ATRIUMsearch → argument graph
Article · 2026-08-09 · 4 moments

GitHub Models is now retired

GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as part of a scheduled retirement brownout. That message is already stale, because the retirement has been completed. GitHub Models was an odd-shaped duck. GitHub provided a model playground tool and a unified API across a bunch of different LLM providers, with the biggest benefit being that code ru ✦ AI generated

01
Prediction

GitHub likely retired Models because coding agent patterns made offering free or subsidized tokens prohibitively expensive.

Though GitHub did not give a reason, the author bets the shutdown fits a pattern where coding agents made free or subsidized tokens prohibitively expensive.

transcript

Simon Willison: GitHub didn't share the reason behind the shutdown, but my bet is that it fits the pattern where coding agent patterns made it prohibitively expensive to offer free or subsidized tokens.

02
Fact

GitHub Models has been retired, and the error message about a scheduled retirement brownout is stale because the retirement is already complete.

The author missed the news of GitHub Models' retirement until a GitHub Actions run failed, producing an already-outdated brownout message.

transcript

Simon Willison: I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as part of a scheduled retirement brownout. That message is already stale, because the retirement has been completed.

03
Definition

GitHub Models offered a model playground and a unified API across many LLM providers, whose biggest benefit was that code in GitHub Actions could use the GitHub API key already present in that environment.

Describes GitHub Models as an odd-shaped duck—a playground plus unified API across providers, valued mainly for reusing the ambient GitHub API key in Actions.

transcript

Simon Willison: GitHub Models was an odd-shaped duck. GitHub provided a model playground tool and a unified API across a bunch of different LLM providers, with the biggest benefit being that code running in GitHub Actions could use the GitHub API key already present in that environment to execute prompts. This made it easy to build things that fit GitHub Next's Continuous AI concept.

04
Example

The author replaced GitHub Models with an OpenAI API key carrying a monthly spending limit, and now generates his README summaries using GPT-5.6 Luna.

The author's workflow calls an LLM to summarize folders for the README; after the shutdown he swapped GitHub Models for a spending-capped OpenAI API key and GPT-5.6 Luna.

transcript

Simon Willison: My workflow uses an LLM call to create folder summaries for the README, using this code here. I swapped GitHub Models out for an OpenAI API key with a monthly spending limit, and I'm now generating my summaries using GPT-5.6 Luna.

Highlight slides
Related episodes