Skip to content

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust

add gpt-5.6 model catalogs (#361)

kt4a0b3de73657
diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index 5c34ca1752..182d5bc138 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -2,6 +2,8 @@
## [Unreleased]
+- Added GPT-5.6 Sol, Terra, and Luna to OpenAI API-key and Codex subscription model catalogs, with their 1.05M API / 272k Codex context windows and `low` through `max` reasoning support.
+
## [0.2.7] - 2026-07-08
- Added `internal/glm-5.2-fast` to the Prime Inference model catalog.
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 9bb9aa8910..6c5971a03f 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -175,6 +175,10 @@ const OPENAI_RESPONSES_NONE_REASONING_MODELS = new Set([
"gpt-5.4-mini",
"gpt-5.4-nano",
"gpt-5.5",
+ "gpt-5.6",
+ "gpt-5.6-sol",
+ "gpt-5.6-terra",
+ "gpt-5.6-luna",
]);
function mergeThinkingLevelMap(model: Model<any>, map: NonNullable<Model<any>["thinkingLevelMap"]>): void {
@@ -186,7 +190,8 @@ function supportsOpenAiXhigh(modelId: string): boolean {
modelId.includes("gpt-5.2") ||
modelId.includes("gpt-5.3") ||
modelId.includes("gpt-5.4") ||
- modelId.includes("gpt-5.5")
+ modelId.includes("gpt-5.5") ||
+ modelId.includes("gpt-5.6")
);
}
@@ -223,6 +228,9 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
if (supportsOpenAiXhigh(model.id)) {
mergeThinkingLevelMap(model, { xhigh: "xhigh" });
}
+ if (model.id.includes("gpt-5.6")) {
+ mergeThinkingLevelMap(model, { minimal: null, max: "max" });
+ }
// Per-family effort support per the Anthropic effort docs. Opus 4.6 / Sonnet 4.6
// have no xhigh; Fable 5 / Mythos 5 / Mythos Preview think every turn (off: null).
if (
@@ -263,7 +271,11 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
if (model.provider === "groq" && model.id === "qwen/qwen3-32b") {
mergeThinkingLevelMap(model, { minimal: null, low: null, medium: null, high: "default" });
}
- if (model.provider === "openai-codex" && supportsOpenAiXhigh(model.id)) {
+ if (
+ model.provider === "openai-codex" &&
+ supportsOpenAiXhigh(model.id) &&
+ !model.id.includes("gpt-5.6")
+ ) {
mergeThinkingLevelMap(model, { minimal: "low" });
}
if (model.provider === "openai-codex" && model.id === "gpt-5.1-codex-mini") {
@@ -1817,6 +1829,42 @@ async function generateModels() {
contextWindow: CODEX_CONTEXT,
maxTokens: CODEX_MAX_TOKENS,
},
+ {
+ id: "gpt-5.6-sol",
+ name: "GPT-5.6 Sol",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: CODEX_BASE_URL,
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 6.25 },
+ contextWindow: CODEX_CONTEXT,
+ maxTokens: CODEX_MAX_TOKENS,
+ },
+ {
+ id: "gpt-5.6-terra",
+ name: "GPT-5.6 Terra",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: CODEX_BASE_URL,
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 3.125 },
+ contextWindow: CODEX_CONTEXT,
+ maxTokens: CODEX_MAX_TOKENS,
+ },
+ {
+ id: "gpt-5.6-luna",
+ name: "GPT-5.6 Luna",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: CODEX_BASE_URL,
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 1, output: 6, cacheRead: 0.1, cacheWrite: 1.25 },
+ contextWindow: CODEX_CONTEXT,
+ maxTokens: CODEX_MAX_TOKENS,
+ },
{
id: "gpt-5.4-mini",
name: "GPT-5.4 Mini",
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 0e628fda9f..7d7c68ef03 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -758,6 +758,23 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"bedrock-converse-stream">,
+ "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
+ id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
+ name: "Claude Haiku 4.5 (JP)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 5,
+ cacheRead: 0.1,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 200000,
+ maxTokens: 64000,
+ } satisfies Model<"bedrock-converse-stream">,
"jp.anthropic.claude-opus-4-7": {
id: "jp.anthropic.claude-opus-4-7",
name: "Claude Opus 4.7 (JP)",
@@ -1826,108 +1843,6 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
},
"anthropic": {
- "claude-3-5-sonnet-20240620": {
- id: "claude-3-5-sonnet-20240620",
- name: "Claude Sonnet 3.5",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
- },
- contextWindow: 200000,
- maxTokens: 8192,
- } satisfies Model<"anthropic-messages">,
- "claude-3-5-sonnet-20241022": {
- id: "claude-3-5-sonnet-20241022",
- name: "Claude Sonnet 3.5 v2",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
- },
- contextWindow: 200000,
- maxTokens: 8192,
- } satisfies Model<"anthropic-messages">,
- "claude-3-7-sonnet-20250219": {
- id: "claude-3-7-sonnet-20250219",
- name: "Claude Sonnet 3.7",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
- },
- contextWindow: 200000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
- "claude-3-haiku-20240307": {
- id: "claude-3-haiku-20240307",
- name: "Claude Haiku 3",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 0.25,
- output: 1.25,
- cacheRead: 0.03,
- cacheWrite: 0.3,
- },
- contextWindow: 200000,
- maxTokens: 4096,
- } satisfies Model<"anthropic-messages">,
- "claude-3-opus-20240229": {
- id: "claude-3-opus-20240229",
- name: "Claude Opus 3",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 15,
- output: 75,
- cacheRead: 1.5,
- cacheWrite: 18.75,
- },
- contextWindow: 200000,
- maxTokens: 4096,
- } satisfies Model<"anthropic-messages">,
- "claude-3-sonnet-20240229": {
- id: "claude-3-sonnet-20240229",
- name: "Claude Sonnet 3",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 0.3,
- },
- contextWindow: 200000,
- maxTokens: 4096,
- } satisfies Model<"anthropic-messages">,
"claude-fable-5": {
id: "claude-fable-5",
name: "Claude Fable 5",
@@ -1980,23 +1895,6 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-0": {
- id: "claude-opus-4-0",
- name: "Claude Opus 4 (latest)",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 15,
- output: 75,
- cacheRead: 1.5,
- cacheWrite: 18.75,
- },
- contextWindow: 200000,
- maxTokens: 32000,
- } satisfies Model<"anthropic-messages">,
"claude-opus-4-1": {
id: "claude-opus-4-1",
name: "Claude Opus 4.1 (latest)",
@@ -2031,23 +1929,6 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-20250514": {
- id: "claude-opus-4-20250514",
- name: "Claude Opus 4",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 15,
- output: 75,
- cacheRead: 1.5,
- cacheWrite: 18.75,
- },
- contextWindow: 200000,
- maxTokens: 32000,
- } satisfies Model<"anthropic-messages">,
"claude-opus-4-5": {
id: "claude-opus-4-5",
name: "Claude Opus 4.5 (latest)",
@@ -2136,40 +2017,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "claude-sonnet-4-0": {
- id: "claude-sonnet-4-0",
- name: "Claude Sonnet 4 (latest)",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
- },
- contextWindow: 200000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
- "claude-sonnet-4-20250514": {
- id: "claude-sonnet-4-20250514",
- name: "Claude Sonnet 4",
- api: "anthropic-messages",
- provider: "anthropic",
- baseUrl: "https://api.anthropic.com",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
- },
- contextWindow: 200000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
"claude-sonnet-4-5": {
id: "claude-sonnet-4-5",
name: "Claude Sonnet 4.5 (latest)",
@@ -2184,7 +2031,7 @@ export const MODELS = {
cacheRead: 0.3,
cacheWrite: 3.75,
},
- contextWindow: 200000,
+ contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"claude-sonnet-4-5-20250929": {
@@ -2201,7 +2048,7 @@ export const MODELS = {
cacheRead: 0.3,
cacheWrite: 3.75,
},
- contextWindow: 200000,
+ contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"claude-sonnet-4-6": {
@@ -2220,7 +2067,7 @@ export const MODELS = {
cacheWrite: 3.75,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"claude-sonnet-5": {
id: "claude-sonnet-5",
@@ -2844,6 +2691,78 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
+ "gpt-5.6": {
+ id: "gpt-5.6",
+ name: "GPT-5.6",
+ api: "azure-openai-responses",
+ provider: "azure-openai-responses",
+ baseUrl: "",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"azure-openai-responses">,
+ "gpt-5.6-luna": {
+ id: "gpt-5.6-luna",
+ name: "GPT-5.6 Luna",
+ api: "azure-openai-responses",
+ provider: "azure-openai-responses",
+ baseUrl: "",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.1,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"azure-openai-responses">,
+ "gpt-5.6-sol": {
+ id: "gpt-5.6-sol",
+ name: "GPT-5.6 Sol",
+ api: "azure-openai-responses",
+ provider: "azure-openai-responses",
+ baseUrl: "",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"azure-openai-responses">,
+ "gpt-5.6-terra": {
+ id: "gpt-5.6-terra",
+ name: "GPT-5.6 Terra",
+ api: "azure-openai-responses",
+ provider: "azure-openai-responses",
+ baseUrl: "",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"azure-openai-responses">,
"o1": {
id: "o1",
name: "o1",
@@ -4038,7 +3957,7 @@ export const MODELS = {
cost: {
input: 1.4,
output: 4.4,
- cacheRead: 0.26,
+ cacheRead: 0.14,
cacheWrite: 0,
},
contextWindow: 1048575,
@@ -6026,6 +5945,24 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
+ "openai/gpt-oss-20b": {
+ id: "openai/gpt-oss-20b",
+ name: "GPT OSS 20B",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.1,
+ output: 0.5,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"stepfun-ai/Step-3.5-Flash": {
id: "stepfun-ai/Step-3.5-Flash",
name: "Step 3.5 Flash",
@@ -6683,11 +6620,11 @@ export const MODELS = {
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
- reasoning: false,
+ reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.4,
- output: 2,
+ input: 1.5,
+ output: 7.5,
cacheRead: 0,
cacheWrite: 0,
},
@@ -7796,18 +7733,90 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
- "o1": {
- id: "o1",
- name: "o1",
+ "gpt-5.6": {
+ id: "gpt-5.6",
+ name: "GPT-5.6",
api: "openai-responses",
provider: "openai",
baseUrl: "https://api.openai.com/v1",
reasoning: true,
+ thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 15,
- output: 60,
- cacheRead: 7.5,
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-responses">,
+ "gpt-5.6-luna": {
+ id: "gpt-5.6-luna",
+ name: "GPT-5.6 Luna",
+ api: "openai-responses",
+ provider: "openai",
+ baseUrl: "https://api.openai.com/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.1,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-responses">,
+ "gpt-5.6-sol": {
+ id: "gpt-5.6-sol",
+ name: "GPT-5.6 Sol",
+ api: "openai-responses",
+ provider: "openai",
+ baseUrl: "https://api.openai.com/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-responses">,
+ "gpt-5.6-terra": {
+ id: "gpt-5.6-terra",
+ name: "GPT-5.6 Terra",
+ api: "openai-responses",
+ provider: "openai",
+ baseUrl: "https://api.openai.com/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-responses">,
+ "o1": {
+ id: "o1",
+ name: "o1",
+ api: "openai-responses",
+ provider: "openai",
+ baseUrl: "https://api.openai.com/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 15,
+ output: 60,
+ cacheRead: 7.5,
cacheWrite: 0,
},
contextWindow: 200000,
@@ -8112,6 +8121,60 @@ export const MODELS = {
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"openai-codex-responses">,
+ "gpt-5.6-luna": {
+ id: "gpt-5.6-luna",
+ name: "GPT-5.6 Luna",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: "https://chatgpt.com/backend-api",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.1,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 272000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-codex-responses">,
+ "gpt-5.6-sol": {
+ id: "gpt-5.6-sol",
+ name: "GPT-5.6 Sol",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: "https://chatgpt.com/backend-api",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 272000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-codex-responses">,
+ "gpt-5.6-terra": {
+ id: "gpt-5.6-terra",
+ name: "GPT-5.6 Terra",
+ api: "openai-codex-responses",
+ provider: "openai-codex",
+ baseUrl: "https://chatgpt.com/backend-api",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 272000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-codex-responses">,
},
"opencode": {
"big-pickle": {
@@ -8774,6 +8837,23 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
+ "grok-4.5": {
+ id: "grok-4.5",
+ name: "Grok 4.5",
+ api: "openai-completions",
+ provider: "opencode",
+ baseUrl: "https://opencode.ai/zen/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"openai-completions">,
"grok-build-0.1": {
id: "grok-build-0.1",
name: "Grok Build 0.1",
@@ -8791,6 +8871,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
+ "hy3-free": {
+ id: "hy3-free",
+ name: "Hy3 Free",
+ api: "openai-completions",
+ provider: "opencode",
+ baseUrl: "https://opencode.ai/zen/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 256000,
+ maxTokens: 64000,
+ } satisfies Model<"openai-completions">,
"kimi-k2.5": {
id: "kimi-k2.5",
name: "Kimi K2.5",
@@ -9225,6 +9322,57 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
+ "aion-labs/aion-2.0": {
+ id: "aion-labs/aion-2.0",
+ name: "AionLabs: Aion-2.0",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.7999999999999999,
+ output: 1.5999999999999999,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
+ "aion-labs/aion-3.0": {
+ id: "aion-labs/aion-3.0",
+ name: "AionLabs: Aion-3.0",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 3,
+ output: 6,
+ cacheRead: 0.75,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
+ "aion-labs/aion-3.0-mini": {
+ id: "aion-labs/aion-3.0-mini",
+ name: "AionLabs: Aion-3.0-Mini",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.7,
+ output: 1.4,
+ cacheRead: 0.18,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"amazon/nova-2-lite-v1": {
id: "amazon/nova-2-lite-v1",
name: "Amazon: Nova 2 Lite",
@@ -9907,13 +10055,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
cost: {
- input: 0.08900000000000001,
+ input: 0.09,
output: 0.18,
cacheRead: 0.018,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -9968,23 +10116,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 65535,
} satisfies Model<"openai-completions">,
- "google/gemini-2.5-flash-lite-preview-09-2025": {
- id: "google/gemini-2.5-flash-lite-preview-09-2025",
- name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.09999999999999999,
- output: 0.39999999999999997,
- cacheRead: 0.01,
- cacheWrite: 0.08333333333333334,
- },
- contextWindow: 1048576,
- maxTokens: 65535,
- } satisfies Model<"openai-completions">,
"google/gemini-2.5-pro": {
id: "google/gemini-2.5-pro",
name: "Google: Gemini 2.5 Pro",
@@ -10538,9 +10669,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.12,
- output: 0.48,
- cacheRead: 0,
+ input: 0.15,
+ output: 0.8999999999999999,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 204800,
@@ -10555,8 +10686,8 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.18,
- output: 0.72,
+ input: 0.24,
+ output: 0.96,
cacheRead: 0,
cacheWrite: 0,
},
@@ -10946,7 +11077,7 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.66,
+ input: 0.65,
output: 3.41,
cacheRead: 0.14,
cacheWrite: 0,
@@ -10963,13 +11094,47 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.74,
- output: 3.5,
- cacheRead: 0.15,
+ input: 0.72,
+ output: 3.49,
+ cacheRead: 0.159,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 262144,
+ } satisfies Model<"openai-completions">,
+ "nex-agi/nex-n2-mini": {
+ id: "nex-agi/nex-n2-mini",
+ name: "Nex AGI: Nex-N2-Mini",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.024999999999999998,
+ output: 0.09999999999999999,
+ cacheRead: 0.0025,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 262144,
+ } satisfies Model<"openai-completions">,
+ "nex-agi/nex-n2-pro": {
+ id: "nex-agi/nex-n2-pro",
+ name: "Nex AGI: Nex-N2-Pro",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.25,
+ output: 1,
+ cacheRead: 0.024999999999999998,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -11048,13 +11213,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.08499999999999999,
- output: 0.39999999999999997,
+ input: 0.08,
+ output: 0.44999999999999996,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
- maxTokens: 16384,
+ maxTokens: 4096,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b:free": {
id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -11782,6 +11947,114 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-luna": {
+ id: "openai/gpt-5.6-luna",
+ name: "OpenAI: GPT-5.6 Luna",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.09999999999999999,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-luna-pro": {
+ id: "openai/gpt-5.6-luna-pro",
+ name: "OpenAI: GPT-5.6 Luna Pro",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.09999999999999999,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-sol": {
+ id: "openai/gpt-5.6-sol",
+ name: "OpenAI: GPT-5.6 Sol",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-sol-pro": {
+ id: "openai/gpt-5.6-sol-pro",
+ name: "OpenAI: GPT-5.6 Sol Pro",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-terra": {
+ id: "openai/gpt-5.6-terra",
+ name: "OpenAI: GPT-5.6 Terra",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "openai/gpt-5.6-terra-pro": {
+ id: "openai/gpt-5.6-terra-pro",
+ name: "OpenAI: GPT-5.6 Terra Pro",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
"openai/gpt-audio": {
id: "openai/gpt-audio",
name: "OpenAI: GPT Audio",
@@ -11842,13 +12115,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.03,
- output: 0.15,
+ input: 0.036,
+ output: 0.18,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 4096,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b:free": {
id: "openai/gpt-oss-120b:free",
@@ -12173,40 +12446,6 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
- "poolside/laguna-xs.2": {
- id: "poolside/laguna-xs.2",
- name: "Poolside: Laguna XS.2",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.09999999999999999,
- output: 0.19999999999999998,
- cacheRead: 0.049999999999999996,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 32768,
- } satisfies Model<"openai-completions">,
- "poolside/laguna-xs.2:free": {
- id: "poolside/laguna-xs.2:free",
- name: "Poolside: Laguna XS.2 (free)",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 32768,
- } satisfies Model<"openai-completions">,
"qwen/qwen-2.5-72b-instruct": {
id: "qwen/qwen-2.5-72b-instruct",
name: "Qwen2.5 72B Instruct",
@@ -12813,7 +13052,7 @@ export const MODELS = {
cost: {
input: 0.385,
output: 2.4499999999999997,
- cacheRead: 0,
+ cacheRead: 0.111,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -12898,7 +13137,7 @@ export const MODELS = {
cost: {
input: 0.28500000000000003,
output: 2.4,
- cacheRead: 0,
+ cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -13108,6 +13347,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
+ "tencent/hy3": {
+ id: "tencent/hy3",
+ name: "Tencent: Hy3",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.14,
+ output: 0.58,
+ cacheRead: 0.035,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 4096,
+ } satisfies Model<"openai-completions">,
"tencent/hy3-preview": {
id: "tencent/hy3-preview",
name: "Tencent: Hy3 preview",
@@ -13125,6 +13381,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
+ "tencent/hy3:free": {
+ id: "tencent/hy3:free",
+ name: "Tencent: Hy3 (free)",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 262144,
+ } satisfies Model<"openai-completions">,
"thedrummer/unslopnemo-12b": {
id: "thedrummer/unslopnemo-12b",
name: "TheDrummer: UnslopNemo 12B",
@@ -13193,6 +13466,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
+ "x-ai/grok-4.5": {
+ id: "x-ai/grok-4.5",
+ name: "xAI: Grok 4.5",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 4096,
+ } satisfies Model<"openai-completions">,
"x-ai/grok-build-0.1": {
id: "x-ai/grok-build-0.1",
name: "xAI: Grok Build 0.1",
@@ -13221,7 +13511,7 @@ export const MODELS = {
cost: {
input: 0.105,
output: 0.28,
- cacheRead: 0,
+ cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -13406,13 +13696,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.975,
- output: 4.300000000000001,
- cacheRead: 0,
+ input: 0.966,
+ output: 3.036,
+ cacheRead: 0.1794,
cacheWrite: 0,
},
contextWindow: 202752,
- maxTokens: 4096,
+ maxTokens: 128000,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
id: "z-ai/glm-5.2",
@@ -13423,13 +13713,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.9299999999999999,
- output: 3,
- cacheRead: 0.18,
+ input: 0.54,
+ output: 1.76,
+ cacheRead: 0.09999999999999999,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 32768,
+ maxTokens: 101376,
} satisfies Model<"openai-completions">,
"z-ai/glm-5v-turbo": {
id: "z-ai/glm-5v-turbo",
@@ -13559,7 +13849,7 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.66,
+ input: 0.65,
output: 3.41,
cacheRead: 0.14,
cacheWrite: 0,
@@ -13579,7 +13869,7 @@ export const MODELS = {
input: 5,
output: 30,
cacheRead: 0.5,
- cacheWrite: 0,
+ cacheWrite: 6.25,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -13601,6 +13891,23 @@ export const MODELS = {
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "~x-ai/grok-latest": {
+ id: "~x-ai/grok-latest",
+ name: "xAI: Grok Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 4096,
+ } satisfies Model<"openai-completions">,
},
"prime-inference": {
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
@@ -15577,6 +15884,23 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
+ "meta/muse-spark-1.1": {
+ id: "meta/muse-spark-1.1",
+ name: "Muse Spark 1.1",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.25,
+ output: 4.25,
+ cacheRead: 0.15,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 1048576,
+ } satisfies Model<"anthropic-messages">,
"minimax/minimax-m2": {
id: "minimax/minimax-m2",
name: "MiniMax M2",
@@ -16694,6 +17018,60 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
+ "openai/gpt-5.6-luna": {
+ id: "openai/gpt-5.6-luna",
+ name: "GPT 5.6 Luna",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1,
+ output: 6,
+ cacheRead: 0.09999999999999999,
+ cacheWrite: 1.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"anthropic-messages">,
+ "openai/gpt-5.6-sol": {
+ id: "openai/gpt-5.6-sol",
+ name: "GPT 5.6 Sol",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 6.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"anthropic-messages">,
+ "openai/gpt-5.6-terra": {
+ id: "openai/gpt-5.6-terra",
+ name: "GPT 5.6 Terra",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"anthropic-messages">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
name: "GPT OSS 120B",
@@ -17051,6 +17429,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 1000000,
} satisfies Model<"anthropic-messages">,
+ "xai/grok-4.5": {
+ id: "xai/grok-4.5",
+ name: "Grok 4.5",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"anthropic-messages">,
"xai/grok-build-0.1": {
id: "xai/grok-build-0.1",
name: "Grok Build 0.1",
@@ -17444,6 +17839,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 30000,
} satisfies Model<"openai-completions">,
+ "grok-4.5": {
+ id: "grok-4.5",
+ name: "Grok 4.5",
+ api: "openai-completions",
+ provider: "xai",
+ baseUrl: "https://api.x.ai/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"openai-completions">,
"grok-build-0.1": {
id: "grok-build-0.1",
name: "Grok Build 0.1",
diff --git a/packages/ai/test/supports-xhigh.test.ts b/packages/ai/test/supports-xhigh.test.ts
index 3d809e0ef1..38f399dde8 100644
--- a/packages/ai/test/supports-xhigh.test.ts
+++ b/packages/ai/test/supports-xhigh.test.ts
@@ -68,6 +68,29 @@ describe("getSupportedThinkingLevels", () => {
expect(getSupportedThinkingLevels(model!)).toContain("xhigh");
});
+ it.each(["gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna"] as const)(
+ "includes xhigh and max for %s through the OpenAI API and Codex subscription",
+ (modelId) => {
+ const apiModel = getModel("openai", modelId);
+ const codexModel = getModel("openai-codex", modelId);
+
+ expect(apiModel).toBeDefined();
+ expect(codexModel).toBeDefined();
+ expect(getSupportedThinkingLevels(apiModel!)).toEqual(["off", "low", "medium", "high", "xhigh", "max"]);
+ expect(getSupportedThinkingLevels(codexModel!)).toEqual(["off", "low", "medium", "high", "xhigh", "max"]);
+ expect(apiModel!.contextWindow).toBe(1050000);
+ expect(apiModel!.maxTokens).toBe(128000);
+ expect(codexModel!.contextWindow).toBe(272000);
+ expect(codexModel!.maxTokens).toBe(128000);
+ },
+ );
+
+ it("supports disabling reasoning for the base GPT-5.6 API alias", () => {
+ const model = getModel("openai", "gpt-5.6");
+ expect(model).toBeDefined();
+ expect(getSupportedThinkingLevels(model!)).toContain("off");
+ });
+
it("includes only high/xhigh plus off for DeepSeek V4 Flash on the DeepSeek provider", () => {
const model = getModel("deepseek", "deepseek-v4-flash");
expect(model).toBeDefined();