CATCH #1881
DETECTED OCT 6, 2026 21:20 UTC
THE CATCHscore 5/10
EXHIBIT 1881
Oct 6, 2026 21:20 UTC
docs
https://platform.claude.com/docs/en/release-notes/api
Anthropic's Models API now reports a new `capabilities.thinking.types.disabled` field, indicating if a model supports turning off 'thinking' with `thinking: {type: "disabled"}`.
READY TO POST:
anthropic's api changelog got an update today – looks like the models api now tells you if a model can disable its 'thinking' capability. interesting control!
new anthropic docs suggest the models api will soon expose whether you can turn off model 'thinking' via `thinking: {type: "disabled"}`. subtle, but could be useful for specific use cases.
EVIDENCE — the receipts
Anthropic API changelog changed: https://platform.claude.com/docs/en/release-notes/api
19 added lines
---
+++
@@ -53,2 +53,17 @@
repository.
+October 5, 2026
+
+We've added
+capabilities.thinking.types.disabled
+to the
+Models API
+.
+GET /v1/models
+and
+GET /v1/models/{model_id}
+now report whether each model accepts
+thinking: {type: "disabled"}
+, which turns thinking off. See
+Using the Models API
+.
October 1, 2026
@@ -693,3 +708,5 @@
configs
-entries become per-tool types. See
+entries become
+per-tool types
+. See
Restrict web search and web fetch domains
@@ -2478,2 +2495,3 @@
+October 5, 2026
October 1, 2026
caught by the 20-minute sweep ·
the live wire · all receipts