TRULYSOVEREIGN AI · RADAR

Claude Opus 5.5 released with breaking API changes, September 22, 2026

Claude Platform release notes · published 2026-09-23 21:12 UTC
ACTION NEEDED MIGRATE MODELAPIPRICINGDEPRECATION
WHAT CHANGEDClaude Opus 5.5 (claude-opus-5-5) launched with 1M token context, 128k max output, $4/$20 per MTok (down from Opus 5's $5/$25). On this model, thinking: {"type": "disabled"} and thinking: {"type": "enabled"} now return 400 errors; tool_choice types "any" and "tool" also return 400. On Claude API and Google Cloud, computer_20251124 tool returns 400 and requires computer_toolset_20260801 instead. Amazon Bedrock still accepts computer_20251124.
WHY IT MATTERSExisting code that sets thinking parameters or uses tool_choice "any"/"tool" will break with 400 errors if you switch to Opus 5.5. Code using computer_20251124 on Claude API or Google Cloud will also break. If you have hardcoded model names or auto-upgrade logic, you may hit these errors without intending to migrate.
WHAT TO DOGrep your codebase for "thinking": {"type" and tool_choice references. If found, pin to claude-opus-5 in model selection logic until you can remove those parameters and migrate computer use toolsets per the migration guide. If you do not use these features, verify your model selection does not auto-upgrade, then test Opus 5.5 in staging to confirm 20% cost savings apply to your workload.
CONFIDENCE 95% Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## Claude Platform release notes — September 22, 2026
+https://platform.claude.com/docs/en/release-notes/overview#september-22-2026
+Tue, 22 Sep 2026 00:00:00 GMT
+
+We've launched Claude Opus 5.5 (claude-opus-5-5), a model for long-running agentic coding and knowledge work. It has a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking, at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25). Claude Opus 5.5 is available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud, and Claude in Microsoft Foundry. See What's new in Claude Opus 5.5 for capabilities, API changes, and migration guidance.
+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.
HOW IT WAS JUDGED
triage verdictMATERIAL at 0.98, needed 0.45
triage reasoningNew model release with pricing, breaking API changes, and feature availability across platforms.
signalsnew model released (Claude Opus 5.5) · pricing change (Opus 5.5: $4/$20 vs Opus 5: $5/$25) · breaking API changes (thinking parameter disabled, tool_choice restrictions) · context window specification (1M tokens) · max output tokens specified (128k) · new feature availability (fast mode, inline tools beta) · toolset deprecation (computer_20251124 returns 400 on Claude API) · multi-platform availability statement
suppression
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)