Unverified50% confidenceFactExact time
Manual Extended Thinking (thinking.type: "enabled" plus budget_tokens) is already marked as outdated on Opus 4.6 and Sonnet 4.6, is not accepted at all by the new models, and is now controlled by the effort parameter, with a default of medium.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedDevelopers can control Gemini 4 Argon's thinking level via the reasoning parameter in the AI SDK or the reasoning_effort parameter in the Chat Completions interface.59% similarUnverifiedToo many tools cause model selection confusion; the current mainstream direction is to provide a small number of tools and let the model iteratively leverage them on its own, or let the model dynamically design tools based on the task (especially by writing scripts).57% similarUnverifiedSkillOpt does not fine-tune the underlying model weights; instead, it establishes an iteratively optimizable closed loop around the definition, invocation, and performance of skills.57% similarUnverifiedThe SDK introduces a between_tools thinking type, allowing the model to reason between consecutive tool calls.56% similarUnverifiedEffort setting is an adjustment knob introduced by Anthropic in the extended thinking feature, allowing users to specify how much compute the model invests in internal reasoning before generating a response.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025654API
curl https://kongchang.com/api/v1/knowledge/claims/1025654MCP
get_claim(id=1025654)