Framework-independent · Promise-first · Apache-2.0

One typed interface for your LLM providers

Use chat completions, streaming, tools, embeddings, responses, images, moderation, and audio without coupling your application to one provider SDK.

Get started View on GitHub

quickstart.ts

import { completion } from "any-llm-ts";

const response = await completion({
  provider: "openai",
  model: "gpt-4.1-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0]?.message.content);

Switch providers

Keep one application-facing API while changing the provider behind it.

Stay type-safe

Get typed parameters, results, streaming chunks, tools, and common errors.

Extend when needed

Use native adapters, registered providers, or your own OpenAI-compatible endpoint.