Anthropic model deprecations

How Anthropic retires models

Anthropic gives customers with active deployments at least 60 days’ notice before it retires a publicly released model, by email and on its model deprecations page. A deprecated model still works, but Anthropic names a replacement and sets a retirement date. Once the model is retired, requests to it fail. Active models carry only a tentative retirement date, given as “not sooner than” a day.

These dates apply to the platforms Anthropic operates: the Claude API, Claude Platform on AWS, Claude models on Google Cloud (Anthropic managed) and Microsoft Foundry. Amazon Bedrock and Google-managed Claude on Google Cloud set their own retirement schedules, so the same model can retire on a different day there. To find the calls still sending a deprecated model, the Usage page of the Claude Console exports usage by API key and model as a CSV.

Next shutdowns: claude-sonnet-4-5 on November 30, 2026, claude-sonnet-4-5-0 on November 30, 2026, claude-sonnet-4-5-20250929 on November 30, 2026.

What Anthropic answers a call to claude-opus-4-1 since August 5, 2026, as recorded from real responses:

{"type":"error","error":{"type":"not_found_error","message":"model: claude-opus-4-1"}}

Policy read on Anthropic's pages on November 5, 2026. Okapi last checked Anthropic's model pages on November 6, 2026.

• Anthropic model deprecations platform.claude.com/docs/en/about-claude/model-deprecations