For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

MAX REST API

The MAX REST API provides an OpenAI-compatible REST endpoint for deploying LLMs and other GenAI models locally or in the cloud.

To create your first endpoint and start sending inference requests, see the quickstart guide.

Supported endpoints

The MAX API is compatible with a subset of the OpenAI API, so you can use any existing OpenAI client to send inference requests to your MAX endpoint.

• Create response (POST /v1/responses)
• Create chat completion (POST /v1/chat/completions)
• Create completion (POST /v1/completions)
• Create embeddings (POST /v1/embeddings)
• Create decisions (POST /v1/decisions)
• Create System One answers (POST /v1/systemone)
• Create speech (POST /v1/audio/speech)
• List models (GET /v1/models)
• Health check (GET /health)

Parameter handling

Although MAX aims for high compatibility, not all OpenAI body parameters are implemented. Some may be accepted as no-ops (ignored without causing errors) to maintain client compatibility. Each endpoint page documents only the parameters that actively affect behavior in MAX.

In addition to the OpenAI APIs, MAX provides a Prometheus-formatted metrics endpoint to help track your model's performance.