Unverified50% confidenceDecision RuleExact time
Fireworks now sends the top-level reasoning value directly instead of uniformly capping it at 'high', but retains exceptions for model families known to reject specific values: GPT-OSS, GLM-5.3 and Muse Spark reject 'none', while Nemotron and Inkling reject 'minimal'.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
UnverifiedLlama、Mistral、Phi等小模型的崛起证明并非所有场景都需要GPT-4级别的能力60% similarUnverifiedGPT-6 Astra and GPT-6.1 Sol do not support disabling reasoning, and receiving reasoning.effort: "none" causes them to return a 400 error.59% similarUnverifiedThe reasoningEffortUpdate: 'none' capability is designed for GPT-6 Sol and Luna models and can be used in request-level options and localized system messages.59% similarUnverifiedWhen looking only at LLM judgment (scored using GPT-5.5), the evaluator tended to dislike Grok, favor Claude Opus and Sonnet, and dislike GPT-5.6.57% similarUnverifiedModels affected by the 'none' downgrade logic include the GPT-6 series, xAI grok-4.5 and later versions, GPT-OSS on Groq, Kimi K3, Perplexity, QuiverAI, OpenAI gpt-oss on Bedrock, and Gemini 2.5 Pro.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112375API
curl https://kongchang.com/api/v1/knowledge/claims/1112375MCP
get_claim(id=1112375)