_search: true,
+ },
+ "perplexity/sonar-pro": {
+ max_tokens: 8000,
+ max_input_tokens: 200000,
+ max_output_tokens: 8000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "perplexity",
+ mode: "chat",
+ search_context_cost_per_query: {
+ search_context_size_low: 0.006,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.014,
+ },
+ supports_web_search: true,
+ },
+ "openrouter/google/gemini-2.0-flash-001": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ },
+ "gpt-4.5-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000075,
+ output_cost_per_token: 0.00015,
+ input_cost_per_token_batches: 0.0000375,
+ output_cost_per_token_batches: 0.000075,
+ cache_read_input_token_cost: 0.0000375,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "gpt-4.5-preview-2025-02-27": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000075,
+ output_cost_per_token: 0.00015,
+ input_cost_per_token_batches: 0.0000375,
+ output_cost_per_token_batches: 0.000075,
+ cache_read_input_token_cost: 0.0000375,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-07-14",
+ },
+ "azure_ai/Phi-4": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.25e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_vision: false,
+ source:
+ "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "cerebras/llama3.3-70b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 8.5e-7,
+ output_cost_per_token: 0.0000012,
+ litellm_provider: "cerebras",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "claude-3-5-haiku-latest": {
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
+ cache_creation_input_token_cost: 0.00000125,
+ cache_read_input_token_cost: 1e-7,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 264,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2025-10-01",
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "claude-3-7-sonnet-latest": {
+ supports_computer_use: true,
+ max_tokens: 128000,
+ max_input_tokens: 200000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2025-06-01",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "claude-3-7-sonnet-20250219": {
+ supports_computer_use: true,
+ max_tokens: 128000,
+ max_input_tokens: 200000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2026-02-01",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_web_search: true,
+ },
+ "vertex_ai/claude-3-7-sonnet@20250219": {
+ supports_computer_use: true,
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_pdf_input: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ deprecation_date: "2025-06-01",
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/anthropic/claude-3.7-sonnet": {
+ supports_computer_use: true,
+ max_tokens: 128000,
+ max_input_tokens: 200000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ input_cost_per_image: 0.0048,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/anthropic/claude-3.7-sonnet:beta": {
+ supports_computer_use: true,
+ max_tokens: 128000,
+ max_input_tokens: 200000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ input_cost_per_image: 0.0048,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_tool_choice: true,
+ },
+ "amazon.rerank-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 32000,
+ max_query_tokens: 32000,
+ max_document_chunks_per_query: 100,
+ max_tokens_per_document_chunk: 512,
+ input_cost_per_token: 0,
+ input_cost_per_query: 0.001,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "rerank",
+ },
+ "anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ supports_computer_use: true,
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_pdf_input: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ supports_computer_use: true,
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "cohere.rerank-v3-5:0": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 32000,
+ max_query_tokens: 32000,
+ max_document_chunks_per_query: 100,
+ max_tokens_per_document_chunk: 512,
+ input_cost_per_token: 0,
+ input_cost_per_query: 0.002,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "rerank",
+ },
+ "jina-reranker-v2-base-multilingual": {
+ max_tokens: 1024,
+ max_input_tokens: 1024,
+ max_output_tokens: 1024,
+ max_document_chunks_per_query: 2048,
+ input_cost_per_token: 1.8e-8,
+ output_cost_per_token: 1.8e-8,
+ litellm_provider: "jina_ai",
+ mode: "rerank",
+ },
+ "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ metadata: {
+ notes: "Anthropic via Invoke route does not currently support pdf input.",
+ },
+ },
+ "azure/gpt-4o-mini-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 6e-7,
+ input_cost_per_audio_token: 0.00001,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_audio_token_cost: 3e-7,
+ output_cost_per_token: 0.0000024,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 6.6e-7,
+ input_cost_per_audio_token: 0.000011,
+ cache_read_input_token_cost: 3.3e-7,
+ cache_creation_input_audio_token_cost: 3.3e-7,
+ output_cost_per_token: 0.00000264,
+ output_cost_per_audio_token: 0.000022,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 6.6e-7,
+ input_cost_per_audio_token: 0.000011,
+ cache_read_input_token_cost: 3.3e-7,
+ cache_creation_input_audio_token_cost: 3.3e-7,
+ output_cost_per_token: 0.00000264,
+ output_cost_per_audio_token: 0.000022,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/gpt-4o-realtime-preview-2024-10-01": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.0001,
+ cache_read_input_token_cost: 0.0000025,
+ cache_creation_input_audio_token_cost: 0.00002,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.0002,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/gpt-4o-realtime-preview-2024-10-01": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000055,
+ input_cost_per_audio_token: 0.00011,
+ cache_read_input_token_cost: 0.00000275,
+ cache_creation_input_audio_token_cost: 0.000022,
+ output_cost_per_token: 0.000022,
+ output_cost_per_audio_token: 0.00022,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-realtime-preview-2024-10-01": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000055,
+ input_cost_per_audio_token: 0.00011,
+ cache_read_input_token_cost: 0.00000275,
+ cache_creation_input_audio_token_cost: 0.000022,
+ output_cost_per_token: 0.000022,
+ output_cost_per_audio_token: 0.00022,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/o3-mini-2025-01-31": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00000121,
+ input_cost_per_token_batches: 6.05e-7,
+ output_cost_per_token: 0.00000484,
+ output_cost_per_token_batches: 0.00000242,
+ cache_read_input_token_cost: 6.05e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_vision: false,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/o3-mini-2025-01-31": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00000121,
+ input_cost_per_token_batches: 6.05e-7,
+ output_cost_per_token: 0.00000484,
+ output_cost_per_token_batches: 0.00000242,
+ cache_read_input_token_cost: 6.05e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_vision: false,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/o1-mini-2024-09-12": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.00000121,
+ input_cost_per_token_batches: 6.05e-7,
+ output_cost_per_token: 0.00000484,
+ output_cost_per_token_batches: 0.00000242,
+ cache_read_input_token_cost: 6.05e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ },
+ "azure/eu/o1-mini-2024-09-12": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.00000121,
+ input_cost_per_token_batches: 6.05e-7,
+ output_cost_per_token: 0.00000484,
+ output_cost_per_token_batches: 0.00000242,
+ cache_read_input_token_cost: 6.05e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ },
+ "azure/us/o1-2024-12-17": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000165,
+ output_cost_per_token: 0.000066,
+ cache_read_input_token_cost: 0.00000825,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/o1-2024-12-17": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000165,
+ output_cost_per_token: 0.000066,
+ cache_read_input_token_cost: 0.00000825,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/o1-preview-2024-09-12": {
+ max_tokens: 32768,
+ max_input_tokens: 128000,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.0000165,
+ output_cost_per_token: 0.000066,
+ cache_read_input_token_cost: 0.00000825,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ },
+ "azure/eu/o1-preview-2024-09-12": {
+ max_tokens: 32768,
+ max_input_tokens: 128000,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.0000165,
+ output_cost_per_token: 0.000066,
+ cache_read_input_token_cost: 0.00000825,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ },
+ "azure/us/gpt-4o-2024-11-20": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000275,
+ cache_creation_input_token_cost: 0.00000138,
+ output_cost_per_token: 0.000011,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-2024-11-20": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000275,
+ cache_creation_input_token_cost: 0.00000138,
+ output_cost_per_token: 0.000011,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/gpt-4o-2024-08-06": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000275,
+ output_cost_per_token: 0.000011,
+ cache_read_input_token_cost: 0.000001375,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-2024-08-06": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000275,
+ output_cost_per_token: 0.000011,
+ cache_read_input_token_cost: 0.000001375,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/gpt-4o-mini-2024-07-18": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.65e-7,
+ output_cost_per_token: 6.6e-7,
+ cache_read_input_token_cost: 8.3e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-mini-2024-07-18": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.65e-7,
+ output_cost_per_token: 6.6e-7,
+ cache_read_input_token_cost: 8.3e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure_ai/deepseek-v3": {
+ max_tokens: 8192,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.00000114,
+ output_cost_per_token: 0.00000456,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_tool_choice: true,
+ source:
+ "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
+ },
+ "azure_ai/mistral-nemo": {
+ max_tokens: 4096,
+ max_input_tokens: 131072,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ source:
+ "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
+ },
+ "azure_ai/Phi-4-mini-instruct": {
+ max_tokens: 4096,
+ max_input_tokens: 131072,
+ max_output_tokens: 4096,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ source:
+ "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112",
+ },
+ "azure_ai/Phi-4-multimodal-instruct": {
+ max_tokens: 4096,
+ max_input_tokens: 131072,
+ max_output_tokens: 4096,
+ input_cost_per_token: 8e-8,
+ input_cost_per_audio_token: 0.000004,
+ output_cost_per_token: 3.2e-7,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_audio_input: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ source:
+ "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112",
+ },
+ "gemini/gemini-2.0-pro-exp-02-05": {
+ max_tokens: 8192,
+ max_input_tokens: 2097152,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 2,
+ tpm: 1000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-thinking-exp-01-21": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65536,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ tpm: 4000000,
+ rpm: 10,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemma-3-27b-it": {
+ max_tokens: 8192,
+ max_input_tokens: 131072,
+ max_output_tokens: 8192,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ source: "https://aistudio.google.com",
+ supports_tool_choice: true,
+ },
+ "gemini/learnlm-1.5-pro-experimental": {
+ max_tokens: 8192,
+ max_input_tokens: 32767,
+ max_output_tokens: 8192,
+ input_cost_per_image: 0,
+ input_cost_per_video_per_second: 0,
+ input_cost_per_audio_per_second: 0,
+ input_cost_per_token: 0,
+ input_cost_per_character: 0,
+ input_cost_per_token_above_128k_tokens: 0,
+ input_cost_per_character_above_128k_tokens: 0,
+ input_cost_per_image_above_128k_tokens: 0,
+ input_cost_per_video_per_second_above_128k_tokens: 0,
+ input_cost_per_audio_per_second_above_128k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_character: 0,
+ output_cost_per_token_above_128k_tokens: 0,
+ output_cost_per_character_above_128k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ source: "https://aistudio.google.com",
+ supports_tool_choice: true,
+ },
+ "vertex_ai/imagen-3.0-generate-002": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "jamba-large-1.6": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "ai21",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "jamba-mini-1.6": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "ai21",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "eu.amazon.nova-micro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 128000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 4.6e-8,
+ output_cost_per_token: 1.84e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "eu.amazon.nova-lite-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 7.8e-8,
+ output_cost_per_token: 3.12e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": {
+ max_input_tokens: 2600,
+ output_cost_per_image: 0.06,
+ litellm_provider: "bedrock",
+ mode: "image_generation",
+ },
+ "eu.amazon.nova-pro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 0.00000105,
+ output_cost_per_token: 0.0000042,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ source: "https://aws.amazon.com/bedrock/pricing/",
+ },
+ "us.deepseek.r1-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00000135,
+ output_cost_per_token: 0.0000054,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_function_calling: false,
+ supports_tool_choice: false,
+ },
+ "snowflake/deepseek-r1": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ supports_reasoning: true,
+ mode: "chat",
+ },
+ "snowflake/snowflake-arctic": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/claude-3-5-sonnet": {
+ supports_computer_use: true,
+ max_tokens: 18000,
+ max_input_tokens: 18000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/mistral-large": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/mistral-large2": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/reka-flash": {
+ max_tokens: 100000,
+ max_input_tokens: 100000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/reka-core": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/jamba-instruct": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/jamba-1.5-mini": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/jamba-1.5-large": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/mixtral-8x7b": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama2-70b-chat": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3-8b": {
+ max_tokens: 8000,
+ max_input_tokens: 8000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3-70b": {
+ max_tokens: 8000,
+ max_input_tokens: 8000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.1-8b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.1-70b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.3-70b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/snowflake-llama-3.3-70b": {
+ max_tokens: 8000,
+ max_input_tokens: 8000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.1-405b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/snowflake-llama-3.1-405b": {
+ max_tokens: 8000,
+ max_input_tokens: 8000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.2-1b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/llama3.2-3b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/mistral-7b": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "snowflake/gemma-7b": {
+ max_tokens: 8000,
+ max_input_tokens: 8000,
+ max_output_tokens: 8192,
+ litellm_provider: "snowflake",
+ mode: "chat",
+ },
+ "azure/global/gpt-4o-2024-11-20": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "azure/global/gpt-4o-2024-08-06": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_tool_choice: true,
+ },
+ "o1-pro": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00015,
+ output_cost_per_token: 0.0006,
+ input_cost_per_token_batches: 0.000075,
+ output_cost_per_token_batches: 0.0003,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_native_streaming: false,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ },
+ "o1-pro-2025-03-19": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00015,
+ output_cost_per_token: 0.0006,
+ input_cost_per_token_batches: 0.000075,
+ output_cost_per_token_batches: 0.0003,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_native_streaming: false,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ },
+ "gpt-4o-search-preview-2025-03-11": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "gpt-4o-search-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.03,
+ search_context_size_medium: 0.035,
+ search_context_size_high: 0.05,
+ },
+ },
+ "gpt-4o-mini-search-preview-2025-03-11": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "gpt-4o-mini-search-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.025,
+ search_context_size_medium: 0.0275,
+ search_context_size_high: 0.03,
+ },
+ },
+ "azure/gpt-4.5-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000075,
+ output_cost_per_token: 0.00015,
+ input_cost_per_token_batches: 0.0000375,
+ output_cost_per_token_batches: 0.000075,
+ cache_read_input_token_cost: 0.0000375,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure_ai/mistral-small-2503": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ },
+ "text-embedding-large-exp-03-07": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ output_vector_size: 3072,
+ input_cost_per_character: 2.5e-8,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-embedding-models",
+ mode: "embedding",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models",
+ },
+ "gpt-4.1": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "gpt-4.1-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "gpt-4.1-mini": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "gpt-4.1-mini-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "gpt-4.1-nano": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "gpt-4.1-nano-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "watsonx/ibm/granite-3-8b-instruct": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 1024,
+ input_cost_per_token: 0.0002,
+ output_cost_per_token: 0.0002,
+ litellm_provider: "watsonx",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_audio_input: false,
+ supports_audio_output: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_system_messages: true,
+ },
+ "computer-use-preview": {
+ max_tokens: 1024,
+ max_input_tokens: 8192,
+ max_output_tokens: 1024,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: false,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ o3: {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/responses",
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "o3-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/responses",
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "o4-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "o4-mini-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "low/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0490417e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "medium/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "high/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.59263611e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "low/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "medium/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "high/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "low/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "medium/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "high/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "gpt-4o-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.000006,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "gpt-4o-mini-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_audio_token: 0.000003,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "gpt-4o-mini-tts": {
+ mode: "audio_speech",
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.000012,
+ output_cost_per_second: 0.00025,
+ litellm_provider: "openai",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["audio"],
+ supported_endpoints: ["/v1/audio/speech"],
+ },
+ "azure/computer-use-preview": {
+ max_tokens: 1024,
+ max_input_tokens: 8192,
+ max_output_tokens: 1024,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: false,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-4o-audio-preview-2024-12-17": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: false,
+ supports_vision: false,
+ supports_prompt_caching: false,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: false,
+ },
+ "azure/gpt-4o-mini-audio-preview-2024-12-17": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: false,
+ supports_vision: false,
+ supports_prompt_caching: false,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: false,
+ },
+ "azure/gpt-4.1": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_web_search: false,
+ },
+ "azure/gpt-4.1-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_web_search: false,
+ },
+ "azure/gpt-4.1-mini": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_web_search: false,
+ },
+ "azure/gpt-4.1-mini-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_web_search: false,
+ },
+ "azure/gpt-4.1-nano": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "azure/gpt-4.1-nano-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "azure/o3": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/o3-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/o4-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/gpt-4o-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/us/gpt-4o-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000055,
+ input_cost_per_audio_token: 0.000044,
+ cache_read_input_token_cost: 0.00000275,
+ cache_read_input_audio_token_cost: 0.0000025,
+ output_cost_per_token: 0.000022,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/eu/gpt-4o-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000055,
+ input_cost_per_audio_token: 0.000044,
+ cache_read_input_token_cost: 0.00000275,
+ cache_read_input_audio_token_cost: 0.0000025,
+ output_cost_per_token: 0.000022,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "azure/o4-mini-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/low/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0490417e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/medium/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/high/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.59263611e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/low/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/medium/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/high/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/low/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/medium/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure/high/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "azure_ai/mistral-large-latest": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "azure_ai",
+ supports_function_calling: true,
+ mode: "chat",
+ source:
+ "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
+ supports_tool_choice: true,
+ },
+ "xai/grok-3-beta": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-fast-beta": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000025,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-fast-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000025,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini-beta": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini-fast-beta": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini-fast-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "groq/whisper-large-v3": {
+ input_cost_per_second: 0.00003083,
+ output_cost_per_second: 0,
+ litellm_provider: "groq",
+ mode: "audio_transcription",
+ },
+ "groq/whisper-large-v3-turbo": {
+ input_cost_per_second: 0.00001111,
+ output_cost_per_second: 0,
+ litellm_provider: "groq",
+ mode: "audio_transcription",
+ },
+ "groq/distil-whisper-large-v3-en": {
+ input_cost_per_second: 0.00000556,
+ output_cost_per_second: 0,
+ litellm_provider: "groq",
+ mode: "audio_transcription",
+ },
+ "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": {
+ max_tokens: 128000,
+ max_input_tokens: 10000000,
+ max_output_tokens: 4028,
+ litellm_provider: "meta_llama",
+ mode: "chat",
+ supports_function_calling: true,
+ source: "https://llama.developer.meta.com/docs/models",
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
+ max_tokens: 128000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 4028,
+ litellm_provider: "meta_llama",
+ mode: "chat",
+ supports_function_calling: true,
+ source: "https://llama.developer.meta.com/docs/models",
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "meta_llama/Llama-3.3-70B-Instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4028,
+ litellm_provider: "meta_llama",
+ mode: "chat",
+ supports_function_calling: true,
+ source: "https://llama.developer.meta.com/docs/models",
+ supports_tool_choice: true,
+ supported_modalities: ["text"],
+ supported_output_modalities: ["text"],
+ },
+ "meta_llama/Llama-3.3-8B-Instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4028,
+ litellm_provider: "meta_llama",
+ mode: "chat",
+ supports_function_calling: true,
+ source: "https://llama.developer.meta.com/docs/models",
+ supports_tool_choice: true,
+ supported_modalities: ["text"],
+ supported_output_modalities: ["text"],
+ },
+ "gemini-2.5-pro-exp-03-25": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-pro-exp-03-25": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 0,
+ input_cost_per_token_above_200k_tokens: 0,
+ output_cost_per_token: 0,
+ output_cost_per_token_above_200k_tokens: 0,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 5,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_web_search: true,
+ cache_read_input_token_cost: 0,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-flash-preview-04-17": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ output_cost_per_reasoning_token: 0.0000035,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.75e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash-preview-04-17": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ output_cost_per_reasoning_token: 0.0000035,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.75e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_audio_input: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ supports_tool_choice: true,
+ source: "https://ai.google.dev/pricing#2_0flash",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-lite": {
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 50,
+ input_cost_per_audio_token: 7.5e-8,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 1.875e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-lite-001": {
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 50,
+ input_cost_per_audio_token: 7.5e-8,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+ supports_tool_choice: true,
+ deprecation_date: "2026-02-25",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 1.875e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-pro-preview-05-06": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.00000125,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ supported_regions: ["global"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-pro-preview-03-25": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.00000125,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-lite": {
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 50,
+ input_cost_per_audio_token: 7.5e-8,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ tpm: 4000000,
+ rpm: 4000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite",
+ supports_web_search: true,
+ cache_read_input_token_cost: 1.875e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-pro-preview-05-06": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-pro-preview-03-25": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": {
+ max_tokens: 10000000,
+ max_input_tokens: 10000000,
+ max_output_tokens: 10000000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 7e-7,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
+ supports_function_calling: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": {
+ max_tokens: 10000000,
+ max_input_tokens: 10000000,
+ max_output_tokens: 10000000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 7e-7,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
+ supports_function_calling: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 0.00000115,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
+ supports_function_calling: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 0.00000115,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_tool_choice: true,
+ supports_function_calling: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "vertex_ai/mistral-small-2503@001": {
+ max_tokens: 8191,
+ max_input_tokens: 32000,
+ max_output_tokens: 8191,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "vertex_ai-mistral_models",
+ supports_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "vertex_ai/mistral-small-2503": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "vertex_ai-mistral_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_tool_choice: true,
+ },
+ multimodalembedding: {
+ max_tokens: 2048,
+ max_input_tokens: 2048,
+ output_vector_size: 768,
+ input_cost_per_character: 2e-7,
+ input_cost_per_image: 0.0001,
+ input_cost_per_video_per_second: 0.0005,
+ input_cost_per_video_per_second_above_8s_interval: 0.001,
+ input_cost_per_video_per_second_above_15s_interval: 0.002,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-embedding-models",
+ mode: "embedding",
+ supported_endpoints: ["/v1/embeddings"],
+ supported_modalities: ["text", "image", "video"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models",
+ },
+ "multimodalembedding@001": {
+ max_tokens: 2048,
+ max_input_tokens: 2048,
+ output_vector_size: 768,
+ input_cost_per_character: 2e-7,
+ input_cost_per_image: 0.0001,
+ input_cost_per_video_per_second: 0.0005,
+ input_cost_per_video_per_second_above_8s_interval: 0.001,
+ input_cost_per_video_per_second_above_15s_interval: 0.002,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-embedding-models",
+ mode: "embedding",
+ supported_endpoints: ["/v1/embeddings"],
+ supported_modalities: ["text", "image", "video"],
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models",
+ },
+ "command-a-03-2025": {
+ max_tokens: 8000,
+ max_input_tokens: 256000,
+ max_output_tokens: 8000,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "cohere_chat",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "mistralai/mistral-small-3.1-24b-instruct": {
+ max_tokens: 32000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "openrouter/openai/o3-mini": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_reasoning: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_tool_choice: true,
+ },
+ "openrouter/openai/o3-mini-high": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_reasoning: true,
+ supports_parallel_function_calling: true,
+ supports_vision: false,
+ supports_tool_choice: true,
+ },
+ "us.amazon.nova-premier-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.0000125,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: false,
+ supports_response_schema: true,
+ },
+ "meta.llama4-maverick-17b-instruct-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 2.4e-7,
+ input_cost_per_token_batches: 1.2e-7,
+ output_cost_per_token: 9.7e-7,
+ output_cost_per_token_batches: 4.85e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "us.meta.llama4-maverick-17b-instruct-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 2.4e-7,
+ input_cost_per_token_batches: 1.2e-7,
+ output_cost_per_token: 9.7e-7,
+ output_cost_per_token_batches: 4.85e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "meta.llama4-scout-17b-instruct-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.7e-7,
+ input_cost_per_token_batches: 8.5e-8,
+ output_cost_per_token: 6.6e-7,
+ output_cost_per_token_batches: 3.3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "us.meta.llama4-scout-17b-instruct-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.7e-7,
+ input_cost_per_token_batches: 8.5e-8,
+ output_cost_per_token: 6.6e-7,
+ output_cost_per_token_batches: 3.3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text", "code"],
+ },
+ "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
+ input_cost_per_token: 2.7e-7,
+ output_cost_per_token: 8.5e-7,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 5.9e-7,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/deepseek-ai/DeepSeek-V3": {
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00000125,
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "perplexity/sonar-deep-research": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ output_cost_per_reasoning_token: 0.000003,
+ citation_cost_per_token: 0.000002,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.005,
+ search_context_size_medium: 0.005,
+ search_context_size_high: 0.005,
+ },
+ litellm_provider: "perplexity",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_web_search: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/deepseek-r1": {
+ max_tokens: 20480,
+ max_input_tokens: 128000,
+ max_output_tokens: 20480,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ },
+ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": {
+ max_tokens: 20480,
+ max_input_tokens: 128000,
+ max_output_tokens: 20480,
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.00000219,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ },
+ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: true,
+ supports_function_calling: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.2e-7,
+ output_cost_per_token: 8.8e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ },
+ "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ },
+ "fireworks-ai-up-to-4b": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "fireworks_ai",
+ },
+ "fireworks-ai-4.1b-to-16b": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "fireworks_ai",
+ },
+ "fireworks-ai-above-16b": {
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 9e-7,
+ litellm_provider: "fireworks_ai",
+ },
+ "databricks/databricks-claude-3-7-sonnet": {
+ max_tokens: 200000,
+ max_input_tokens: 200000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.0000025,
+ input_dbu_cost_per_token: 0.00003571,
+ output_cost_per_token: 0.000017857,
+ output_db_cost_per_token: 0.000214286,
+ litellm_provider: "databricks",
+ mode: "chat",
+ source:
+ "https://www.databricks.com/product/pricing/foundation-model-serving",
+ metadata: {
+ notes:
+ "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
+ },
+ supports_assistant_prefill: true,
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "databricks/databricks-meta-llama-3-3-70b-instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000100002,
+ input_dbu_cost_per_token: 0.000014286,
+ output_cost_per_token: 0.00000299999,
+ output_dbu_cost_per_token: 0.000042857,
+ litellm_provider: "databricks",
+ mode: "chat",
+ source:
+ "https://www.databricks.com/product/pricing/foundation-model-serving",
+ metadata: {
+ notes:
+ "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation.",
+ },
+ supports_tool_choice: true,
+ },
+ "azure_ai/deepseek-v3-0324": {
+ max_tokens: 8192,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.00000114,
+ output_cost_per_token: 0.00000456,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ source:
+ "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
+ },
+ "azure_ai/Llama-4-Scout-17B-16E-Instruct": {
+ max_tokens: 16384,
+ max_input_tokens: 10000000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 7.8e-7,
+ litellm_provider: "azure_ai",
+ supports_function_calling: true,
+ supports_vision: true,
+ mode: "chat",
+ source:
+ "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
+ supports_tool_choice: true,
+ },
+ "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": {
+ max_tokens: 16384,
+ max_input_tokens: 1000000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000141,
+ output_cost_per_token: 3.5e-7,
+ litellm_provider: "azure_ai",
+ supports_function_calling: true,
+ supports_vision: true,
+ mode: "chat",
+ source:
+ "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
+ supports_tool_choice: true,
+ },
+ "cerebras/llama-3.3-70b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 8.5e-7,
+ output_cost_per_token: 0.0000012,
+ litellm_provider: "cerebras",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "perplexity/sonar-reasoning": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "perplexity",
+ mode: "chat",
+ search_context_cost_per_query: {
+ search_context_size_low: 0.005,
+ search_context_size_medium: 0.008,
+ search_context_size_high: 0.014,
+ },
+ supports_web_search: true,
+ supports_reasoning: true,
+ },
+ "perplexity/sonar-reasoning-pro": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "perplexity",
+ mode: "chat",
+ search_context_cost_per_query: {
+ search_context_size_low: 0.006,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.014,
+ },
+ supports_web_search: true,
+ supports_reasoning: true,
+ },
+ "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
+ input_cost_per_token: 9e-8,
+ output_cost_per_token: 2.9e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ },
+ "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": {
+ input_cost_per_token: 1e-8,
+ output_cost_per_token: 3e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ },
+ "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ input_cost_per_token: 1e-8,
+ output_cost_per_token: 3e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ },
+ "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": {
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ },
+ "nscale/Qwen/QwQ-32B": {
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ input_cost_per_token: 3.75e-7,
+ output_cost_per_token: 3.75e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 2.5e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ input_cost_per_token: 9e-8,
+ output_cost_per_token: 9e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 7e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/mistralai/mixtral-8x22b-instruct-v0.1": {
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/meta-llama/Llama-3.1-8B-Instruct": {
+ input_cost_per_token: 3e-8,
+ output_cost_per_token: 3e-8,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/meta-llama/Llama-3.3-70B-Instruct": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "nscale",
+ mode: "chat",
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
+ metadata: {
+ notes:
+ "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output.",
+ },
+ },
+ "nscale/black-forest-labs/FLUX.1-schnell": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.3e-9,
+ output_cost_per_pixel: 0,
+ litellm_provider: "nscale",
+ supported_endpoints: ["/v1/images/generations"],
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#image-models",
+ },
+ "nscale/stabilityai/stable-diffusion-xl-base-1.0": {
+ mode: "image_generation",
+ input_cost_per_pixel: 3e-9,
+ output_cost_per_pixel: 0,
+ litellm_provider: "nscale",
+ supported_endpoints: ["/v1/images/generations"],
+ source:
+ "https://docs.nscale.com/docs/inference/serverless-models/current#image-models",
+ },
+ "azure/gpt-4o-mini-tts": {
+ mode: "audio_speech",
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.000012,
+ output_cost_per_second: 0.00025,
+ litellm_provider: "azure",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["audio"],
+ supported_endpoints: ["/v1/audio/speech"],
+ },
+ "azure_ai/embed-v-4-0": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ output_vector_size: 3072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "azure_ai",
+ mode: "embedding",
+ supports_embedding_image_input: true,
+ supported_endpoints: ["/v1/embeddings"],
+ supported_modalities: ["text", "image"],
+ source:
+ "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
+ },
+ "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ supports_computer_use: true,
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "xai/grok-3": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "groq/llama-guard-3-8b": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ },
+ "groq/meta-llama/llama-4-scout-17b-16e-instruct": {
+ max_tokens: 8192,
+ max_input_tokens: 131072,
+ max_output_tokens: 8192,
+ input_cost_per_token: 1.1e-7,
+ output_cost_per_token: 3.4e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "groq/meta-llama/llama-4-maverick-17b-128e-instruct": {
+ max_tokens: 8192,
+ max_input_tokens: 131072,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "groq/mistral-saba-24b": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 7.9e-7,
+ output_cost_per_token: 7.9e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ },
+ "groq/qwen-qwq-32b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.9e-7,
+ output_cost_per_token: 3.9e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "groq/playai-tts": {
+ max_tokens: 10000,
+ max_input_tokens: 10000,
+ max_output_tokens: 10000,
+ input_cost_per_character: 0.00005,
+ litellm_provider: "groq",
+ mode: "audio_speech",
+ },
+ "claude-opus-4-20250514": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "claude-sonnet-4-20250514": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "gemini/gemini-2.5-flash-preview-tts": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ output_cost_per_reasoning_token: 0.0000035,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text"],
+ supported_output_modalities: ["audio"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.75e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-flash-preview-05-20": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash-preview-05-20": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-preview-image-generation": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_audio_input: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ supports_tool_choice: true,
+ source: "https://ai.google.dev/pricing#2_0flash",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-pro-preview-tts": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text"],
+ supported_output_modalities: ["audio"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.0-flash-preview-image-generation": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_audio_input: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ supports_tool_choice: true,
+ source: "https://ai.google.dev/pricing#2_0flash",
+ supports_web_search: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-pro-preview-tts": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text"],
+ supported_output_modalities: ["audio"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "vertex_ai/claude-opus-4@20250514": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "vertex_ai/claude-sonnet-4@20250514": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "anthropic.claude-opus-4-20250514-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "anthropic.claude-sonnet-4-20250514-v1:0": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "us.anthropic.claude-opus-4-20250514-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "us.anthropic.claude-sonnet-4-20250514-v1:0": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "eu.anthropic.claude-opus-4-20250514-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "databricks/databricks-llama-4-maverick": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000005,
+ input_dbu_cost_per_token: 0.00007143,
+ output_cost_per_token: 0.000015,
+ output_dbu_cost_per_token: 0.00021429,
+ litellm_provider: "databricks",
+ mode: "chat",
+ source:
+ "https://www.databricks.com/product/pricing/foundation-model-serving",
+ metadata: {
+ notes:
+ "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token).",
+ },
+ supports_tool_choice: true,
+ },
+ "sambanova/Llama-4-Maverick-17B-128E-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6.3e-7,
+ output_cost_per_token: 0.0000018,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ metadata: {
+ notes:
+ "For vision models, images are converted to 6432 input tokens and are billed at that amount",
+ },
+ },
+ "sambanova/Llama-4-Scout-17B-16E-Instruct": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 7e-7,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ metadata: {
+ notes:
+ "For vision models, images are converted to 6432 input tokens and are billed at that amount",
+ },
+ },
+ "sambanova/Meta-Llama-Guard-3-8B": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/Qwen3-32B": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "sambanova",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/QwQ-32B": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.000001,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/Qwen2-Audio-7B-Instruct": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0001,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ supports_audio_input: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/DeepSeek-R1-Distill-Llama-70B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 7e-7,
+ output_cost_per_token: 0.0000014,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/DeepSeek-R1": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000007,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "sambanova/DeepSeek-V3-0324": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.0000045,
+ litellm_provider: "sambanova",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://cloud.sambanova.ai/plans/pricing",
+ },
+ "featherless_ai/featherless-ai/Qwerky-72B": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 4096,
+ litellm_provider: "featherless_ai",
+ mode: "chat",
+ },
+ "featherless_ai/featherless-ai/Qwerky-QwQ-32B": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 4096,
+ litellm_provider: "featherless_ai",
+ mode: "chat",
+ },
+ "azure_ai/mistral-medium-2505": {
+ max_tokens: 8191,
+ max_input_tokens: 131072,
+ max_output_tokens: 8191,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ },
+ "mistral/devstral-small-2505": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/news/devstral",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ },
+ "gpt-4o-mini-audio-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ input_cost_per_audio_token: 0.00001,
+ output_cost_per_token: 6e-7,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "mistral/mistral-medium-2505": {
+ max_tokens: 8191,
+ max_input_tokens: 131072,
+ max_output_tokens: 8191,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "mistral",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ },
+ "embed-v4.0": {
+ max_tokens: 1024,
+ max_input_tokens: 1024,
+ input_cost_per_token: 1.2e-7,
+ input_cost_per_image: 4.7e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "cohere",
+ mode: "embedding",
+ supports_image_input: true,
+ supports_embedding_image_input: true,
+ metadata: {
+ notes:
+ "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead.",
+ },
+ },
+ "cerebras/qwen-3-32b": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "cerebras",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ source: "https://inference-docs.cerebras.ai/support/pricing",
+ },
+ "gemini-embedding-001": {
+ max_tokens: 2048,
+ max_input_tokens: 2048,
+ output_vector_size: 3072,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-embedding-models",
+ mode: "embedding",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models",
+ },
+ "claude-4-opus-20250514": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "claude-4-sonnet-20250514": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ input_cost_per_token_above_200k_tokens: 0.000006,
+ output_cost_per_token_above_200k_tokens: 0.0000225,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_token_cost_above_200k_tokens: 0.0000075,
+ cache_read_input_token_cost_above_200k_tokens: 6e-7,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 9e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_tool_choice: false,
+ supports_vision: true,
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ },
+ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": {
+ max_tokens: 160000,
+ max_input_tokens: 160000,
+ max_output_tokens: 160000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: false,
+ supports_response_schema: true,
+ },
+ "codex-mini-latest": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000006,
+ cache_read_input_token_cost: 3.75e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses"],
+ },
+ "azure/codex-mini-latest": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000006,
+ cache_read_input_token_cost: 3.75e-7,
+ litellm_provider: "azure",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses"],
+ },
+ "gemini-2.5-pro-preview-06-05": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.00000125,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-pro-preview-06-05": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10000,
+ tpm: 10000000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "openai/gpt-4": {
+ max_tokens: 4096,
+ max_input_tokens: 8192,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-audio-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.0001,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.0002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-audio-preview-2024-10-01": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.0001,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.0002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini-2024-07-18": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.025,
+ search_context_size_medium: 0.0275,
+ search_context_size_high: 0.03,
+ },
+ },
+ "openai/o1-mini": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ },
+ "openai/o1-mini-2024-09-12": {
+ max_tokens: 65536,
+ max_input_tokens: 128000,
+ max_output_tokens: 65536,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000012,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ },
+ "openai/o1-preview": {
+ max_tokens: 32768,
+ max_input_tokens: 128000,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ },
+ "openai/o1-preview-2024-09-12": {
+ max_tokens: 32768,
+ max_input_tokens: 128000,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ },
+ "openai/chatgpt-4o-latest": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-2024-05-13": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000015,
+ input_cost_per_token_batches: 0.0000025,
+ output_cost_per_token_batches: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-2024-08-06": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-turbo-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-0314": {
+ max_tokens: 4096,
+ max_input_tokens: 8192,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-0613": {
+ max_tokens: 4096,
+ max_input_tokens: 8192,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ deprecation_date: "2025-06-06",
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-32k": {
+ max_tokens: 4096,
+ max_input_tokens: 32768,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00006,
+ output_cost_per_token: 0.00012,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-32k-0314": {
+ max_tokens: 4096,
+ max_input_tokens: 32768,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00006,
+ output_cost_per_token: 0.00012,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-32k-0613": {
+ max_tokens: 4096,
+ max_input_tokens: 32768,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00006,
+ output_cost_per_token: 0.00012,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-turbo": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-turbo-2024-04-09": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-1106-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-0125-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-vision-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ deprecation_date: "2024-12-06",
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4-1106-vision-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ deprecation_date: "2024-12-06",
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo": {
+ max_tokens: 4097,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-0301": {
+ max_tokens: 4097,
+ max_input_tokens: 4097,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-0613": {
+ max_tokens: 4097,
+ max_input_tokens: 4097,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-1106": {
+ max_tokens: 16385,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-0125": {
+ max_tokens: 16385,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-16k": {
+ max_tokens: 16385,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-3.5-turbo-16k-0613": {
+ max_tokens: 16385,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-3.5-turbo": {
+ max_tokens: 4096,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
+ input_cost_per_token_batches: 0.0000015,
+ output_cost_per_token_batches: 0.000003,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-3.5-turbo-0125": {
+ max_tokens: 4096,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-3.5-turbo-1106": {
+ max_tokens: 4096,
+ max_input_tokens: 16385,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-3.5-turbo-0613": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-4-0613": {
+ max_tokens: 4096,
+ max_input_tokens: 8192,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00006,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ source:
+ "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing",
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-4o-2024-08-06": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000375,
+ output_cost_per_token: 0.000015,
+ input_cost_per_token_batches: 0.000001875,
+ output_cost_per_token_batches: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-4o-mini-2024-07-18": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000012,
+ input_cost_per_token_batches: 1.5e-7,
+ output_cost_per_token_batches: 6e-7,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/text-embedding-3-large": {
+ max_tokens: 8191,
+ max_input_tokens: 8191,
+ output_vector_size: 3072,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 0,
+ input_cost_per_token_batches: 6.5e-8,
+ output_cost_per_token_batches: 0,
+ litellm_provider: "openai",
+ mode: "embedding",
+ },
+ "openai/text-embedding-3-small": {
+ max_tokens: 8191,
+ max_input_tokens: 8191,
+ output_vector_size: 1536,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 0,
+ input_cost_per_token_batches: 1e-8,
+ output_cost_per_token_batches: 0,
+ litellm_provider: "openai",
+ mode: "embedding",
+ },
+ "openai/text-embedding-ada-002": {
+ max_tokens: 8191,
+ max_input_tokens: 8191,
+ output_vector_size: 1536,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "embedding",
+ },
+ "openai/text-embedding-ada-002-v2": {
+ max_tokens: 8191,
+ max_input_tokens: 8191,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 0,
+ litellm_provider: "openai",
+ mode: "embedding",
+ },
+ "openai/text-moderation-stable": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/text-moderation-007": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/text-moderation-latest": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/256-x-256/dall-e-2": {
+ mode: "image_generation",
+ input_cost_per_pixel: 2.4414e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/512-x-512/dall-e-2": {
+ mode: "image_generation",
+ input_cost_per_pixel: 6.86e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/1024-x-1024/dall-e-2": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.9e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/hd/1024-x-1792/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 6.539e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/hd/1792-x-1024/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 6.539e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/hd/1024-x-1024/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 7.629e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/standard/1024-x-1792/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.359e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/standard/1792-x-1024/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.359e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/standard/1024-x-1024/dall-e-3": {
+ mode: "image_generation",
+ input_cost_per_pixel: 3.81469e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ },
+ "openai/whisper-1": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0.0001,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "openai/tts-1": {
+ mode: "audio_speech",
+ input_cost_per_character: 0.000015,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/speech"],
+ },
+ "openai/tts-1-hd": {
+ mode: "audio_speech",
+ input_cost_per_character: 0.00003,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/speech"],
+ },
+ "openai/gpt-4o-2024-11-20": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/ft:gpt-4o-2024-11-20": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.00000375,
+ cache_creation_input_token_cost: 0.000001875,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/omni-moderation-latest": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/omni-moderation-latest-intents": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/omni-moderation-2024-09-26": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 0,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "openai",
+ mode: "moderation",
+ },
+ "openai/gpt-4o-audio-preview-2024-12-17": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini-audio-preview-2024-12-17": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ input_cost_per_audio_token: 0.00001,
+ output_cost_per_token: 6e-7,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/o1": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/o1-2024-12-17": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ cache_read_input_token_cost: 0.0000075,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-realtime-preview-2024-10-01": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.0001,
+ cache_read_input_token_cost: 0.0000025,
+ cache_creation_input_audio_token_cost: 0.00002,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.0002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-realtime-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini-realtime-preview": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 6e-7,
+ input_cost_per_audio_token: 0.00001,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_audio_token_cost: 3e-7,
+ output_cost_per_token: 0.0000024,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini-realtime-preview-2024-12-17": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 6e-7,
+ input_cost_per_audio_token: 0.00001,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_audio_token_cost: 3e-7,
+ output_cost_per_token: 0.0000024,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/o3-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/o3-mini-2025-01-31": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 5.5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4.5-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000075,
+ output_cost_per_token: 0.00015,
+ input_cost_per_token_batches: 0.0000375,
+ output_cost_per_token_batches: 0.000075,
+ cache_read_input_token_cost: 0.0000375,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4.5-preview-2025-02-27": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000075,
+ output_cost_per_token: 0.00015,
+ input_cost_per_token_batches: 0.0000375,
+ output_cost_per_token_batches: 0.000075,
+ cache_read_input_token_cost: 0.0000375,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ deprecation_date: "2025-07-14",
+ },
+ "openai/o1-pro": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00015,
+ output_cost_per_token: 0.0006,
+ input_cost_per_token_batches: 0.000075,
+ output_cost_per_token_batches: 0.0003,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_native_streaming: false,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ },
+ "openai/o1-pro-2025-03-19": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00015,
+ output_cost_per_token: 0.0006,
+ input_cost_per_token_batches: 0.000075,
+ output_cost_per_token_batches: 0.0003,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_native_streaming: false,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ },
+ "openai/gpt-4o-search-preview-2025-03-11": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-search-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ input_cost_per_token_batches: 0.00000125,
+ output_cost_per_token_batches: 0.000005,
+ cache_read_input_token_cost: 0.00000125,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.03,
+ search_context_size_medium: 0.035,
+ search_context_size_high: 0.05,
+ },
+ },
+ "openai/gpt-4o-mini-search-preview-2025-03-11": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-mini-search-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ input_cost_per_token_batches: 7.5e-8,
+ output_cost_per_token_batches: 3e-7,
+ cache_read_input_token_cost: 7.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.025,
+ search_context_size_medium: 0.0275,
+ search_context_size_high: 0.03,
+ },
+ },
+ "openai/gpt-4.1": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/gpt-4.1-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/gpt-4.1-mini": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/gpt-4.1-mini-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ input_cost_per_token_batches: 2e-7,
+ output_cost_per_token_batches: 8e-7,
+ cache_read_input_token_cost: 1e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/gpt-4.1-nano": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/gpt-4.1-nano-2025-04-14": {
+ max_tokens: 32768,
+ max_input_tokens: 1047576,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ input_cost_per_token_batches: 5e-8,
+ output_cost_per_token_batches: 2e-7,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/o3": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/responses",
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "openai/o3-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/responses",
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "openai/o4-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/o4-mini-2025-04-16": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ cache_read_input_token_cost: 2.75e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/low/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0490417e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/medium/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/high/1024-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.59263611e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/low/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/medium/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/high/1024-x-1536/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/low/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.0172526e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/medium/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 4.0054321e-8,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/high/1536-x-1024/gpt-image-1": {
+ mode: "image_generation",
+ input_cost_per_pixel: 1.58945719e-7,
+ output_cost_per_pixel: 0,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "openai/gpt-4o-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.000006,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "openai/gpt-4o-mini-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_audio_token: 0.000003,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "openai",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "openai/gpt-4o-mini-tts": {
+ mode: "audio_speech",
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.000012,
+ output_cost_per_second: 0.00025,
+ litellm_provider: "openai",
+ supported_modalities: ["text", "audio"],
+ supported_output_modalities: ["audio"],
+ supported_endpoints: ["/v1/audio/speech"],
+ },
+ "openai/gpt-4o-mini-audio-preview": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 1.5e-7,
+ input_cost_per_audio_token: 0.00001,
+ output_cost_per_token: 6e-7,
+ output_cost_per_audio_token: 0.00002,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/codex-mini-latest": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000006,
+ cache_read_input_token_cost: 3.75e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses"],
+ },
+ "gpt-4o-audio-preview-2025-06-03": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-audio-preview-2025-06-03": {
+ max_tokens: 16384,
+ max_input_tokens: 128000,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.00004,
+ output_cost_per_token: 0.00001,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "o3-pro": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ output_cost_per_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "o3-pro-2025-06-10": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ output_cost_per_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "mistral/magistral-medium-2506": {
+ max_tokens: 40000,
+ max_input_tokens: 40000,
+ max_output_tokens: 40000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/news/magistral",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ },
+ "mistral/magistral-small-2506": {
+ max_tokens: 40000,
+ max_input_tokens: 40000,
+ max_output_tokens: 40000,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/pricing#api-pricing",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ },
+ "vertex_ai/claude-opus-4": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "vertex_ai/claude-sonnet-4": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "openai/o3-pro": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ output_cost_per_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "openai/o3-pro-2025-06-10": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ output_cost_per_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "responses",
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/responses", "/v1/batch"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ },
+ "deepgram/nova-3": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-3-general": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-3-medical": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00008667,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0052,
+ calculation: "$0.0052/60 seconds = $0.00008667 per second (multilingual)",
+ },
+ },
+ "deepgram/nova-2": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-general": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-meeting": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-phonecall": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-voicemail": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-finance": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-conversationalai": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-video": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-drivethru": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-automotive": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-2-atc": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-general": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/nova-phonecall": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00007167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0043,
+ calculation: "$0.0043/60 seconds = $0.00007167 per second",
+ },
+ },
+ "deepgram/enhanced": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00024167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0145,
+ calculation: "$0.0145/60 seconds = $0.00024167 per second",
+ },
+ },
+ "deepgram/enhanced-general": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00024167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0145,
+ calculation: "$0.0145/60 seconds = $0.00024167 per second",
+ },
+ },
+ "deepgram/enhanced-meeting": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00024167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0145,
+ calculation: "$0.0145/60 seconds = $0.00024167 per second",
+ },
+ },
+ "deepgram/enhanced-phonecall": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00024167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0145,
+ calculation: "$0.0145/60 seconds = $0.00024167 per second",
+ },
+ },
+ "deepgram/enhanced-finance": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00024167,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0145,
+ calculation: "$0.0145/60 seconds = $0.00024167 per second",
+ },
+ },
+ "deepgram/base": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-general": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-meeting": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-phonecall": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-voicemail": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-finance": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-conversationalai": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/base-video": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.00020833,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ original_pricing_per_minute: 0.0125,
+ calculation: "$0.0125/60 seconds = $0.00020833 per second",
+ },
+ },
+ "deepgram/whisper": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "deepgram/whisper-tiny": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "deepgram/whisper-base": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "deepgram/whisper-small": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "deepgram/whisper-medium": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "deepgram/whisper-large": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0001,
+ output_cost_per_second: 0,
+ litellm_provider: "deepgram",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://deepgram.com/pricing",
+ metadata: {
+ notes:
+ "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models",
+ },
+ },
+ "azure/gpt-4o-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.0000025,
+ input_cost_per_audio_token: 0.000006,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "azure/gpt-4o-mini-transcribe": {
+ mode: "audio_transcription",
+ max_input_tokens: 16000,
+ max_output_tokens: 2000,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_audio_token: 0.000003,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "azure",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ },
+ "mistral/magistral-medium-latest": {
+ max_tokens: 40000,
+ max_input_tokens: 40000,
+ max_output_tokens: 40000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/news/magistral",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ },
+ "mistral/magistral-small-latest": {
+ max_tokens: 40000,
+ max_input_tokens: 40000,
+ max_output_tokens: 40000,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/pricing#api-pricing",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ },
+ "xai/grok-3-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "xai/grok-3-mini-fast": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source: "https://x.ai/api#pricing",
+ supports_web_search: true,
+ },
+ "vertex_ai/imagen-4.0-generate-preview-06-06": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "vertex_ai/imagen-4.0-ultra-generate-preview-06-06": {
+ output_cost_per_image: 0.06,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "vertex_ai/imagen-4.0-fast-generate-preview-06-06": {
+ output_cost_per_image: 0.02,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/gemini-2.5-pro": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 2000,
+ tpm: 800000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash-lite-preview-06-17": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 5e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ output_cost_per_reasoning_token: 4e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "openrouter/deepseek/deepseek-r1-0528": {
+ max_tokens: 8192,
+ max_input_tokens: 65336,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5e-7,
+ input_cost_per_token_cache_hit: 1.4e-7,
+ output_cost_per_token: 0.00000215,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_prompt_caching: true,
+ },
+ "openrouter/google/gemini-2.5-pro": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/google/gemini-2.5-flash": {
+ max_tokens: 8192,
+ max_input_tokens: 1048576,
+ max_output_tokens: 8192,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 7e-7,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/anthropic/claude-sonnet-4": {
+ supports_computer_use: true,
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ input_cost_per_image: 0.0048,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ },
+ "gemini/gemini-2.5-flash": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ tpm: 8000000,
+ rpm: 100000,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini/gemini-2.5-flash-lite-preview-06-17": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 5e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ output_cost_per_reasoning_token: 4e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 15,
+ tpm: 250000,
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-pro": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 0.00000125,
+ input_cost_per_token_above_200k_tokens: 0.0000025,
+ output_cost_per_token: 0.00001,
+ output_cost_per_token_above_200k_tokens: 0.000015,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_audio_input: true,
+ supports_video_input: true,
+ supports_pdf_input: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_web_search: true,
+ cache_read_input_token_cost: 3.125e-7,
+ supports_prompt_caching: true,
+ },
+ "apac.amazon.nova-micro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 128000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 3.7e-8,
+ output_cost_per_token: 1.48e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "apac.amazon.nova-lite-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 6.3e-8,
+ output_cost_per_token: 2.52e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "apac.amazon.nova-pro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 8.4e-7,
+ output_cost_per_token: 0.00000336,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "apac.anthropic.claude-3-haiku-20240307-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.00000125,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "apac.anthropic.claude-3-sonnet-20240229-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_computer_use: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
+ max_tokens: 64000,
+ max_input_tokens: 200000,
+ max_output_tokens: 64000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00000375,
+ cache_read_input_token_cost: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "azure/codex-mini": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000006,
+ cache_read_input_token_cost: 3.75e-7,
+ litellm_provider: "azure",
+ mode: "responses",
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supported_endpoints: ["/v1/responses"],
+ },
+ "openrouter/mistralai/mistral-small-3.1-24b-instruct": {
+ max_tokens: 32000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "openrouter/mistralai/mistral-small-3.2-24b-instruct": {
+ max_tokens: 32000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "azure/o3-pro": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ output_cost_per_token: 0.00008,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ litellm_provider: "azure",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: false,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "azure/o3-pro-2025-06-10": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00002,
+ output_cost_per_token: 0.00008,
+ input_cost_per_token_batches: 0.00001,
+ output_cost_per_token_batches: 0.00004,
+ litellm_provider: "azure",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_function_calling: true,
+ supports_parallel_function_calling: false,
+ supports_vision: true,
+ supports_prompt_caching: false,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "o3-deep-research": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ input_cost_per_token_batches: 0.000005,
+ output_cost_per_token_batches: 0.00002,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "o3-deep-research-2025-06-26": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ input_cost_per_token_batches: 0.000005,
+ output_cost_per_token_batches: 0.00002,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "o4-mini-deep-research": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "o4-mini-deep-research-2025-06-26": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/o3-deep-research": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ input_cost_per_token_batches: 0.000005,
+ output_cost_per_token_batches: 0.00002,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/o3-deep-research-2025-06-26": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ input_cost_per_token_batches: 0.000005,
+ output_cost_per_token_batches: 0.00002,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/o4-mini-deep-research": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "openai/o4-mini-deep-research-2025-06-26": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ input_cost_per_token_batches: 0.000001,
+ output_cost_per_token_batches: 0.000004,
+ cache_read_input_token_cost: 5e-7,
+ litellm_provider: "openai",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ },
+ "deepseek/deepseek-r1": {
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.5e-7,
+ input_cost_per_token_cache_hit: 1.4e-7,
+ output_cost_per_token: 0.00000219,
+ litellm_provider: "deepseek",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_prompt_caching: true,
+ },
+ "deepseek/deepseek-v3": {
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2.7e-7,
+ input_cost_per_token_cache_hit: 7e-8,
+ cache_read_input_token_cost: 7e-8,
+ cache_creation_input_token_cost: 0,
+ output_cost_per_token: 0.0000011,
+ litellm_provider: "deepseek",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_prompt_caching: true,
+ },
+ "elevenlabs/scribe_v1": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0000611,
+ output_cost_per_second: 0,
+ litellm_provider: "elevenlabs",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://elevenlabs.io/pricing",
+ metadata: {
+ original_pricing_per_hour: 0.22,
+ calculation:
+ "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)",
+ notes:
+ "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support",
+ },
+ },
+ "elevenlabs/scribe_v1_experimental": {
+ mode: "audio_transcription",
+ input_cost_per_second: 0.0000611,
+ output_cost_per_second: 0,
+ litellm_provider: "elevenlabs",
+ supported_endpoints: ["/v1/audio/transcriptions"],
+ source: "https://elevenlabs.io/pricing",
+ metadata: {
+ original_pricing_per_hour: 0.22,
+ calculation:
+ "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)",
+ notes:
+ "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model",
+ },
+ },
+ "watsonx/mistralai/mistral-large": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.00001,
+ litellm_provider: "watsonx",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_audio_input: false,
+ supports_audio_output: false,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_system_messages: true,
+ },
+ "azure/o3-deep-research": {
+ max_tokens: 100000,
+ max_input_tokens: 200000,
+ max_output_tokens: 100000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ litellm_provider: "azure",
+ mode: "responses",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_web_search: true,
+ },
+ "azure_ai/grok-3": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.0000033,
+ output_cost_per_token: 0.0000165,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source:
+ "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+ supports_web_search: true,
+ },
+ "azure_ai/global/grok-3": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_response_schema: false,
+ source:
+ "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+ supports_web_search: true,
+ },
+ "azure_ai/global/grok-3-mini": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.00000127,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source:
+ "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+ supports_web_search: true,
+ },
+ "azure_ai/grok-3-mini": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.75e-7,
+ output_cost_per_token: 0.00000138,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_response_schema: false,
+ source:
+ "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+ supports_web_search: true,
+ },
+ "azure_ai/cohere-rerank-v3.5": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ max_query_tokens: 2048,
+ input_cost_per_token: 0,
+ input_cost_per_query: 0.002,
+ output_cost_per_token: 0,
+ litellm_provider: "azure_ai",
+ mode: "rerank",
+ },
+ "mistral/devstral-small-2507": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/news/devstral",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ },
+ "mistral/devstral-medium-2507": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "mistral",
+ mode: "chat",
+ source: "https://mistral.ai/news/devstral",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_response_schema: true,
+ },
+ "xai/grok-4": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ supports_web_search: true,
+ },
+ "xai/grok-4-0709": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ supports_web_search: true,
+ },
+ "xai/grok-4-latest": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ supports_web_search: true,
+ },
+ "groq/moonshotai-kimi-k2-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "jamba-large-1.7": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "ai21",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "jamba-mini-1.7": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "ai21",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "eu.mistral.pixtral-large-2502-v1:0": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ },
+ "us.mistral.pixtral-large-2502-v1:0": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: false,
+ },
+ "together_ai/deepseek-ai/DeepSeek-R1": {
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000007,
+ max_tokens: 20480,
+ max_input_tokens: 128000,
+ max_output_tokens: 20480,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "together_ai/moonshotai/Kimi-K2-Instruct": {
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "together_ai",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_parallel_function_calling: true,
+ mode: "chat",
+ source: "https://www.together.ai/models/kimi-k2-instruct",
+ },
+ "dashscope/qwen-max": {
+ max_tokens: 32768,
+ max_input_tokens: 30720,
+ max_output_tokens: 8192,
+ litellm_provider: "dashscope",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ mode: "chat",
+ source:
+ "https://bailian.console.alibabacloud.com/?spm=a2c63.p38356.0.0.4a615d7bjSUCb4&tab=doc#/doc/?type=model&url=https%3A%2F%2Fwww.alibabacloud.com%2Fhelp%2Fen%2Fdoc-detail%2F2840914.html",
+ },
+ "dashscope/qwen-plus-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 129024,
+ max_output_tokens: 16384,
+ litellm_provider: "dashscope",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ mode: "chat",
+ source:
+ "https://bailian.console.alibabacloud.com/?spm=a2c63.p38356.0.0.4a615d7bjSUCb4&tab=doc#/doc/?type=model&url=https%3A%2F%2Fwww.alibabacloud.com%2Fhelp%2Fen%2Fdoc-detail%2F2840914.html",
+ },
+ "dashscope/qwen-turbo-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 129024,
+ max_output_tokens: 16384,
+ litellm_provider: "dashscope",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ mode: "chat",
+ source:
+ "https://bailian.console.alibabacloud.com/?spm=a2c63.p38356.0.0.4a615d7bjSUCb4&tab=doc#/doc/?type=model&url=https%3A%2F%2Fwww.alibabacloud.com%2Fhelp%2Fen%2Fdoc-detail%2F2840914.html",
+ },
+ "dashscope/qwen3-30b-a3b": {
+ max_tokens: 131072,
+ max_input_tokens: 129024,
+ max_output_tokens: 16384,
+ litellm_provider: "dashscope",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ mode: "chat",
+ source:
+ "https://bailian.console.alibabacloud.com/?spm=a2c63.p38356.0.0.4a615d7bjSUCb4&tab=doc#/doc/?type=model&url=https%3A%2F%2Fwww.alibabacloud.com%2Fhelp%2Fen%2Fdoc-detail%2F2840914.html",
+ },
+ "moonshot/moonshot-v1-8k": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-32k": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-128k": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-auto": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/kimi-k2-0711-preview": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.0000025,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ mode: "chat",
+ source:
+ "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
+ },
+ "moonshot/moonshot-v1-32k-0430": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-128k-0430": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-8k-0430": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "azure_ai/jais-30b-chat": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.0032,
+ output_cost_per_token: 0.00971,
+ litellm_provider: "azure_ai",
+ mode: "chat",
+ source:
+ "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat",
+ },
+ "groq/moonshotai/kimi-k2-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 16384,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/switchpoint/router": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 8.5e-7,
+ output_cost_per_token: 0.0000034,
+ litellm_provider: "openrouter",
+ source: "https://openrouter.ai/switchpoint/router",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "v0/v0-1.0-md": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "v0",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "v0/v0-1.5-md": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "v0",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "v0/v0-1.5-lg": {
+ max_tokens: 512000,
+ max_input_tokens: 512000,
+ max_output_tokens: 512000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ litellm_provider: "v0",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ output_vector_size: 1536,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "embedding",
+ },
+ "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ output_vector_size: 1024,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "embedding",
+ },
+ "bedrock/us-gov-east-1/amazon.titan-text-express-v1": {
+ max_tokens: 8000,
+ max_input_tokens: 42000,
+ max_output_tokens: 8000,
+ input_cost_per_token: 0.0000013,
+ output_cost_per_token: 0.0000017,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": {
+ max_tokens: 4000,
+ max_input_tokens: 42000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 42000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": {
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.0000036,
+ output_cost_per_token: 0.000018,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": {
+ max_tokens: 2048,
+ max_input_tokens: 8000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 0.00000265,
+ output_cost_per_token: 0.0000035,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_pdf_input: true,
+ },
+ "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": {
+ max_tokens: 2048,
+ max_input_tokens: 8000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.00000265,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_pdf_input: true,
+ },
+ "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ output_vector_size: 1536,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "embedding",
+ },
+ "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ output_vector_size: 1024,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "bedrock",
+ mode: "embedding",
+ },
+ "bedrock/us-gov-west-1/amazon.titan-text-express-v1": {
+ max_tokens: 8000,
+ max_input_tokens: 42000,
+ max_output_tokens: 8000,
+ input_cost_per_token: 0.0000013,
+ output_cost_per_token: 0.0000017,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": {
+ max_tokens: 4000,
+ max_input_tokens: 42000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 42000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ },
+ "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": {
+ max_tokens: 8192,
+ max_input_tokens: 200000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.0000036,
+ output_cost_per_token: 0.000018,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_tool_choice: true,
+ },
+ "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": {
+ max_tokens: 2048,
+ max_input_tokens: 8000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 0.00000265,
+ output_cost_per_token: 0.0000035,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_pdf_input: true,
+ },
+ "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": {
+ max_tokens: 2048,
+ max_input_tokens: 8000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.00000265,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_pdf_input: true,
+ },
+ "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 9.6e-7,
+ output_cost_per_token: 0.00000384,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": {
+ max_tokens: 10000,
+ max_input_tokens: 300000,
+ max_output_tokens: 10000,
+ input_cost_per_token: 9.6e-7,
+ output_cost_per_token: 0.00000384,
+ litellm_provider: "bedrock",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ },
+ "moonshot/kimi-latest": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/kimi-latest-8k": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/kimi-latest-32k": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/kimi-latest-128k": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ cache_read_input_token_cost: 1.5e-7,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/kimi-thinking-preview": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.00003,
+ output_cost_per_token: 0.00003,
+ litellm_provider: "moonshot",
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-8k-vision-preview": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-32k-vision-preview": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "moonshot/moonshot-v1-128k-vision-preview": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "moonshot",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_vision: true,
+ mode: "chat",
+ source: "https://platform.moonshot.ai/docs/pricing",
+ },
+ "groq/qwen/qwen3-32b": {
+ max_tokens: 131000,
+ max_input_tokens: 131000,
+ max_output_tokens: 131000,
+ input_cost_per_token: 2.9e-7,
+ output_cost_per_token: 5.9e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/qwen/qwen-vl-plus": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 2048,
+ input_cost_per_token: 2.1e-7,
+ output_cost_per_token: 6.3e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 16384,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.0000025,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://fireworks.ai/models/fireworks/kimi-k2-instruct",
+ },
+ "lambda_ai/deepseek-llama3.3-70b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "lambda_ai/deepseek-r1-0528": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "lambda_ai/deepseek-r1-671b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "lambda_ai/deepseek-v3-0324": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/hermes3-405b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/hermes3-70b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/hermes3-8b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 4e-8,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/lfm-40b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/lfm-7b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 4e-8,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama-4-scout-17b-16e-instruct": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.1-405b-instruct-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.1-70b-instruct-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.1-8b-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 4e-8,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.2-11b-vision-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.5e-8,
+ output_cost_per_token: 2.5e-8,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_vision: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.2-3b-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.5e-8,
+ output_cost_per_token: 2.5e-8,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/llama3.3-70b-instruct-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/qwen25-coder-32b-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "lambda_ai/qwen3-32b-fp8": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "lambda_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "recraft/recraftv3": {
+ mode: "image_generation",
+ output_cost_per_image: 0.04,
+ litellm_provider: "recraft",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://www.recraft.ai/docs#pricing",
+ },
+ "recraft/recraftv2": {
+ mode: "image_generation",
+ output_cost_per_image: 0.022,
+ litellm_provider: "recraft",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://www.recraft.ai/docs#pricing",
+ },
+ "morph/morph-v3-fast": {
+ max_tokens: 16000,
+ max_input_tokens: 16000,
+ max_output_tokens: 16000,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.0000012,
+ litellm_provider: "morph",
+ mode: "chat",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ },
+ "morph/morph-v3-large": {
+ max_tokens: 16000,
+ max_input_tokens: 16000,
+ max_output_tokens: 16000,
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 0.0000019,
+ litellm_provider: "morph",
+ mode: "chat",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_vision: false,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ },
+ "gemini/gemini-2.0-flash-live-001": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 3.5e-7,
+ input_cost_per_audio_token: 0.0000021,
+ input_cost_per_image: 0.0000021,
+ input_cost_per_video_per_second: 0.0000021,
+ output_cost_per_token: 0.0000015,
+ output_cost_per_audio_token: 0.0000085,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 10,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "audio"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001",
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.0-flash-live-preview-04-09": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_token: 5e-7,
+ input_cost_per_audio_token: 0.000003,
+ input_cost_per_image: 0.000003,
+ input_cost_per_video_per_second: 0.000003,
+ output_cost_per_token: 0.000002,
+ output_cost_per_audio_token: 0.000012,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ rpm: 10,
+ tpm: 250000,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_reasoning: true,
+ supports_response_schema: true,
+ supports_audio_output: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/chat/completions", "/v1/completions"],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "audio"],
+ source:
+ "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09",
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "vertex_ai/meta/llama-3.1-8b-instruct-maas": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_vision: true,
+ source:
+ "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
+ supports_tool_choice: true,
+ metadata: {
+ notes:
+ "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost.",
+ },
+ },
+ "vertex_ai/meta/llama-3.1-70b-instruct-maas": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 0,
+ output_cost_per_token: 0,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_vision: true,
+ source:
+ "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
+ supports_tool_choice: true,
+ },
+ "vertex_ai/meta/llama-3.1-405b-instruct-maas": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 2048,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000016,
+ litellm_provider: "vertex_ai-llama_models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_vision: true,
+ source:
+ "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
+ supports_tool_choice: true,
+ },
+ "hyperbolic/moonshotai/Kimi-K2-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/deepseek-ai/DeepSeek-R1-0528": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 2.5e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/Qwen/Qwen3-235B-A22B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/deepseek-ai/DeepSeek-V3-0324": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/Qwen/QwQ-32B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/deepseek-ai/DeepSeek-R1": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/deepseek-ai/DeepSeek-V3": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/Qwen/Qwen2.5-72B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "hyperbolic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "gemini/gemini-2.5-flash-lite": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 5e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ output_cost_per_reasoning_token: 4e-7,
+ litellm_provider: "gemini",
+ mode: "chat",
+ rpm: 15,
+ tpm: 250000,
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash-lite": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 5e-7,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ output_cost_per_reasoning_token: 4e-7,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_reasoning: true,
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 2.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gpt-4o-realtime-preview-2025-06-03": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "openrouter/bytedance/ui-tars-1.5-7b": {
+ max_tokens: 2048,
+ max_input_tokens: 131072,
+ max_output_tokens: 2048,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ source: "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b",
+ supports_tool_choice: true,
+ },
+ "openrouter/qwen/qwen3-coder": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
+ litellm_provider: "openrouter",
+ source: "https://openrouter.ai/qwen/qwen3-coder",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "openai/gpt-4o-realtime-preview-2025-06-03": {
+ max_tokens: 4096,
+ max_input_tokens: 128000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000005,
+ input_cost_per_audio_token: 0.00004,
+ cache_read_input_token_cost: 0.0000025,
+ output_cost_per_token: 0.00002,
+ output_cost_per_audio_token: 0.00008,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ },
+ "gemini/imagen-4.0-generate-preview-06-06": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-4.0-ultra-generate-preview-06-06": {
+ output_cost_per_image: 0.06,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-4.0-fast-generate-preview-06-06": {
+ output_cost_per_image: 0.02,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-3.0-generate-002": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-3.0-generate-001": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-3.0-fast-generate-001": {
+ output_cost_per_image: 0.02,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "openrouter/x-ai/grok-4": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://openrouter.ai/x-ai/grok-4",
+ supports_web_search: true,
+ },
+ "claude-opus-4-1-20250805": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "anthropic.claude-opus-4-1-20250805-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "us.anthropic.claude-opus-4-1-20250805-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "eu.anthropic.claude-opus-4-1-20250805-v1:0": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/glm-4p5": {
+ max_tokens: 96000,
+ max_input_tokens: 128000,
+ max_output_tokens: 96000,
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.00000219,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://fireworks.ai/models/fireworks/glm-4p5",
+ },
+ "fireworks_ai/accounts/fireworks/models/glm-4p5-air": {
+ max_tokens: 96000,
+ max_input_tokens: 128000,
+ max_output_tokens: 96000,
+ input_cost_per_token: 2.2e-7,
+ output_cost_per_token: 8.8e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://artificialanalysis.ai/models/glm-4-5-air",
+ },
+ "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://fireworks.ai/pricing",
+ },
+ "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ source: "https://fireworks.ai/pricing",
+ },
+ "vertex_ai/claude-opus-4-1": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ input_cost_per_token_batches: 0.0000075,
+ output_cost_per_token_batches: 0.0000375,
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ },
+ "vertex_ai/claude-opus-4-1@20250805": {
+ max_tokens: 4096,
+ max_input_tokens: 200000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ input_cost_per_token_batches: 0.0000075,
+ output_cost_per_token_batches: 0.0000375,
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "vertex_ai-anthropic_models",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ },
+ "openai.gpt-oss-20b-1:0": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "openai.gpt-oss-120b-1:0": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "bedrock_converse",
+ mode: "chat",
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "gpt-5": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-mini": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-nano": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-chat": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-chat-latest": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-mini-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "gpt-5-nano-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-mini": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-mini-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-nano-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-nano": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "azure/gpt-5-chat": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ source:
+ "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/",
+ },
+ "azure/gpt-5-chat-latest": {
+ max_tokens: 128000,
+ max_input_tokens: 272000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "azure",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "groq/openai/gpt-oss-20b": {
+ max_tokens: 32768,
+ max_input_tokens: 131072,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "groq/openai/gpt-oss-120b": {
+ max_tokens: 32766,
+ max_input_tokens: 131072,
+ max_output_tokens: 32766,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 7.5e-7,
+ litellm_provider: "groq",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_web_search: true,
+ },
+ "claude-opus-4-1": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ search_context_cost_per_query: {
+ search_context_size_low: 0.01,
+ search_context_size_medium: 0.01,
+ search_context_size_high: 0.01,
+ },
+ cache_creation_input_token_cost: 0.00001875,
+ cache_read_input_token_cost: 0.0000015,
+ litellm_provider: "anthropic",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_pdf_input: true,
+ supports_prompt_caching: true,
+ supports_response_schema: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": {
+ max_tokens: 512000,
+ max_input_tokens: 512000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/meta.llama-4-scout-17b-16e-instruct": {
+ max_tokens: 192000,
+ max_input_tokens: 192000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/meta.llama-3.3-70b-instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/meta.llama-3.2-90b-vision-instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/meta.llama-3.1-405b-instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 4000,
+ input_cost_per_token: 0.00001068,
+ output_cost_per_token: 0.00001068,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/xai.grok-4": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/xai.grok-3": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/xai.grok-3-mini": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/xai.grok-3-fast": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000025,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "oci/xai.grok-3-mini-fast": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "oci",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_response_schema: false,
+ source:
+ "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+ },
+ "openai/gpt-5": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-mini": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-nano": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-chat": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-chat-latest": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: false,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-mini-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "openai/gpt-5-nano-2025-08-07": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "openai",
+ mode: "chat",
+ supported_endpoints: ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_pdf_input: true,
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_vision: true,
+ supports_prompt_caching: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supports_native_streaming: true,
+ supports_reasoning: true,
+ },
+ "cerebras/openai/gpt-oss-20b": {
+ max_tokens: 32768,
+ max_input_tokens: 131072,
+ max_output_tokens: 32768,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "cerebras",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ source: "https://inference-docs.cerebras.ai/support/pricing",
+ },
+ "cerebras/openai/gpt-oss-120b": {
+ max_tokens: 32768,
+ max_input_tokens: 131072,
+ max_output_tokens: 32768,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 6.9e-7,
+ litellm_provider: "cerebras",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ source:
+ "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras",
+ },
+ "openrouter/openai/gpt-oss-20b": {
+ max_tokens: 32768,
+ max_input_tokens: 131072,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ source: "https://openrouter.ai/openai/gpt-oss-20b",
+ },
+ "openrouter/openai/gpt-oss-120b": {
+ max_tokens: 32768,
+ max_input_tokens: 131072,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_response_schema: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ source: "https://openrouter.ai/openai/gpt-oss-120b",
+ },
+ "gradient_ai/anthropic-claude-3.7-sonnet": {
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 1024,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/anthropic-claude-3.5-sonnet": {
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 1024,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/anthropic-claude-3.5-haiku": {
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 1024,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/anthropic-claude-3-opus": {
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 1024,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/deepseek-r1-distill-llama-70b": {
+ input_cost_per_token: 9.9e-7,
+ output_cost_per_token: 9.9e-7,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 8000,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/llama3.3-70b-instruct": {
+ input_cost_per_token: 6.5e-7,
+ output_cost_per_token: 6.5e-7,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 2048,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/llama3-8b-instruct": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 512,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/mistral-nemo-instruct-2407": {
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 512,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/openai-o3": {
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 100000,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/openai-o3-mini": {
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 100000,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/openai-gpt-4o": {
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 16384,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/openai-gpt-4o-mini": {
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 16384,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "gradient_ai/alibaba-qwen3-32b": {
+ litellm_provider: "gradient_ai",
+ mode: "chat",
+ max_tokens: 2048,
+ supported_endpoints: ["/v1/chat/completions"],
+ supported_modalities: ["text"],
+ supports_tool_choice: false,
+ },
+ "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": {
+ max_tokens: 8192,
+ max_input_tokens: 65336,
+ max_output_tokens: 8192,
+ input_cost_per_token: 0.00000135,
+ output_cost_per_token: 0.0000054,
+ litellm_provider: "vertex_ai-deepseek_models",
+ mode: "chat",
+ source:
+ "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_prompt_caching: true,
+ },
+ "azure_ai/FLUX-1.1-pro": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "azure_ai",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source:
+ "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659",
+ },
+ "azure_ai/FLUX.1-Kontext-pro": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "azure_ai",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source:
+ "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
+ },
+ "openrouter/deepseek/deepseek-chat-v3-0324": {
+ max_tokens: 8192,
+ max_input_tokens: 65536,
+ max_output_tokens: 8192,
+ input_cost_per_token: 1.4e-7,
+ output_cost_per_token: 2.8e-7,
+ litellm_provider: "openrouter",
+ supports_prompt_caching: true,
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": {
+ max_tokens: 32768,
+ max_input_tokens: 262144,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000004,
+ litellm_provider: "vertex_ai-qwen_models",
+ mode: "chat",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
+ max_tokens: 16384,
+ max_input_tokens: 262144,
+ max_output_tokens: 16384,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000001,
+ litellm_provider: "vertex_ai-qwen_models",
+ mode: "chat",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ },
+ "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.000006,
+ max_input_tokens: 262000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ supports_tool_choice: false,
+ source: "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8",
+ },
+ "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000002,
+ max_input_tokens: 256000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ supports_tool_choice: false,
+ source: "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct",
+ },
+ "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": {
+ input_cost_per_token: 6.5e-7,
+ output_cost_per_token: 0.000003,
+ max_input_tokens: 256000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ supports_tool_choice: false,
+ source: "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507",
+ },
+ "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ max_input_tokens: 40000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ supports_tool_choice: false,
+ source: "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput",
+ },
+ "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": {
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.00000219,
+ max_input_tokens: 128000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ supports_tool_choice: false,
+ source: "https://www.together.ai/models/deepseek-r1-0528-throughput",
+ },
+ "together_ai/openai/gpt-oss-120b": {
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ max_input_tokens: 128000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_tool_choice: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ source: "https://www.together.ai/models/gpt-oss-120b",
+ },
+ "together_ai/OpenAI/gpt-oss-20B": {
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 2e-7,
+ max_input_tokens: 128000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_tool_choice: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ source: "https://www.together.ai/models/gpt-oss-20b",
+ },
+ "together_ai/zai-org/GLM-4.5-Air-FP8": {
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000011,
+ max_input_tokens: 128000,
+ litellm_provider: "together_ai",
+ supports_function_calling: false,
+ supports_tool_choice: false,
+ supports_parallel_function_calling: false,
+ mode: "chat",
+ source: "https://www.together.ai/models/glm-4-5-air",
+ },
+ "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 9e-7,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/models/fireworks/deepseek-v3-0324",
+ supports_tool_choice: false,
+ },
+ "vertex_ai/imagen-4.0-generate-001": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "vertex_ai/imagen-4.0-ultra-generate-001": {
+ output_cost_per_image: 0.06,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "vertex_ai/imagen-4.0-fast-generate-001": {
+ output_cost_per_image: 0.02,
+ litellm_provider: "vertex_ai-image-models",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-4.0-generate-001": {
+ output_cost_per_image: 0.04,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-4.0-ultra-generate-001": {
+ output_cost_per_image: 0.06,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "gemini/imagen-4.0-fast-generate-001": {
+ output_cost_per_image: 0.02,
+ litellm_provider: "gemini",
+ mode: "image_generation",
+ source: "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+ },
+ "deepinfra/deepseek-ai/DeepSeek-V3": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 3.8e-7,
+ output_cost_per_token: 8.9e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.5e-8,
+ output_cost_per_token: 2e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemma-2-9b-it": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3e-8,
+ output_cost_per_token: 6e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/Qwen/Qwen2-7B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/QVQ-72B-Preview": {
+ max_tokens: 32000,
+ max_input_tokens: 32000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-3.3-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.3e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/microsoft/Phi-4-multimodal-instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/mistralai/Devstral-Small-2507": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 2.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/microsoft/WizardLM-2-7B": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-V3-0324": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 2.8e-7,
+ output_cost_per_token: 8.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/anthropic/claude-3-7-sonnet-latest": {
+ max_tokens: 200000,
+ max_input_tokens: 200000,
+ max_output_tokens: 200000,
+ input_cost_per_token: 0.0000033,
+ output_cost_per_token: 0.0000165,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/cognitivecomputations/dolphin-2.9.1-llama-3-70b": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen3-235B-A22B": {
+ max_tokens: 40960,
+ max_input_tokens: 40960,
+ max_output_tokens: 40960,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-V3-0324-Turbo": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/microsoft/WizardLM-2-8x22B": {
+ max_tokens: 65536,
+ max_input_tokens: 65536,
+ max_output_tokens: 65536,
+ input_cost_per_token: 4.8e-7,
+ output_cost_per_token: 4.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-Guard-4-12B": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 1.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-3.2-1B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-9,
+ output_cost_per_token: 1e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemma-2-27b-it": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 2.7e-7,
+ output_cost_per_token: 2.7e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/mistralai/Mixtral-8x22B-Instruct-v0.1": {
+ max_tokens: 65536,
+ max_input_tokens: 65536,
+ max_output_tokens: 65536,
+ input_cost_per_token: 6.5e-7,
+ output_cost_per_token: 6.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen2.5-7B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 4e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/google/gemini-1.5-flash-8b": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 3.75e-8,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 2.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ supports_reasoning: true,
+ },
+ "deepinfra/meta-llama/Llama-Guard-3-8B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 8e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/anthropic/claude-4-opus": {
+ max_tokens: 200000,
+ max_input_tokens: 200000,
+ max_output_tokens: 200000,
+ input_cost_per_token: 0.0000165,
+ output_cost_per_token: 0.0000825,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/openchat/openchat-3.6-8b": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/google/gemma-3-27b-it": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 9e-8,
+ output_cost_per_token: 1.7e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Austism/chronos-hermes-13b-v2": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 1.3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6.5e-7,
+ output_cost_per_token: 7.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/QwQ-32B-Preview": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 1.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/anthropic/claude-4-sonnet": {
+ max_tokens: 200000,
+ max_input_tokens: 200000,
+ max_output_tokens: 200000,
+ input_cost_per_token: 0.0000033,
+ output_cost_per_token: 0.0000165,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/microsoft/Phi-3-medium-4k-instruct": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.4e-7,
+ output_cost_per_token: 1.4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/mattshumer/Reflection-Llama-3.1-70B": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 6.5e-7,
+ output_cost_per_token: 7.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2.3e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-V3.1": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.000001,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ supports_reasoning: true,
+ },
+ "deepinfra/Qwen/Qwen2.5-Coder-7B": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-Prover-V2-671B": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.00000218,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ supports_reasoning: true,
+ },
+ "deepinfra/zai-org/GLM-4.5": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Llama-3.2-3B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1.2e-8,
+ output_cost_per_token: 2.4e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemini-1.5-flash": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/KoboldAI/LLaMA2-13B-Tiefighter": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemini-2.5-pro": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 8.75e-7,
+ output_cost_per_token: 0.000007,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen3-30B-A3B": {
+ max_tokens: 40960,
+ max_input_tokens: 40960,
+ max_output_tokens: 40960,
+ input_cost_per_token: 8e-8,
+ output_cost_per_token: 2.9e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/QwQ-32B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/moonshotai/Kimi-K2-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.000002,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Sao10K/L3-70B-Euryale-v2.1": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 7e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/microsoft/phi-4-reasoning-plus": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 3.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/google/gemma-3-12b-it": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemini-2.5-flash": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 2.1e-7,
+ output_cost_per_token: 0.00000175,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 4.5e-7,
+ output_cost_per_token: 0.00000215,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/mistralai/Mistral-7B-Instruct-v0.3": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 2.8e-8,
+ output_cost_per_token: 5.4e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen2.5-72B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 3.9e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen3-14B": {
+ max_tokens: 40960,
+ max_input_tokens: 40960,
+ max_output_tokens: 40960,
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 2.4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/allenai/olmOCR-7B-0725-FP8": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 2.7e-7,
+ output_cost_per_token: 0.0000015,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
+ max_tokens: 262144,
+ max_input_tokens: 262144,
+ max_output_tokens: 262144,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/microsoft/phi-4": {
+ max_tokens: 16384,
+ max_input_tokens: 16384,
+ max_output_tokens: 16384,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 1.4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 7e-7,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/zai-org/GLM-4.5-Air": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000011,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/openai/gpt-oss-120b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 9e-8,
+ output_cost_per_token: 4.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/codegemma-7b-it": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 7e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": {
+ max_tokens: 262144,
+ max_input_tokens: 262144,
+ max_output_tokens: 262144,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000012,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 4e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/openbmb/MiniCPM-Llama3-V-2_5": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3.4e-7,
+ output_cost_per_token: 3.4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/bigcode/starcoder2-15b-instruct-v0.1": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 1.5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
+ max_tokens: 1048576,
+ max_input_tokens: 1048576,
+ max_output_tokens: 1048576,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
+ max_tokens: 327680,
+ max_input_tokens: 327680,
+ max_output_tokens: 327680,
+ input_cost_per_token: 8e-8,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/google/gemini-2.0-flash-001": {
+ max_tokens: 1000000,
+ max_input_tokens: 1000000,
+ max_output_tokens: 1000000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Gryphe/MythoMax-L2-13b-turbo": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 1.3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/google/gemma-1.1-7b-it": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 7e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 2.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3e-8,
+ output_cost_per_token: 5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen3-32B": {
+ max_tokens: 40960,
+ max_input_tokens: 40960,
+ max_output_tokens: 40960,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": {
+ max_tokens: 262144,
+ max_input_tokens: 262144,
+ max_output_tokens: 262144,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/nvidia/Nemotron-4-340B-Instruct": {
+ max_tokens: 4096,
+ max_input_tokens: 4096,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.0000042,
+ output_cost_per_token: 0.0000042,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1-0528": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.00000215,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": {
+ max_tokens: 163840,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000003,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "deepinfra/NovaSky-AI/Sky-T1-32B-Preview": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 1.8e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": {
+ max_tokens: 262144,
+ max_input_tokens: 262144,
+ max_output_tokens: 262144,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/mistralai/Mistral-Small-3.1-24B-Instruct-2503": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 1e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Qwen/Qwen2-72B-Instruct": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 3.5e-7,
+ output_cost_per_token: 4e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 5e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/Sao10K/L3-8B-Lunaris-v1": {
+ max_tokens: 8192,
+ max_input_tokens: 8192,
+ max_output_tokens: 8192,
+ input_cost_per_token: 3e-8,
+ output_cost_per_token: 6e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/google/gemma-3-4b-it": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 4e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/mistralai/Mistral-7B-Instruct-v0.2": {
+ max_tokens: 32768,
+ max_input_tokens: 32768,
+ max_output_tokens: 32768,
+ input_cost_per_token: 5.5e-8,
+ output_cost_per_token: 5.5e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 3.8e-8,
+ output_cost_per_token: 1.2e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/mistralai/Devstral-Small-2505": {
+ max_tokens: 128000,
+ max_input_tokens: 128000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 1.2e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 4.9e-8,
+ output_cost_per_token: 4.9e-8,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: false,
+ },
+ "deepinfra/openai/gpt-oss-20b": {
+ max_tokens: 131072,
+ max_input_tokens: 131072,
+ max_output_tokens: 131072,
+ input_cost_per_token: 4e-8,
+ output_cost_per_token: 1.6e-7,
+ litellm_provider: "deepinfra",
+ mode: "chat",
+ supports_tool_choice: true,
+ },
+ "voyage/voyage-context-3": {
+ max_tokens: 120000,
+ max_input_tokens: 120000,
+ input_cost_per_token: 1.8e-7,
+ output_cost_per_token: 0,
+ litellm_provider: "voyage",
+ mode: "embedding",
+ },
+ "openrouter/deepseek/deepseek-chat-v3.1": {
+ max_tokens: 8192,
+ max_input_tokens: 163840,
+ max_output_tokens: 163840,
+ input_cost_per_token: 2e-7,
+ input_cost_per_token_cache_hit: 2e-8,
+ output_cost_per_token: 8e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_assistant_prefill: true,
+ supports_reasoning: true,
+ supports_tool_choice: true,
+ supports_prompt_caching: true,
+ },
+ "aiml/flux/kontext-pro/text-to-image": {
+ output_cost_per_image: 0.042,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes:
+ "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed",
+ },
+ },
+ "aiml/flux/kontext-max/text-to-image": {
+ output_cost_per_image: 0.084,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes:
+ "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed",
+ },
+ },
+ "aiml/flux-pro/v1.1-ultra": {
+ output_cost_per_image: 0.063,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "aiml/flux-pro/v1.1": {
+ output_cost_per_image: 0.042,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ },
+ "aiml/flux-realism": {
+ output_cost_per_image: 0.037,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "Flux Pro - Professional-grade image generation model",
+ },
+ },
+ "aiml/flux/schnell": {
+ output_cost_per_image: 0.003,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "Flux Schnell - Fast generation model optimized for speed",
+ },
+ },
+ "aiml/flux/dev": {
+ output_cost_per_image: 0.026,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "Flux Dev - Development version optimized for experimentation",
+ },
+ },
+ "aiml/flux-pro": {
+ output_cost_per_image: 0.053,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "Flux Dev - Development version optimized for experimentation",
+ },
+ },
+ "aiml/dall-e-3": {
+ output_cost_per_image: 0.042,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "DALL-E 3 via AI/ML API - High-quality text-to-image generation",
+ },
+ },
+ "aiml/dall-e-2": {
+ output_cost_per_image: 0.021,
+ litellm_provider: "aiml",
+ mode: "image_generation",
+ supported_endpoints: ["/v1/images/generations"],
+ source: "https://docs.aimlapi.com/",
+ metadata: {
+ notes: "DALL-E 2 via AI/ML API - Reliable text-to-image generation",
+ },
+ },
+ "gemini/gemini-2.5-flash-image-preview": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ output_cost_per_image: 0.039,
+ litellm_provider: "gemini",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ tpm: 8000000,
+ rpm: 100000,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "gemini-2.5-flash-image-preview": {
+ max_tokens: 65535,
+ max_input_tokens: 1048576,
+ max_output_tokens: 65535,
+ max_images_per_prompt: 3000,
+ max_videos_per_prompt: 10,
+ max_video_length: 1,
+ max_audio_length_hours: 8.4,
+ max_audio_per_prompt: 1,
+ max_pdf_size_mb: 30,
+ input_cost_per_audio_token: 0.000001,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ output_cost_per_reasoning_token: 0.0000025,
+ output_cost_per_image: 0.039,
+ litellm_provider: "vertex_ai-language-models",
+ mode: "chat",
+ supports_system_messages: true,
+ supports_function_calling: true,
+ supports_vision: true,
+ supports_response_schema: true,
+ supports_audio_output: false,
+ supports_tool_choice: true,
+ supported_endpoints: [
+ "/v1/chat/completions",
+ "/v1/completions",
+ "/v1/batch",
+ ],
+ supported_modalities: ["text", "image", "audio", "video"],
+ supported_output_modalities: ["text", "image"],
+ source:
+ "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+ supports_parallel_function_calling: true,
+ supports_web_search: true,
+ supports_url_context: true,
+ tpm: 8000000,
+ rpm: 100000,
+ supports_pdf_input: true,
+ cache_read_input_token_cost: 7.5e-8,
+ supports_prompt_caching: true,
+ },
+ "openrouter/anthropic/claude-opus-4": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ input_cost_per_image: 0.0048,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "openrouter/anthropic/claude-opus-4.1": {
+ max_tokens: 32000,
+ max_input_tokens: 200000,
+ max_output_tokens: 32000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ input_cost_per_image: 0.0048,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_vision: true,
+ tool_use_system_prompt_tokens: 159,
+ supports_assistant_prefill: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ supports_computer_use: true,
+ },
+ "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": {
+ max_tokens: 8192,
+ max_input_tokens: 128000,
+ max_output_tokens: 8192,
+ input_cost_per_token: 5.6e-7,
+ output_cost_per_token: 0.00000168,
+ litellm_provider: "fireworks_ai",
+ mode: "chat",
+ supports_response_schema: true,
+ source: "https://fireworks.ai/pricing",
+ supports_tool_choice: true,
+ },
+ "openrouter/openai/gpt-5-mini": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000002,
+ cache_read_input_token_cost: 2.5e-8,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "openrouter/openai/gpt-5-nano": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 4e-7,
+ cache_read_input_token_cost: 5e-9,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "openrouter/openai/gpt-5-chat": {
+ max_tokens: 128000,
+ max_input_tokens: 400000,
+ max_output_tokens: 128000,
+ input_cost_per_token: 0.00000125,
+ output_cost_per_token: 0.00001,
+ cache_read_input_token_cost: 1.25e-7,
+ litellm_provider: "openrouter",
+ mode: "chat",
+ supported_modalities: ["text", "image"],
+ supported_output_modalities: ["text"],
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ },
+ "xai/grok-code-fast-1": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000015,
+ cache_read_input_token_cost: 2e-8,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ },
+ "xai/grok-code-fast": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000015,
+ cache_read_input_token_cost: 2e-8,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ },
+ "xai/grok-code-fast-1-0825": {
+ max_tokens: 256000,
+ max_input_tokens: 256000,
+ max_output_tokens: 256000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000015,
+ cache_read_input_token_cost: 2e-8,
+ litellm_provider: "xai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_tool_choice: true,
+ supports_reasoning: true,
+ source: "https://docs.x.ai/docs/models",
+ },
+ "gpt-realtime": {
+ max_tokens: 4096,
+ max_input_tokens: 32000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000004,
+ cache_read_input_token_cost: 4e-7,
+ output_cost_per_token: 0.000016,
+ input_cost_per_audio_token: 0.000032,
+ output_cost_per_audio_token: 0.000064,
+ cache_creation_input_audio_token_cost: 4e-7,
+ input_cost_per_image: 0.000005,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/realtime"],
+ supported_modalities: ["text", "image", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ },
+ "gpt-realtime-2025-08-28": {
+ max_tokens: 4096,
+ max_input_tokens: 32000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000004,
+ cache_read_input_token_cost: 4e-7,
+ output_cost_per_token: 0.000016,
+ input_cost_per_audio_token: 0.000032,
+ output_cost_per_audio_token: 0.000064,
+ cache_creation_input_audio_token_cost: 4e-7,
+ input_cost_per_image: 0.000005,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/realtime"],
+ supported_modalities: ["text", "image", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ },
+ "vercel_ai_gateway/alibaba/qwen3-coder": {
+ max_tokens: 262144,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ max_output_tokens: 66536,
+ max_input_tokens: 262144,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/codestral-embed": {
+ max_tokens: 0,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/gemini-2.5-pro": {
+ max_tokens: 1048576,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 65536,
+ max_input_tokens: 1048576,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/deepseek/deepseek-v3": {
+ max_tokens: 128000,
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 9e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/amazon/nova-lite": {
+ max_tokens: 300000,
+ input_cost_per_token: 6e-8,
+ output_cost_per_token: 2.4e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 300000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-4-scout": {
+ max_tokens: 131072,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.2-1b": {
+ max_tokens: 128000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 1e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/mistral-small": {
+ max_tokens: 32000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ max_output_tokens: 4000,
+ max_input_tokens: 32000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/gemini-2.5-flash": {
+ max_tokens: 1000000,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 0.0000025,
+ max_output_tokens: 65536,
+ max_input_tokens: 1000000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/inception/mercury-coder-small": {
+ max_tokens: 32000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.000001,
+ max_output_tokens: 16384,
+ max_input_tokens: 32000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/text-embedding-3-small": {
+ max_tokens: 0,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/xai/grok-2-vision": {
+ max_tokens: 32768,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 32768,
+ max_input_tokens: 32768,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/xai/grok-2": {
+ max_tokens: 131072,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 4000,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": {
+ max_tokens: 131072,
+ input_cost_per_token: 7.5e-7,
+ output_cost_per_token: 9.9e-7,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.1-70b": {
+ max_tokens: 128000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/xai/grok-3": {
+ max_tokens: 131072,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/alibaba/qwen-3-235b": {
+ max_tokens: 40960,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ max_output_tokens: 16384,
+ max_input_tokens: 40960,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/xai/grok-3-fast": {
+ max_tokens: 131072,
+ input_cost_per_token: 0.000005,
+ output_cost_per_token: 0.000025,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/vercel/v0-1.5-md": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 32768,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/o4-mini": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ max_output_tokens: 100000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 2.75e-7,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/magistral-medium": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000005,
+ max_output_tokens: 64000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/amazon/titan-embed-text-v2": {
+ max_tokens: 0,
+ input_cost_per_token: 2e-8,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/alibaba/qwen-3-30b": {
+ max_tokens: 40960,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ max_output_tokens: 16384,
+ max_input_tokens: 40960,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/zai/glm-4.5-air": {
+ max_tokens: 128000,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 0.0000011,
+ max_output_tokens: 96000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4-turbo": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.00001,
+ output_cost_per_token: 0.00003,
+ max_output_tokens: 4096,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/mistral-large": {
+ max_tokens: 32000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
+ max_output_tokens: 4000,
+ max_input_tokens: 32000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/perplexity/sonar-pro": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 8000,
+ max_input_tokens: 200000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.2-90b": {
+ max_tokens: 128000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3-8b": {
+ max_tokens: 8192,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 8e-8,
+ max_output_tokens: 8192,
+ max_input_tokens: 8192,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/text-embedding-005": {
+ max_tokens: 0,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/mistral/pixtral-large": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000006,
+ max_output_tokens: 4000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-3.5-sonnet": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 8192,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_token_cost: 0.00000375,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/amazon/nova-micro": {
+ max_tokens: 128000,
+ input_cost_per_token: 3.5e-8,
+ output_cost_per_token: 1.4e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/cohere/command-r": {
+ max_tokens: 128000,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ max_output_tokens: 4096,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/morph/morph-v3-large": {
+ max_tokens: 32768,
+ input_cost_per_token: 9e-7,
+ output_cost_per_token: 0.0000019,
+ max_output_tokens: 16384,
+ max_input_tokens: 32768,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": {
+ max_tokens: 65536,
+ input_cost_per_token: 0.0000012,
+ output_cost_per_token: 0.0000012,
+ max_output_tokens: 2048,
+ max_input_tokens: 65536,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/xai/grok-4": {
+ max_tokens: 256000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 256000,
+ max_input_tokens: 256000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.1-8b": {
+ max_tokens: 131000,
+ input_cost_per_token: 5e-8,
+ output_cost_per_token: 8e-8,
+ max_output_tokens: 131072,
+ max_input_tokens: 131000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-3-opus": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ max_output_tokens: 4096,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 0.0000015,
+ cache_creation_input_token_cost: 0.00001875,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/zai/glm-4.5": {
+ max_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.0000022,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4o": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 16384,
+ max_input_tokens: 128000,
+ cache_read_input_token_cost: 0.00000125,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/o3-mini": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.0000011,
+ output_cost_per_token: 0.0000044,
+ max_output_tokens: 100000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 5.5e-7,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/ministral-8b": {
+ max_tokens: 128000,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 1e-7,
+ max_output_tokens: 4000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/o3": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ max_output_tokens: 100000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 5e-7,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/vercel/v0-1.0-md": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 32000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/text-multilingual-embedding-002": {
+ max_tokens: 0,
+ input_cost_per_token: 2.5e-8,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/amazon/nova-pro": {
+ max_tokens: 300000,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.0000032,
+ max_output_tokens: 8192,
+ max_input_tokens: 300000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/morph/morph-v3-fast": {
+ max_tokens: 32768,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.0000012,
+ max_output_tokens: 16384,
+ max_input_tokens: 32768,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-3.5-turbo": {
+ max_tokens: 16385,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ max_output_tokens: 4096,
+ max_input_tokens: 16385,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/codestral": {
+ max_tokens: 256000,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 9e-7,
+ max_output_tokens: 4000,
+ max_input_tokens: 256000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.2-11b": {
+ max_tokens: 128000,
+ input_cost_per_token: 1.6e-7,
+ output_cost_per_token: 1.6e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3-70b": {
+ max_tokens: 8192,
+ input_cost_per_token: 5.9e-7,
+ output_cost_per_token: 7.9e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 8192,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/xai/grok-3-mini-fast": {
+ max_tokens: 131072,
+ input_cost_per_token: 6e-7,
+ output_cost_per_token: 0.000004,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/text-embedding-3-large": {
+ max_tokens: 0,
+ input_cost_per_token: 1.3e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/google/gemini-2.0-flash-lite": {
+ max_tokens: 1048576,
+ input_cost_per_token: 7.5e-8,
+ output_cost_per_token: 3e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 1048576,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/ministral-3b": {
+ max_tokens: 128000,
+ input_cost_per_token: 4e-8,
+ output_cost_per_token: 4e-8,
+ max_output_tokens: 4000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/perplexity/sonar-reasoning-pro": {
+ max_tokens: 127000,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ max_output_tokens: 8000,
+ max_input_tokens: 127000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/gemini-embedding-001": {
+ max_tokens: 0,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/anthropic/claude-3-haiku": {
+ max_tokens: 200000,
+ input_cost_per_token: 2.5e-7,
+ output_cost_per_token: 0.00000125,
+ max_output_tokens: 4096,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 3e-8,
+ cache_creation_input_token_cost: 3e-7,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/o1": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.00006,
+ max_output_tokens: 100000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 0.0000075,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/deepseek/deepseek-r1": {
+ max_tokens: 128000,
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.00000219,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/mistral-embed": {
+ max_tokens: 0,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4.1-mini": {
+ max_tokens: 1047576,
+ input_cost_per_token: 4e-7,
+ output_cost_per_token: 0.0000016,
+ max_output_tokens: 32768,
+ max_input_tokens: 1047576,
+ cache_read_input_token_cost: 1e-7,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4o-mini": {
+ max_tokens: 128000,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ max_output_tokens: 16384,
+ max_input_tokens: 128000,
+ cache_read_input_token_cost: 7.5e-8,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/alibaba/qwen-3-14b": {
+ max_tokens: 40960,
+ input_cost_per_token: 8e-8,
+ output_cost_per_token: 2.4e-7,
+ max_output_tokens: 16384,
+ max_input_tokens: 40960,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-4-opus": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000015,
+ output_cost_per_token: 0.000075,
+ max_output_tokens: 32000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 0.0000015,
+ cache_creation_input_token_cost: 0.00001875,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/mistral-saba-24b": {
+ max_tokens: 32768,
+ input_cost_per_token: 7.9e-7,
+ output_cost_per_token: 7.9e-7,
+ max_output_tokens: 32768,
+ max_input_tokens: 32768,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/perplexity/sonar-reasoning": {
+ max_tokens: 127000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000005,
+ max_output_tokens: 8000,
+ max_input_tokens: 127000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-3.5-haiku": {
+ max_tokens: 200000,
+ input_cost_per_token: 8e-7,
+ output_cost_per_token: 0.000004,
+ max_output_tokens: 8192,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 8e-8,
+ cache_creation_input_token_cost: 0.000001,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/cohere/command-a": {
+ max_tokens: 256000,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 8000,
+ max_input_tokens: 256000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/gemma-2-9b": {
+ max_tokens: 8192,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 2e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 8192,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.2-3b": {
+ max_tokens: 128000,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 1.5e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4.1-nano": {
+ max_tokens: 1047576,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 4e-7,
+ max_output_tokens: 32768,
+ max_input_tokens: 1047576,
+ cache_read_input_token_cost: 2.5e-8,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-4-sonnet": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 64000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_token_cost: 0.00000375,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/perplexity/sonar": {
+ max_tokens: 127000,
+ input_cost_per_token: 0.000001,
+ output_cost_per_token: 0.000001,
+ max_output_tokens: 8000,
+ max_input_tokens: 127000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-4-maverick": {
+ max_tokens: 131072,
+ input_cost_per_token: 2e-7,
+ output_cost_per_token: 6e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/text-embedding-ada-002": {
+ max_tokens: 0,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "embedding",
+ },
+ "vercel_ai_gateway/xai/grok-3-mini": {
+ max_tokens: 131072,
+ input_cost_per_token: 3e-7,
+ output_cost_per_token: 5e-7,
+ max_output_tokens: 131072,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/cohere/embed-v4.0": {
+ max_tokens: 0,
+ input_cost_per_token: 1.2e-7,
+ output_cost_per_token: 0,
+ max_output_tokens: 0,
+ max_input_tokens: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/meta/llama-3.3-70b": {
+ max_tokens: 128000,
+ input_cost_per_token: 7.2e-7,
+ output_cost_per_token: 7.2e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/cohere/command-r-plus": {
+ max_tokens: 128000,
+ input_cost_per_token: 0.0000025,
+ output_cost_per_token: 0.00001,
+ max_output_tokens: 4096,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": {
+ max_tokens: 8192,
+ input_cost_per_token: 0.0000015,
+ output_cost_per_token: 0.000002,
+ max_output_tokens: 4096,
+ max_input_tokens: 8192,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/devstral-small": {
+ max_tokens: 128000,
+ input_cost_per_token: 7e-8,
+ output_cost_per_token: 2.8e-7,
+ max_output_tokens: 128000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/anthropic/claude-3.7-sonnet": {
+ max_tokens: 200000,
+ input_cost_per_token: 0.000003,
+ output_cost_per_token: 0.000015,
+ max_output_tokens: 64000,
+ max_input_tokens: 200000,
+ cache_read_input_token_cost: 3e-7,
+ cache_creation_input_token_cost: 0.00000375,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/google/gemini-2.0-flash": {
+ max_tokens: 1048576,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 6e-7,
+ max_output_tokens: 8192,
+ max_input_tokens: 1048576,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/pixtral-12b": {
+ max_tokens: 128000,
+ input_cost_per_token: 1.5e-7,
+ output_cost_per_token: 1.5e-7,
+ max_output_tokens: 4000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/mistral/magistral-small": {
+ max_tokens: 128000,
+ input_cost_per_token: 5e-7,
+ output_cost_per_token: 0.0000015,
+ max_output_tokens: 64000,
+ max_input_tokens: 128000,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/moonshotai/kimi-k2": {
+ max_tokens: 131072,
+ input_cost_per_token: 5.5e-7,
+ output_cost_per_token: 0.0000022,
+ max_output_tokens: 16384,
+ max_input_tokens: 131072,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/alibaba/qwen-3-32b": {
+ max_tokens: 40960,
+ input_cost_per_token: 1e-7,
+ output_cost_per_token: 3e-7,
+ max_output_tokens: 16384,
+ max_input_tokens: 40960,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "vercel_ai_gateway/openai/gpt-4.1": {
+ max_tokens: 1047576,
+ input_cost_per_token: 0.000002,
+ output_cost_per_token: 0.000008,
+ max_output_tokens: 32768,
+ max_input_tokens: 1047576,
+ cache_read_input_token_cost: 5e-7,
+ cache_creation_input_token_cost: 0,
+ litellm_provider: "vercel_ai_gateway",
+ mode: "chat",
+ },
+ "openai/gpt-realtime": {
+ max_tokens: 4096,
+ max_input_tokens: 32000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000004,
+ cache_read_input_token_cost: 4e-7,
+ output_cost_per_token: 0.000016,
+ input_cost_per_audio_token: 0.000032,
+ output_cost_per_audio_token: 0.000064,
+ cache_creation_input_audio_token_cost: 4e-7,
+ input_cost_per_image: 0.000005,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/realtime"],
+ supported_modalities: ["text", "image", "audio"],
+ supported_output_modalities: ["text", "audio"],
+ },
+ "openai/gpt-realtime-2025-08-28": {
+ max_tokens: 4096,
+ max_input_tokens: 32000,
+ max_output_tokens: 4096,
+ input_cost_per_token: 0.000004,
+ cache_read_input_token_cost: 4e-7,
+ output_cost_per_token: 0.000016,
+ input_cost_per_audio_token: 0.000032,
+ output_cost_per_audio_token: 0.000064,
+ cache_creation_input_audio_token_cost: 4e-7,
+ input_cost_per_image: 0.000005,
+ litellm_provider: "openai",
+ mode: "chat",
+ supports_function_calling: true,
+ supports_parallel_function_calling: true,
+ supports_audio_input: true,
+ supports_audio_output: true,
+ supports_system_messages: true,
+ supports_tool_choice: true,
+ supported_endpoints: ["/v1/realtime"],
+ supported_modalities: ["text", "image", "audio"],
+ supported_output_modalities: ["text", "audio"],
},
};
diff --git a/apps/api/src/scraper/scrapeURL/transformers/llmExtract.ts b/apps/api/src/scraper/scrapeURL/transformers/llmExtract.ts
index 9a559c6d1..6ec308354 100644
--- a/apps/api/src/scraper/scrapeURL/transformers/llmExtract.ts
+++ b/apps/api/src/scraper/scrapeURL/transformers/llmExtract.ts
@@ -190,6 +190,12 @@ export function calculateCost(
"gpt-4o-mini": { input_cost: 0.15, output_cost: 0.6 },
"openai/gpt-4o-mini": { input_cost: 0.15, output_cost: 0.6 },
"openai/gpt-4o": { input_cost: 2.5, output_cost: 10 },
+ "gpt-5": { input_cost: 1.25, output_cost: 10 },
+ "openai/gpt-5": { input_cost: 1.25, output_cost: 10 },
+ "gpt-5-mini": { input_cost: 0.25, output_cost: 2 },
+ "openai/gpt-5-mini": { input_cost: 0.25, output_cost: 2 },
+ "gpt-5-nano": { input_cost: 0.05, output_cost: 0.4 },
+ "openai/gpt-5-nano": { input_cost: 0.05, output_cost: 0.4 },
"google/gemini-2.0-flash-001": { input_cost: 0.15, output_cost: 0.6 },
"gemini-2.0-flash": { input_cost: 0.15, output_cost: 0.6 },
"deepseek/deepseek-r1": { input_cost: 0.55, output_cost: 2.19 },
@@ -693,6 +699,11 @@ export async function generateCompletions({
: {}),
},
},
+ ...(currentModel.modelId.startsWith("gpt-5")
+ ? {
+ temperature: 1,
+ }
+ : {}),
} satisfies Parameters<typeof generateObject>[0];
// const now = new Date().getTime();
@@ -1070,8 +1081,8 @@ export async function performSummary(
},
markdown: document.markdown,
previousWarning: document.warning,
- model: getModel("gpt-4o-mini", "openai"),
- retryModel: getModel("gpt-4o", "openai"),
+ model: getModel("gpt-5-mini", "openai"),
+ retryModel: getModel("gpt-4o-mini", "openai"),
costTrackingOptions: {
costTracking: meta.costTracking,
metadata: {
@@ -1084,6 +1095,11 @@ export async function performSummary(
functionId: "performSummary",
scrapeId: meta.id,
},
+ providerOptions: {
+ openai: {
+ reasoning: { effort: "minimal" },
+ },
+ } as any,
};
const { extract, warning, totalUsage, model } =