GitHub Models API now available

You can now use the GitHub Models REST API to programmatically explore and run inference with models hosted on GitHub. This includes:

• GET /catalog/models — List all available models, including publisher, modality support, and rate limits.
• POST /inference/chat/completions — Run a chat completion using any supported model.
• POST /orgs/{org}/inference/chat/completions — Attribute inference requests to a GitHub organization.

These endpoints support streaming and non-streaming completions, as well as advanced options like temperature, stop sequences, and deterministic sampling via seed.

Check out the Models API reference docs to get started, or join the conversation in community discussions.