Skip to content

The agent engineering platform.

release(model-profiles): 0.0.4 (#33917)

ccurme4f3729c00497
diff --git a/libs/model-profiles/langchain_model_profiles/data/models.json b/libs/model-profiles/langchain_model_profiles/data/models.json
index 3fed45989a..1043b6b7e2 100644
--- a/libs/model-profiles/langchain_model_profiles/data/models.json
+++ b/libs/model-profiles/langchain_model_profiles/data/models.json
@@ -2333,6 +2333,11 @@
},
"gpt-5-codex": {
"attachment": false,
+ "cost": {
+ "cache_read": 0.13,
+ "input": 1.25,
+ "output": 10
+ },
"id": "gpt-5-codex",
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
@@ -2605,13 +2610,13 @@
],
"id": "baseten",
"models": {
- "Qwen3/Qwen3-Coder-480B-A35B-Instruct": {
+ "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"attachment": false,
"cost": {
"input": 0.38,
"output": 1.53
},
- "id": "Qwen3/Qwen3-Coder-480B-A35B-Instruct",
+ "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
"knowledge": "2025-04",
"last_updated": "2025-07-23",
"limit": {
@@ -3366,6 +3371,10 @@
},
"llama-2-7b-chat-int8": {
"attachment": false,
+ "cost": {
+ "input": 0.556,
+ "output": 6.667
+ },
"id": "llama-2-7b-chat-int8",
"last_updated": "2023-09-25",
"limit": {
@@ -3443,6 +3452,10 @@
},
"llama-3.1-70b-instruct": {
"attachment": false,
+ "cost": {
+ "input": 0.293,
+ "output": 2.253
+ },
"id": "llama-3.1-70b-instruct",
"last_updated": "2024-12-15",
"limit": {
@@ -3520,6 +3533,10 @@
},
"llama-3.1-8b-instruct-fast": {
"attachment": false,
+ "cost": {
+ "input": 0.045,
+ "output": 0.384
+ },
"id": "llama-3.1-8b-instruct-fast",
"last_updated": "2024-09-25",
"limit": {
@@ -4799,6 +4816,60 @@
"temperature": true,
"tool_call": true
},
+ "openai/gpt-oss-120b": {
+ "attachment": false,
+ "cost": {
+ "input": 0.05,
+ "output": 0.24
+ },
+ "id": "openai/gpt-oss-120b",
+ "last_updated": "2025-08-05",
+ "limit": {
+ "context": 131072,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "GPT OSS 120B",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-08-05",
+ "temperature": true,
+ "tool_call": true
+ },
+ "openai/gpt-oss-20b": {
+ "attachment": false,
+ "cost": {
+ "input": 0.03,
+ "output": 0.14
+ },
+ "id": "openai/gpt-oss-20b",
+ "last_updated": "2025-08-05",
+ "limit": {
+ "context": 131072,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "GPT OSS 20B",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-08-05",
+ "temperature": true,
+ "tool_call": true
+ },
"zai-org/GLM-4.5": {
"attachment": false,
"cost": {
@@ -5131,6 +5202,34 @@
"temperature": true,
"tool_call": true
},
+ "accounts/fireworks/models/minimax-m2": {
+ "attachment": false,
+ "cost": {
+ "input": 0.3,
+ "output": 1.2
+ },
+ "id": "accounts/fireworks/models/minimax-m2",
+ "knowledge": "2024-11",
+ "last_updated": "2025-10-27",
+ "limit": {
+ "context": 128000,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "MiniMax-M2",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-10-27",
+ "temperature": true,
+ "tool_call": true
+ },
"accounts/fireworks/models/qwen3-235b-a22b": {
"attachment": false,
"cost": {
@@ -8278,8 +8377,8 @@
"npm": "@ai-sdk/mistral"
},
"nebius": {
- "api": "https://api.studio.nebius.com/v1/",
- "doc": "https://docs.studio.nebius.com/quickstart",
+ "api": "https://api.tokenfactory.nebius.com/v1",
+ "doc": "https://docs.tokenfactory.nebius.com/",
"env": [
"NEBIUS_API_KEY"
],
@@ -8706,7 +8805,7 @@
"tool_call": true
}
},
- "name": "Nebius AI Studio",
+ "name": "Nebius Token Factory",
"npm": "@ai-sdk/openai-compatible"
},
"nvidia": {
@@ -8860,6 +8959,34 @@
"temperature": true,
"tool_call": true
},
+ "minimaxai/minimax-m2": {
+ "attachment": false,
+ "cost": {
+ "input": 0,
+ "output": 0
+ },
+ "id": "minimaxai/minimax-m2",
+ "knowledge": "2024-07",
+ "last_updated": "2025-10-31",
+ "limit": {
+ "context": 128000,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "MiniMax-M2",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-10-27",
+ "temperature": true,
+ "tool_call": true
+ },
"moonshotai/kimi-k2-instruct": {
"attachment": false,
"cost": {
@@ -9030,6 +9157,34 @@
"temperature": false,
"tool_call": false
},
+ "nvidia/nvidia-nemotron-nano-9b-v2": {
+ "attachment": false,
+ "cost": {
+ "input": 0,
+ "output": 0
+ },
+ "id": "nvidia/nvidia-nemotron-nano-9b-v2",
+ "knowledge": "2024-09",
+ "last_updated": "2025-08-18",
+ "limit": {
+ "context": 131072,
+ "output": 131072
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "nvidia-nemotron-nano-9b-v2",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-08-18",
+ "temperature": true,
+ "tool_call": true
+ },
"nvidia/parakeet-tdt-0.6b-v2": {
"attachment": false,
"cost": {
@@ -9169,6 +9324,62 @@
"release_date": "2025-07-23",
"temperature": true,
"tool_call": true
+ },
+ "qwen/qwen3-next-80b-a3b-instruct": {
+ "attachment": false,
+ "cost": {
+ "input": 0,
+ "output": 0
+ },
+ "id": "qwen/qwen3-next-80b-a3b-instruct",
+ "knowledge": "2024-12",
+ "last_updated": "2025-09-05",
+ "limit": {
+ "context": 262144,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "Qwen3-Next-80B-A3B-Instruct",
+ "open_weights": false,
+ "reasoning": false,
+ "release_date": "2024-12-01",
+ "temperature": true,
+ "tool_call": true
+ },
+ "qwen/qwen3-next-80b-a3b-thinking": {
+ "attachment": false,
+ "cost": {
+ "input": 0,
+ "output": 0
+ },
+ "id": "qwen/qwen3-next-80b-a3b-thinking",
+ "knowledge": "2024-12",
+ "last_updated": "2025-09-05",
+ "limit": {
+ "context": 262144,
+ "output": 16384
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "Qwen3-Next-80B-A3B-Thinking",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2024-12-01",
+ "temperature": true,
+ "tool_call": true
}
},
"name": "Nvidia",
@@ -11775,6 +11986,35 @@
"temperature": true,
"tool_call": true
},
+ "moonshotai/kimi-k2-thinking": {
+ "attachment": false,
+ "cost": {
+ "cache_read": 0.15,
+ "input": 0.6,
+ "output": 2.5
+ },
+ "id": "moonshotai/kimi-k2-thinking",
+ "knowledge": "2024-08",
+ "last_updated": "2025-11-06",
+ "limit": {
+ "context": 262144,
+ "output": 262144
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "Kimi K2 Thinking",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-11-06",
+ "temperature": true,
+ "tool_call": true
+ },
"moonshotai/kimi-k2:free": {
"attachment": false,
"cost": {
@@ -11887,6 +12127,34 @@
"temperature": true,
"tool_call": true
},
+ "nvidia/nemotron-nano-9b-v2": {
+ "attachment": false,
+ "cost": {
+ "input": 0.04,
+ "output": 0.16
+ },
+ "id": "nvidia/nemotron-nano-9b-v2",
+ "knowledge": "2024-09",
+ "last_updated": "2025-08-18",
+ "limit": {
+ "context": 131072,
+ "output": 131072
+ },
+ "modalities": {
+ "input": [
+ "text"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "nvidia-nemotron-nano-9b-v2",
+ "open_weights": true,
+ "reasoning": true,
+ "release_date": "2025-08-18",
+ "temperature": true,
+ "tool_call": true
+ },
"openai/gpt-4.1": {
"attachment": true,
"cost": {
@@ -12381,6 +12649,35 @@
"temperature": false,
"tool_call": true
},
+ "openrouter/polaris-alpha": {
+ "attachment": true,
+ "cost": {
+ "input": 0,
+ "output": 0
+ },
+ "id": "openrouter/polaris-alpha",
+ "knowledge": "2025-07",
+ "last_updated": "2025-07-30",
+ "limit": {
+ "context": 256000,
+ "output": 128000
+ },
+ "modalities": {
+ "input": [
+ "text",
+ "image"
+ ],
+ "output": [
+ "text"
+ ]
+ },
+ "name": "Polaris Alpha",
+ "open_weights": false,
+ "reasoning": false,
+ "release_date": "2025-07-30",
+ "temperature": false,
+ "tool_call": true
+ },
"openrouter/sonoma-dusk-alpha": {
"attachment": true,
"cost": {
diff --git a/libs/model-profiles/pyproject.toml b/libs/model-profiles/pyproject.toml
index 3d569ba88d..e68aba8675 100644
--- a/libs/model-profiles/pyproject.toml
+++ b/libs/model-profiles/pyproject.toml
@@ -9,7 +9,7 @@ readme = "README.md"
license = { text = "MIT" }
authors = []
-version = "0.0.3"
+version = "0.0.4"
requires-python = ">=3.10.0,<4.0.0"
dependencies = [
"tomli>=2.0.0,<3.0.0; python_version < '3.11'",
diff --git a/libs/model-profiles/uv.lock b/libs/model-profiles/uv.lock
index de16e602a7..5c5c1d96c6 100644
--- a/libs/model-profiles/uv.lock
+++ b/libs/model-profiles/uv.lock
@@ -459,7 +459,7 @@ wheels = [
[[package]]
name = "langchain"
-version = "1.0.3"
+version = "1.0.5"
source = { editable = "../langchain_v1" }
dependencies = [
{ name = "langchain-core" },
@@ -528,7 +528,7 @@ typing = [
[[package]]
name = "langchain-core"
-version = "1.0.3"
+version = "1.0.4"
source = { editable = "../core" }
dependencies = [
{ name = "jsonpatch" },
@@ -588,7 +588,7 @@ typing = [
[[package]]
name = "langchain-model-profiles"
-version = "0.0.3"
+version = "0.0.4"
source = { editable = "." }
dependencies = [
{ name = "tomli", marker = "python_full_version < '3.11'" },