Skip to content
Back

AnthropicClaude API

Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways

AI summary

Written by AI from the official notes. Check them for exact details.

Claude Sonnet 5.5 introduces compatibility issues with code from Claude Sonnet 5, affecting tool usage and thinking blocks.

  • Code from Claude Sonnet 5 may break on Claude Sonnet 5.5.
  • Use thinking: {"type": "between_tools"} to disable up-front thinking.
  • Forced tool use returns a 400 error.
  • Thinking blocks are account-specific in Claude Sonnet 5.5.
  • Earlier model blocks are unaffected.

Why it matters: Developers using Claude Sonnet 5 should review changes to ensure compatibility with Claude Sonnet 5.5.

Official notes on platform.claude.com

Full release notes2 changes

  • Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send thinking: {"type": "between_tools"} instead of "disabled", at high effort or below. Forced tool use (tool_choice types any and tool) returns a 400 error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, the earlier computer_20251124 computer use tool isn’t accepted. The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors. See What’s new in Claude Sonnet 5.5 for each change and the Claude Sonnet 5.5 migration guide for before-and-after requests. For model-specific prompting patterns, see Prompting Claude Sonnet 5.5.
  • Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. Blocks from earlier models aren’t affected. See Preserved thinking.