mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-19 12:04:08 +00:00
add Azure OpenAI Responses provider with deployment-aware model mapping
This commit is contained in:
Markus Ylisiurunen
Mario Zechner
parent
951fb953ed
commit
856012296b
23 changed files with 1465 additions and 21 deletions
|
|
@ -1300,6 +1300,586 @@ export const MODELS = {
|
|||
maxTokens: 64000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
},
|
||||
"azure-openai-responses": {
|
||||
"codex-mini-latest": {
|
||||
id: "codex-mini-latest",
|
||||
name: "Codex Mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.5,
|
||||
output: 6,
|
||||
cacheRead: 0.375,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4": {
|
||||
id: "gpt-4",
|
||||
name: "GPT-4",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 30,
|
||||
output: 60,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8192,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4-turbo": {
|
||||
id: "gpt-4-turbo",
|
||||
name: "GPT-4 Turbo",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 10,
|
||||
output: 30,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4.1": {
|
||||
id: "gpt-4.1",
|
||||
name: "GPT-4.1",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 8,
|
||||
cacheRead: 0.5,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1047576,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4.1-mini": {
|
||||
id: "gpt-4.1-mini",
|
||||
name: "GPT-4.1 mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 1.6,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1047576,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4.1-nano": {
|
||||
id: "gpt-4.1-nano",
|
||||
name: "GPT-4.1 nano",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.4,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1047576,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4o": {
|
||||
id: "gpt-4o",
|
||||
name: "GPT-4o",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2.5,
|
||||
output: 10,
|
||||
cacheRead: 1.25,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4o-2024-05-13": {
|
||||
id: "gpt-4o-2024-05-13",
|
||||
name: "GPT-4o (2024-05-13)",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 5,
|
||||
output: 15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4o-2024-08-06": {
|
||||
id: "gpt-4o-2024-08-06",
|
||||
name: "GPT-4o (2024-08-06)",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2.5,
|
||||
output: 10,
|
||||
cacheRead: 1.25,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4o-2024-11-20": {
|
||||
id: "gpt-4o-2024-11-20",
|
||||
name: "GPT-4o (2024-11-20)",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2.5,
|
||||
output: 10,
|
||||
cacheRead: 1.25,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-4o-mini": {
|
||||
id: "gpt-4o-mini",
|
||||
name: "GPT-4o mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0.08,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5": {
|
||||
id: "gpt-5",
|
||||
name: "GPT-5",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5-chat-latest": {
|
||||
id: "gpt-5-chat-latest",
|
||||
name: "GPT-5 Chat Latest",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5-codex": {
|
||||
id: "gpt-5-codex",
|
||||
name: "GPT-5-Codex",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5-mini": {
|
||||
id: "gpt-5-mini",
|
||||
name: "GPT-5 Mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 2,
|
||||
cacheRead: 0.025,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5-nano": {
|
||||
id: "gpt-5-nano",
|
||||
name: "GPT-5 Nano",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.05,
|
||||
output: 0.4,
|
||||
cacheRead: 0.005,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5-pro": {
|
||||
id: "gpt-5-pro",
|
||||
name: "GPT-5 Pro",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 15,
|
||||
output: 120,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 272000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.1": {
|
||||
id: "gpt-5.1",
|
||||
name: "GPT-5.1",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.13,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.1-chat-latest": {
|
||||
id: "gpt-5.1-chat-latest",
|
||||
name: "GPT-5.1 Chat",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.1-codex": {
|
||||
id: "gpt-5.1-codex",
|
||||
name: "GPT-5.1 Codex",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.1-codex-max": {
|
||||
id: "gpt-5.1-codex-max",
|
||||
name: "GPT-5.1 Codex Max",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.1-codex-mini": {
|
||||
id: "gpt-5.1-codex-mini",
|
||||
name: "GPT-5.1 Codex mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 2,
|
||||
cacheRead: 0.025,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.2": {
|
||||
id: "gpt-5.2",
|
||||
name: "GPT-5.2",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.75,
|
||||
output: 14,
|
||||
cacheRead: 0.175,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.2-chat-latest": {
|
||||
id: "gpt-5.2-chat-latest",
|
||||
name: "GPT-5.2 Chat",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.75,
|
||||
output: 14,
|
||||
cacheRead: 0.175,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.2-codex": {
|
||||
id: "gpt-5.2-codex",
|
||||
name: "GPT-5.2 Codex",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.75,
|
||||
output: 14,
|
||||
cacheRead: 0.175,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.2-pro": {
|
||||
id: "gpt-5.2-pro",
|
||||
name: "GPT-5.2 Pro",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 21,
|
||||
output: 168,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o1": {
|
||||
id: "o1",
|
||||
name: "o1",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 15,
|
||||
output: 60,
|
||||
cacheRead: 7.5,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o1-pro": {
|
||||
id: "o1-pro",
|
||||
name: "o1-pro",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 150,
|
||||
output: 600,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o3": {
|
||||
id: "o3",
|
||||
name: "o3",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 8,
|
||||
cacheRead: 0.5,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o3-deep-research": {
|
||||
id: "o3-deep-research",
|
||||
name: "o3-deep-research",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 10,
|
||||
output: 40,
|
||||
cacheRead: 2.5,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o3-mini": {
|
||||
id: "o3-mini",
|
||||
name: "o3-mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.1,
|
||||
output: 4.4,
|
||||
cacheRead: 0.55,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o3-pro": {
|
||||
id: "o3-pro",
|
||||
name: "o3-pro",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 20,
|
||||
output: 80,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o4-mini": {
|
||||
id: "o4-mini",
|
||||
name: "o4-mini",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.1,
|
||||
output: 4.4,
|
||||
cacheRead: 0.28,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o4-mini-deep-research": {
|
||||
id: "o4-mini-deep-research",
|
||||
name: "o4-mini-deep-research",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 8,
|
||||
cacheRead: 0.5,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
},
|
||||
"cerebras": {
|
||||
"gpt-oss-120b": {
|
||||
id: "gpt-oss-120b",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue