Expired50% confidenceFactExact time
Anthropic provides a thinking parameter control switch at the API level, as well as a budget_tokens parameter for setting the maximum number of tokens that the thinking process can consume.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Claude Fable 5是真的吗？揭秘AI套壳服务骗局套路
bilibiliAIGC技术流学院6/11/2026
Related Claims
UnverifiedMax Reasoning Effort is a feature that exposes the model's internal reasoning budget as a user-configurable parameter.75% similarUnverifiedOpenAI has introduced a 'Thinking Budget' mechanism in its o-series reasoning models, which can dynamically control the length of the internal reasoning chain.74% similarUnverifiedAnthropic 在 Claude 推理模型中引入了可调节的推理强度机制（Effort Level），控制模型在生成答案前花费在思维链上的计算预算73% similarUnverifiedReasoning budget refers to the upper limit on the number of intermediate reasoning tokens a chain-of-thought model is allowed to consume before generating a final answer; the higher the budget, the deeper the self-reflection and multi-step verification the model can perform.72% similarUnverified现代推理模型通常具备推理预算机制，为每次推理分配一定量的令牌配额67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/61622API
curl https://kongchang.com/api/v1/knowledge/claims/61622MCP
get_claim(id=61622)