Unverified50% confidenceFactExact time
OpenAI的o1系列模型的reasoning tokens对用户不可见
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/12/2026
First Seen
Valid until: 11/10/2026
Sources
Related Claims
UnverifiedThe OpenAI o1 series uses implicit CoT (thinking tokens), where the reasoning process is invisible to users but still consumes computational resources.80% similarUnverifiedThe Codex APP's reasoning levels correspond to the reasoning tokens mechanism in OpenAI's o-series models.76% similarUnverifiedOpenAI's o3/o4-mini series reasoning models have a context window of 128K–200K tokens.70% similarUnverifiedThe reasoning field in run.messages (the large model's reasoning process) is currently only supported by OpenAI O-series models.69% similarUnverifiedOpenAI's o1 has reasoning capabilities but does not disclose the reasoning chain, with the official explanation citing safety considerations.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/735420API
curl https://kongchang.com/api/v1/knowledge/claims/735420MCP
get_claim(id=735420)