Follow Discord
Sweep 23 Oct 2026 · 21:48Z Build v2.1.310 529 read Stable v2.1.308 Latest v2.1.309 Next v2.1.310 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.310 ·

Allowed-model lists now match model ids that carry a provider prefix

Model allowlist matching now also tries the part of a model id after its last slash, and matches through catalog names and families

You'll notice Improvements
JSON All of v2.1.310
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
ModelsArea: what it touches
ImprovementsKind: in v2.1.310,
ImprovementsSection of the release
What

An administrator can limit which models people may use with a list of allowed models, the availableModels setting. Matching a model against that list used to compare only the model's name and its alias, ignoring upper and lower case. It now also:

  • Tries the part of the model id after the last /, so an id with a provider prefix in front can still match.
  • Expands matches through the names and families in the model catalog.

When Claude Code is not using Anthropic's own API, enforcing the list now picks the first usable entry from it.

Why

An availableModels list written with plain model names now works for ids that a provider or gateway writes with a prefix such as a provider name and a slash.

Read from
Names in the bundleavailableModels

See this entry in the whole of v2.1.310 →

Feedback