Modular

MAX Inference REST API

OpenAI-compatible inference API served by MAX. Exposes /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/responses (image and video generation), and /v1/models. Hosted at api.modular.com with Bearer API-token auth, or self-hosted via `max serve`.

GitHub

Documentation

📖
Documentation
https://docs.modular.com/max/rest-api/

Other Resources

🔗
OpenAICompatible
https://docs.modular.com/max/inference/text-to-text/
🔗
APIsJSON
https://raw.githubusercontent.com/api-evangelist/modular/refs/heads/main/apis.yml

API entry from apis.yml

apis.yml Raw ↑ 
name: MAX Inference REST API
description: OpenAI-compatible inference API served by MAX. Exposes /v1/chat/completions, /v1/completions,
  /v1/embeddings, /v1/responses (image and video generation), and /v1/models. Hosted at api.modular.com
  with Bearer API-token auth, or self-hosted via `max serve`.
humanURL: https://docs.modular.com/max/rest-api/
baseURL: https://api.modular.com/v1
tags:
- Inference
- LLM
- Embeddings
- AI
properties:
- type: Documentation
  url: https://docs.modular.com/max/rest-api/
- type: OpenAICompatible
  url: https://docs.modular.com/max/inference/text-to-text/