CATCH #2176
DETECTED OCT 20, 2026 02:29 UTC
THE CATCHscore 6/10
EXHIBIT 2176 · URGENT
Oct 20, 2026 02:29 UTC
docs
https://platform.claude.com/docs/en/release-notes/api
Anthropic API changelog now reports `capabilities.thinking.types.between_tools` in the Models API, indicating if a model accepts `thinking: {type: "between_tools"}`.
READY TO POST:
anthropic's api changelog updated. `get /v1/models` and `get /v1/models/{model_id}` now show if a model supports `thinking: {type: "between_tools"}` to turn off up-front thinking.
looks like anthropic models api is getting more granular with thinking capabilities. you can now check if a model accepts `thinking: {type: "between_tools"}`.
EVIDENCE — the receipts
Anthropic API changelog changed: https://platform.claude.com/docs/en/release-notes/api
17 added lines
---
+++
@@ -55,2 +55,15 @@
+We've added
+capabilities.thinking.types.between_tools
+to the
+Models API
+.
+GET /v1/models
+and
+GET /v1/models/{model_id}
+now report whether each model accepts
+thinking: {type: "between_tools"}
+, which turns off up-front thinking. See
+Using the Models API
+.
The
@@ -159,3 +172,3 @@
tools
-, or earlier turns can also return a 400 error. On Amazon Bedrock, structured outputs aren't available for Claude Haiku 5.5. Adaptive thinking is on by default, so a response can begin with
+, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with
thinking
@@ -1186,3 +1199,3 @@
Workbench
-. You can export any data you want to keep from the banner and under your
+in the Console. You can export any data you want to keep from the banner and under your
Organizational Settings
@@ -2361,3 +2374,3 @@
-Console users with the Developer role can now access the
+In the Console, users with the Developer role can now access the
Cost
@@ -2590,3 +2603,3 @@
tool use
-in the
+in the Console
Workbench
caught by the 20-minute sweep ·
the live wire · all receipts