← Anthropic — deprecations

Observed 13 November 2026

The page's list of partner-operated platforms was reworded: the Amazon Bedrock table references changed from "Amazon Bedrock" and "Amazon Bedrock (Opus 4.6 and earlier)" to "Amazon Bedrock (bedrock-mantle)" and "Amazon Bedrock (bedrock-runtime)".

what changed matterssummary written by a model — check it against the diff below

A restriction or obligation was removed or reworded — 1 line containing binding language went away. Loosenings are rarely announced.

+1 −1  ·  88f0f1b → 572f6db  ·  572f6db59b04  ·  live page

anthropic/model-deprecations.txt13 Nov 2026
10 unchanged lines
- Deprecated: The model is still functional but no longer recommended. Anthropic provides a recommended replacement and assigns a retirement date.
- Retired: The model is no longer available for use. Requests to retired models fail.
Deprecated models are likely to be less reliable than active models. Move workloads to active models to maintain the highest level of support and reliability.
The dates on this page apply to Anthropic-operated platforms: the Claude API, Claude Platform on AWS , Claude Models on Google Cloud (Anthropic managed) , and Microsoft Foundry . Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Amazon Bedrock, set their own retirement schedules, so a model’s lifecycle status and dates can differ. See the Amazon Bedrock , Amazon Bedrock (Opus 4.6 and earlier) , and Claude Models on Google Cloud (Google managed) model tables.
The dates on this page apply to Anthropic-operated platforms: the Claude API, Claude Platform on AWS , Claude Models on Google Cloud (Anthropic managed) , and Microsoft Foundry . Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Amazon Bedrock, set their own retirement schedules, so a model’s lifecycle status and dates can differ. See the Amazon Bedrock ( bedrock-mantle ) , Amazon Bedrock ( bedrock-runtime ) , and Claude Models on Google Cloud (Google managed) model tables.
Migrating to replacements
Once a model is deprecated, migrate all usage to a suitable replacement before the retirement date. Requests to models past the retirement date will fail.
To help measure the performance of replacement models on your tasks, consider thorough testing of your applications with the new models well before the retirement date.
115 unchanged lines

Underlined words mark what moved within a rewritten line. Nothing here is interpreted — this is the difference between two captures, and the conclusion is yours.