ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ff28097a36d761906ec6f4cfad781b60e3c95a29
pi_harness/packages/ai/src/providers/azure-openai-responses.models.ts
T
Mario Zechner 9993c96907 feat(coding-agent): replace model registry with model runtime 
Move provider auth and OAuth flows onto pi-ai Models, compose models.json and extension overlays through ModelRuntime, and retain ModelRegistry as an extension compatibility facade.
2026-07-14 17:48:45 +02:00

817 lines
18 KiB
TypeScript
Raw Blame History

// This file is auto-generated by scripts/generate-models.ts
// Do not edit manually - run 'npm run generate-models' to update
import type { Model } from "../types.ts";
export const AZURE_OPENAI_RESPONSES_MODELS = {
"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: 0.025,
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: 0.075,
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 15,
output: 120,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} 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,
thinkingLevelMap: {"off":null},
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-chat-latest": {
id: "gpt-5.1-chat-latest",
name: "GPT-5.1 Chat",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null},
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,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
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,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
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,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
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,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 21,
output: 168,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.3-chat-latest": {
id: "gpt-5.3-chat-latest",
name: "GPT-5.3 Chat (latest)",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: false,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"azure-openai-responses">,
"gpt-5.3-codex": {
id: "gpt-5.3-codex",
name: "GPT-5.3 Codex",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.3-codex-spark": {
id: "gpt-5.3-codex-spark",
name: "GPT-5.3 Codex Spark",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 32000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.4": {
id: "gpt-5.4",
name: "GPT-5.4",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 2.5,
output: 15,
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.4-mini": {
id: "gpt-5.4-mini",
name: "GPT-5.4 mini",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 0.75,
output: 4.5,
cacheRead: 0.075,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.4-nano": {
id: "gpt-5.4-nano",
name: "GPT-5.4 nano",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 0.2,
output: 1.25,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.4-pro": {
id: "gpt-5.4-pro",
name: "GPT-5.4 Pro",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 30,
output: 180,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.5": {
id: "gpt-5.5",
name: "GPT-5.5",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-5.5-pro": {
id: "gpt-5.5-pro",
name: "GPT-5.5 Pro",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"low":null},
input: ["text", "image"],
cost: {
input: 30,
output: 180,
cacheRead: 0,
cacheWrite: 0,
},
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","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","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","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">,
"gpt-realtime-2.1": {
id: "gpt-realtime-2.1",
name: "GPT-Realtime-2.1",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
input: ["text", "image"],
cost: {
input: 4,
output: 24,
cacheRead: 0.4,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 32000,
} 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: 0.275,
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">,
} as const;
Reference in New Issue View Git Blame Copy Permalink