On Claude Opus 5.5, thinking can't be disabled: thinking: {"type": "disabled"} and thinking: {"type":…

Tuesday, 22 September 2026

AI summary

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

Claude Opus 5.5 introduces changes to thinking controls and tool management, requiring new parameters and toolsets.

Thinking cannot be disabled; use effort parameter instead.
Fast mode is now available on the Claude API.
Tools can be defined in mid-conversation system messages.
New tool management features allow for dynamic updates without prompt cache invalidation.

Why it matters: Developers using Claude Opus 5.5 should adapt to new tool and thinking management requirements.

On Claude Opus 5.5, thinking can't be disabled: thinking: {"type": "disabled"} and thinking: {"type": "enabled",...} return a 400 error. Omit the thinking field and control thinking depth with the effort parameter. tool_choice types any and tool also return a 400 error, as on Claude Fable 5.1; use auto with strict tool use. On the Claude API and Google Cloud, computer use on this model requires the computer_toolset_20260801 toolset and the earlier computer_20251124 tool returns a 400 error; on Amazon Bedrock, computer_20251124 keeps working. See the migration guide.
Fast mode (research preview) is available for Claude Opus 5.5 on the Claude API.
Tools can now be defined inside a mid-conversation system message, in beta on the Claude API with the inline-tools-2026-09-15 beta header. A tool_addition block can carry the tool's full definition (tool: {"type": "tool_definition", "definition": {...}}), so you can add a tool, change its schema, or move a server tool to a newer version without editing tools or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's mcp-client-2026-09-15 beta header as well, the definition can be an MCP toolset, and a response records each server's fetched tool list in an mcp_tool_listing block, which pins that list when you send it back.

Full release notes3 changes

On Claude Opus 5.5, thinking can't be disabled: thinking: {"type": "disabled"} and thinking: {"type": "enabled",...} return a 400 error. Omit the thinking field and control thinking depth with the effort parameter. tool_choice types any and tool also return a 400 error, as on Claude Fable 5.1; use auto with strict tool use. On the Claude API and Google Cloud, computer use on this model requires the computer_toolset_20260801 toolset and the earlier computer_20251124 tool returns a 400 error; on Amazon Bedrock, computer_20251124 keeps working. See the migration guide.
Fast mode (research preview) is available for Claude Opus 5.5 on the Claude API.
Tools can now be defined inside a mid-conversation system message, in beta on the Claude API with the inline-tools-2026-09-15 beta header. A tool_addition block can carry the tool's full definition (tool: {"type": "tool_definition", "definition": {...}}), so you can add a tool, change its schema, or move a server tool to a newer version without editing tools or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's mcp-client-2026-09-15 beta header as well, the definition can be an MCP toolset, and a response records each server's fetched tool list in an mcp_tool_listing block, which pins that list when you send it back.