Unverified50% confidenceDecision RuleExact time
On the Chat Completions endpoint, `reasoning_effort` accepts values from `minimal` to `max`, does not support `none`, and sending `none` returns a 400 error.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedThe max_tokens parameter is required in the Anthropic Messages protocol.61% similarUnverifiedExperiments found that the task_score under the shaped reward configuration was only 0.125, compared to 0.417 for the naive reward configuration, with an effect size of d=4.47.59% similarUnverifiedZero-shot Gemma 3 270M is nearly unusable on the grammar correction task, with an F0.5 of only 0.122, and 99.6% of correct sentences were altered.58% similarUnverifiedAcross three re-runs, only 4 responses in promptfoo had their pass/fail conclusion flip.58% similarUnverifiedv3.19.1 clarified at the API level the value constraints for the seed parameter in the Chat Completions interface (#3945).57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034238API
curl https://kongchang.com/api/v1/knowledge/claims/1034238MCP
get_claim(id=1034238)