AI summary
Written by AI from the official notes. Check them for exact details.Claude Sonnet 5 has been launched with a larger token capacity and some behavioral changes.
- Supports 1M token context window and 128k max output tokens.
- Adaptive thinking is now on by default.
- Manual extended thinking feature removed, returns 400 error.
- Non-default sampling parameters return a 400 error.
- New tokenizer increases token output by approximately 30%.
Why it matters: Users of Claude models should review changes for migration and updated usage guidelines.
Full release notes
We've launched Claude Sonnet 5 (claude-sonnet-5), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a 1M token context window, 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except Priority Tier, which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: adaptive thinking is now on by default; manual extended thinking (thinking: {type: "enabled", budget_tokens: N}) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See What's new in Claude Sonnet 5 for details and migration guidance. For behavioral differences and model-specific prompting patterns, see Prompting Claude Sonnet 5.