Skip to content

GitHub Copilot adds Gemini 4 Argon as a selectable model

Google's frontier model is now generally available across Copilot, from VS Code to the CLI, billed at provider list pricing.

Source: GitHub Changelog

GitHub made Gemini 4 Argon generally available in Copilot today, 13 October. It’s selectable from the model picker in VS Code, Visual Studio, Copilot CLI, the Copilot coding agent, the Copilot app, JetBrains IDEs, Xcode and Eclipse, for Pro+, Max, Business and Enterprise plans.

GitHub says the model solved more tasks than previous Gemini models on every coding benchmark it tested, with the largest gains in Copilot CLI, and that it checks its own work and tests edge cases before finishing. It’s billed at provider list pricing under usage-based billing. Rollout is gradual, so it may not appear in your picker immediately. Business and Enterprise admins control access through the model policy in Copilot settings, where new models are enabled by default unless an admin turns them off.

Why it matters: this is the same model Google shipped generally available with a 1M-token context window earlier this month, now reachable from inside the editor most Copilot users already have open. If you’ve been picking models per task, it’s worth a direct comparison against whatever you currently default to for agentic or CLI work, since that’s where GitHub says the gap is widest.

The caveat: “billed at provider list pricing” means you should check the per-token rate before turning it on for heavy agentic use, since it won’t necessarily match what you pay for GitHub’s own model tiers.

Share

Related reading

ML for Web Devs

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

More from The Wire

All briefs