# LM Studio as a Local LLM API Server

Run an LLM API server on localhost with LM Studio

You can serve local LLMs from LM Studio's Developer tab, either on `localhost` or on the network.

LM Studio's APIs can be used through [REST API](/content/docs/developer/rest/index.html), client libraries like [lmstudio-js](/content/docs/typescript/index.html) and [lmstudio-python](/content/docs/python/index.html), and compatibility endpoints like [OpenAI-compatible](/content/docs/developer/openai-compat/index.html) and [Anthropic-compatible](/content/docs/developer/anthropic-compat/index.html).

### Running the server

To run the server, go to the Developer tab in LM Studio, and toggle the "Start server" switch to start the API server.

Alternatively, you can use `lms` ( [LM Studio's CLI](/content/docs/cli/index.html)) to start the server from your terminal:

```
lms server start
```

### API options

- [LM Studio REST API](/content/docs/developer/rest/index.html)
- [TypeScript SDK](/content/docs/typescript/index.html) \- `lmstudio-js`
- [Python SDK](/content/docs/python/index.html) \- `lmstudio-python`
- [OpenAI-compatible endpoints](/content/docs/developer/openai-compat/index.html)
- [Anthropic-compatible endpoints](/content/docs/developer/anthropic-compat/index.html)

[API Changelog\
\
Updates and changes to the LM Studio API.](/content/docs/developer/api-changelog/index.html) [Serve on Local Network\
\
Allow other devices in your network use this LM Studio API server](/content/docs/developer/core/server/serve-on-network/index.html)

### On this page

[Running the server](/content/docs/developer/core/server#running-the-server/index.html) [API options](/content/docs/developer/core/server#api-options/index.html)