Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.305 ·

1M-context model variant is picked in more cases

Claude Code now adds the [1m] long-context suffix to a model in more cases where a configured model already uses 1M context

You'll notice Improvements
JSON All of v2.1.305
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
ModelsArea: what it touches
ImprovementsKind: in v2.1.305,
ImprovementsSection of the release

Unclear Exactly which model names now get the 1M-context variant is not stated.

What

Some models have a variant with a context window of one million tokens, marked by [1m] after the model name. The context window is how much conversation the model can see at once. When working out which model to use, Claude Code now adds [1m] in one more case: when a configured model, or the model's own settings, already use 1M context and the model matches. The check for 1M support was also adjusted.

Why

If you use 1M-context models, the [1m] variant may be picked in more alias and override cases than before.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtExactly which model names now get the 1M-context variant is not stated.
Anthropic's release notes agreeFixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag

See this entry in the whole of v2.1.305 →

Feedback