# FlexInference

## Docs

- [Authentication](https://flexinference.mintlify.app/authentication.md): Your FlexInference API key and your BYOK OpenAI key.
- [Pricing and billing](https://flexinference.mintlify.app/billing.md): What FlexInference charges, how BYOK works, and when your card is charged.
- [Deadline routing](https://flexinference.mintlify.app/deadline-routing.md): The start_within field, the flex race, and automatic fallback.
- [Errors](https://flexinference.mintlify.app/errors.md): The error envelope, FlexInference codes, and what passes through from OpenAI.
- [What FlexInference does](https://flexinference.mintlify.app/index.md): An OpenAI-compatible router that works with OpenAI, Gemini, and Anthropic. Bring your own key and set one field, start_within, to say how long you can wait. FlexInference finds a cheaper way to run the same request, and you only pay when it saves you money.
- [MCP server](https://flexinference.mintlify.app/mcp.md): Connect Claude, Cursor, and other agents to FlexInference over the Model Context Protocol.
- [Supported models](https://flexinference.mintlify.app/models.md): The models FlexInference routes, and the inputs they accept.
- [Quickstart](https://flexinference.mintlify.app/quickstart.md): From zero to your first request that runs the cheaper tier and still comes back in time.
- [SDKs and API usage](https://flexinference.mintlify.app/sdks.md): Use the OpenAI SDK you already have. Change the base URL, add start_within.

## Optional

- [Status](https://api.flexinference.com/health)
- [Python SDK](https://pypi.org/project/flexinference/)
- [TypeScript SDK](https://www.npmjs.com/package/flexinference)