Partially Verified65% confidenceFactExact time
Maximum output tokens: MiniMax M3.1 Flash is 512K, DeepSeek V4.1 Flash 1017 is 384K, and Claude Haiku 5.5 is 128K.
3
Sources
65%
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 uses a MoE architecture with approximately 428B total parameters and approximately 23B activated per token.78% 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 524,288.77% similarUnverifiedOn the DeepSWE coding leaderboard, Beam scored 44.4 points, ranking last, below DeepSeek V4.1 Flash's 74.2 points, Kimi K3's approximately 68 points, GLM's approximately 61 points, and Qwen3 Max's approximately 51 points.76% similarUnverifiedCache read price (per million tokens): MiniMax M3.1 Flash is $0.0165, DeepSeek V4.1 Flash 1017 is $0.0031, and Claude Haiku 5.5 is $0.01.76% similarUnverifiedThe Qwen3.8 Flash Next (Q3 quantized version) weights are approximately 84 GB and run on an AMD 7900XTX 24 GB GPU with an average decoding output speed of approximately 90 tokens/s.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067155API
curl https://kongchang.com/api/v1/knowledge/claims/1067155MCP
get_claim(id=1067155)