{"version":"2.1.287","anchor":"claude-5-sonnet-model-entry-drops-native-1m-3p-flags","canonical_anchor":"claude-5-sonnet-model-entry-drops-native-1m-3p-flags","heading":"Sonnet model entries no longer mark Bedrock, Vertex and Foundry as natively 1M","tier":"notice","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287\/e\/claude-5-sonnet-model-entry-drops-native-1m-3p-flags","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287","markdown":"### Sonnet model entries no longer mark Bedrock, Vertex and Foundry as natively 1M\n\nTwo Sonnet model entries no longer flag Bedrock, Vertex and Foundry as supporting the 1M-token context window natively\n\n**Unclear.** It is not clear how Claude Code treats a model with no native 1M setting for third-party providers.\n\n**What**\n\nClaude Code keeps a built-in list of models with details about each one. Two Sonnet entries in that list have changed: the one that falls back to `claude-sonnet-4-6`, and the one that falls back to `claude-sonnet-5` on third-party providers. Third-party providers are the cloud services that can host Claude models: Amazon Bedrock, Google Vertex AI and Microsoft Foundry.\n\nBoth entries used to say that Bedrock, Vertex and Foundry natively support a context window of 1 million tokens. That setting has been removed. The context window is how much text the model can consider at once. Both entries still list a 1-million-token context window, native 1M support and support for the 1M beta.\n\n**Why**\n\nIf you use these Sonnet models through Bedrock, Vertex or Foundry, Claude Code may now handle their large context window differently.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 4\/5"}