GitHub Models

GitHub Models opened as a limited public beta on August 1, 2024 with an argument that was hard to dispute: the largest population of developers on earth was already logged into GitHub, so the shortest path from curiosity to production ran through a free playground sitting next to the code. It shipped with Llama 3.1, GPT-4o, Phi 3, and Mistral Large 2, a written promise that no prompt or output would be shared with model providers or used for training, and a route out through Codespaces and VS Code into Azure. What it never had was a reason to exist inside Microsoft, which by 2026 wanted durable AI work running through Copilot or Foundry rather than a third front door. GitHub closed the product to new customers on June 16, 2026, announced full retirement on July 1, and ran deliberate outages on July 16 and July 23 so that anything still calling the inference API would break loudly before it broke silently. On July 30, 2026 the playground, the catalog, the API, and the bring-your-own-key layer were removed together, and every model in the catalog went on being available somewhere else.

Founded

2024-08

Shut down

2026-07-30

Funding raised

Undisclosed

Years alive

2

Founders

GitHub