Unverified50% confidenceFactExact time
For the same MiniMax M3.1 Flash model, the effort field is named reasoning_effort, output_config.effort, and reasoning.effort under the OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses protocols respectively; all three accept the five values low/medium/high/xhigh/max, and all default to max.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedOpenCode (issue #54801, reproduced on v2.0.27) cannot parse effort variants for M3.1 Flash; the workaround is to declare five variants in opencode.json and set reasoning_effort for each separately (without none).69% similarUnverifiedIn the OpenAI Chat Completions API, max_tokens is an early field used to limit the total number of tokens in the generated content; OpenAI introduced max_completion_tokens in the o1 series and later reasoning models to constrain the token upper limit of the entire completion, and gradually recommends that new models use the latter.67% similarUnverifiedOpenAI-compatible endpoints follow the OpenAI Chat Completions API specification, but 'compatible' does not mean 'behaviorally identical,' and vendors may differ in their implementations of token counting rules and max_tokens semantics.63% similarUnverifiedNanoGPT supports routing complex reasoning tasks to openai/o3-pro and simple tasks to different models such as openai/gpt-6.1-mini, achieving separation of fast and slow models to control costs.63% similarUnverifiedThe OpenAI API measures RPM and combined TPM by model series, and on each request checks whether the estimated prompt tokens plus the requested max_tokens fall within the remaining TPM pool.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067177API
curl https://kongchang.com/api/v1/knowledge/claims/1067177MCP
get_claim(id=1067177)