mirror of
https://github.com/badlogic/pi-mono.git
synced 2026-11-05 23:37:25 +00:00
2e0f175bd5
This builds the model catalog from per-provider definitions and models.dev v2 data. It eplacer `generate-models.ts` with one `defineProvider()` file per built-in provider, shared model-family rules (Claude, GPT, DeepSeek, Kimi, Google), and source adapters. models.dev is read through its v2 API. Outputs and CLI flags are unchanged.
61 lines
2.2 KiB
TypeScript
61 lines
2.2 KiB
TypeScript
import type { Model, ModelCost } from "../../src/types.ts";
|
|
import { type ChatModel, defineProvider, mergeCompat } from "../define.ts";
|
|
import { enableOpenAiGrammarTools } from "../families/openai.ts";
|
|
|
|
// Azure Foundry deploys these with larger context windows than OpenAI's own short-tier defaults.
|
|
// See models-sold-directly-by-azure docs.
|
|
const CONTEXT_WINDOW_OVERRIDES: Record<string, number> = {
|
|
"gpt-5.4": 1050000,
|
|
"gpt-5.5": 1050000,
|
|
"gpt-5.6-luna": 1050000,
|
|
"gpt-5.6-sol": 1050000,
|
|
"gpt-5.6-terra": 1050000,
|
|
};
|
|
|
|
// Azure resells DeepSeek at its own rates. US data zone, checked 2026-09-16.
|
|
// https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/
|
|
const DEEPSEEK_V4_PRO_COST: ModelCost = { input: 1.925, output: 3.828, cacheRead: 0.165, cacheWrite: 0 };
|
|
|
|
/** OpenAI models as Azure deploys them. Azure bills without OpenAI's long-context tier. */
|
|
function openAiModels(models: ChatModel[]): ChatModel[] {
|
|
return models
|
|
.filter((model) => model.api === "openai-responses")
|
|
.map((model) => ({
|
|
...model,
|
|
api: "azure-openai-responses",
|
|
provider: "azure",
|
|
baseUrl: "",
|
|
cost: {
|
|
input: model.cost.input,
|
|
output: model.cost.output,
|
|
cacheRead: model.cost.cacheRead,
|
|
cacheWrite: model.cost.cacheWrite,
|
|
},
|
|
contextWindow: CONTEXT_WINDOW_OVERRIDES[model.id] ?? model.contextWindow,
|
|
}));
|
|
}
|
|
|
|
export default defineProvider({
|
|
id: "azure",
|
|
models: (ctx) => [
|
|
...openAiModels(ctx.providerModels("openai")),
|
|
...ctx
|
|
.providerModels("deepseek")
|
|
.filter((model) => model.id === "deepseek-v4-pro")
|
|
.map((model) => ({ ...model, provider: "azure", baseUrl: "", cost: DEEPSEEK_V4_PRO_COST })),
|
|
],
|
|
compat: { "openai-completions": { supportsStrictMode: true } },
|
|
finalize: (model) => {
|
|
enableOpenAiGrammarTools(model);
|
|
if (model.api === "openai-completions") {
|
|
// Azure 400s on DeepSeek's `thinking` field and on every prompt cache parameter, discards a
|
|
// `developer` system message unbilled once reasoning_effort is set, and honours mid-convo ones (#9645).
|
|
mergeCompat(model as Model<"openai-completions">, {
|
|
supportsDeveloperRole: false,
|
|
supportsMidConvoSystemMessages: true,
|
|
thinkingFormat: "openai",
|
|
supportsLongCacheRetention: false,
|
|
});
|
|
}
|
|
},
|
|
});
|