LM Studio API

LM Studio offers a powerful REST API with first-class support for local inference and model management. In addition to our native API, we provide full OpenAI compatibility mode (learn more).

What's new

Previously, there was a v0 REST API. That API has since been deprecated in favor of the v1 REST API.

The v1 REST API includes enhanced features such as:

• MCP via API
• Stateful chats
• Authentication configuration with API tokens
• Model download and load endpoints

Supported endpoints

The following endpoints are available in LM Studio's v1 REST API.

Endpoint	Method	Docs
/api/v1/chat	POST	Chat
/api/v1/models	GET	List Models
/api/v1/models/load	POST	Load
/api/v1/models/download	POST	Download
/api/v1/models/download/status	GET	Download Status

Inference endpoint comparison

The table below compares the features of LM Studio's /api/v1/chat endpoint with the OpenAI-compatible /v1/responses and /v1/chat/completions endpoints.

Feature	/api/v1/chat	/v1/responses	/v1/chat/completions
Stateful chat	✅	✅	❌
Remote MCPs	✅	✅	❌
MCPs you have in LM Studio	✅	✅	❌
Custom tools	❌	✅	✅
Model load streaming events	✅	❌	❌
Prompt processing streaming events	✅	❌	❌
Specify context length in the request	✅	❌	❌

---

Please report bugs by opening an issue on Github.