Unverified50% confidenceFactExact time
MiniMax M3.1 Flash cannot disable thinking: passing thinking: {"type": "disabled"} or setting effort to none returns HTTP 400 with the error message model "MiniMax-M3.1-Flash" requires adaptive thinking.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedMiniMax M3.1 Flash defaults to the max setting when the effort field is not passed in the request, and the model always performs thinking.77% similarUnverifiedOn October 19, MiniMax M2.5/M2.7 were closed to new users and plan requests were routed to M3.1 Flash; on the same day `minimax-m3.1-flash` launched on AIHubMix on a pay-per-token basis.70% similarUnverifiedFlashMLA's prefill throughput for the sparse attention operator on the Ascend 950 reaches 410 TFLOPS (95% of the hardware's theoretical peak), and decode reaches 360 TFLOPS (83%), both figures as published by DeepSeek itself with no third-party measurements.68% similarUnverifiedMiniMax M3.1 Flash's thinking tokens count toward the max_tokens limit, so reusing the 4K or 8K caps from the M2.x era may cause truncation with finish_reason: "length"; MiniMax recommends raising max_tokens to 131,072, with an upper limit of 524,288.67% similarUnverifiedMaximum output tokens: MiniMax M3.1 Flash is 512K, DeepSeek V4.1 Flash 1017 is 384K, and Claude Haiku 5.5 is 128K.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067176API
curl https://kongchang.com/api/v1/knowledge/claims/1067176MCP
get_claim(id=1067176)