> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.mixlayer.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.mixlayer.com/_mcp/server.

# Introduction

> Welcome to the Mixlayer Docs!

Welcome! 👋

Mixlayer is an inference platform for open source AI models. We expose an OpenAI-compatible REST API, so you can drop Mixlayer into most existing applications by swapping the base URL and API key.

```bash
curl https://models.mixlayer.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIXLAYER_API_KEY" \
  -d '{"model": "qwen/qwen3.5-4b-free", "messages": [...]}'
```

## Get started

1. **Sign up** at [console.mixlayer.com](https://console.mixlayer.com/sign-up) and grab an [API key](https://console.mixlayer.com/app/api-keys).
2. Walk through the **[Quickstart](/quickstart)** to make your first request.
3. Browse the **[Models](/models)** catalog to pick the right model for your workload.
4. Read the **[Chat Completions](/api-reference/inference-ap-is/chat-completions/chat-completions)** reference for every supported parameter.

## Guides

* **[Client Libraries](/client-libraries)** — Python, TypeScript, Rust, and curl examples
* **[Choosing an Inference API](/choosing-an-inference-api)** — decide between Chat Completions and Responses
* **[Tool Calling](/tool-calling)** — let the model invoke your functions
* **[Reasoning](/reasoning)** — read the model's chain of thought