Anthropic’s API now shows whether a model has thinking turned off via a new capabilities flag.
NoteBy OossaPublished by Oossa: 1 min read
Event date:
Anthropic updated its API on October 5, 2026. The Models API now includes a new field called capabilities.thinking.types.disabled. When you call GET /v1/models or GET /v1/models/{model_id}, the response tells you if a model has thinking turned off (type: "disabled"). This lets developers see at a glance which models can use the thinking feature.
Developers can now programmatically avoid models that have thinking disabled, preventing unexpected behavior in applications.
Tools & agents
Morgan Stanley, JPMorgan, Bank of America, Wells Fargo and others are stopping AI tools that log in with user credentials.
Tools & agents
Agent Compute Engine already powers Gemini and is expected to enter preview in the coming months. Google says it can pause idle agents to save capacity.
Tools & agents
Rerank 5 has a 32K context window and passage-level context features. The reported Pro price is $0.05 per million tokens.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
