// AI Platform Drift
Models API now reports server tool support per model
Claude Platform release notes · published 2026-10-07 23:06 UTC
WHAT CHANGEDThe Models API endpoints (GET /v1/models and GET /v1/models/{model_id}) added a capabilities.server_tools field on October 6, 2026. This field reports whether each model accepts web search and code execution tools. capabilities.server_tools.code_execution indicates server-side code execution support; the existing top-level capabilities.code_execution indicates whether code can call other tools in the request.
WHY IT MATTERSIf you dynamically select models or validate tool availability at runtime, your code may not distinguish between server-side code execution (the new field) and code-that-calls-tools (the existing field). Requests that assume all models support web search or code execution will fail when routed to models that do not.
WHAT TO DOGrep your codebase for capabilities.code_execution and confirm you are checking the correct field for your use case. If you offer web search or code execution, add a check against capabilities.server_tools.code_execution or capabilities.server_tools.web_search before sending those tools in a request.
Model-reported confidence 85% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## Claude Platform release notes — October 6, 2026 +https://platform.claude.com/docs/en/release-notes/overview#october-6-2026 +Tue, 06 Oct 2026 00:00:00 GMT + +We've added capabilities.server_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts the web search and code execution tools. To check whether a model accepts the code execution tool, read capabilities.server_tools.code_execution. The top-level capabilities.code_execution reports whether code can call your request's other tools. See Using the Models API.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.72, needed 0.45 |
|---|---|
| triage reasoning | New API field changes how developers query model capabilities; affects integration logic. |
| signals | new API capability field added · models endpoint behavior change · new model introspection surface · affects tool availability detection |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |