MiniMax M3.1 Flash Benchmarks, Pricing & Rankings
MiniMax · 2026-10-19 · Closed · Current
Snapshot 2026-10-19 · updated weekly
MiniMax M3.1 Flash ranks #13 of 44 on the AMR leaderboard.
MiniMax M3.1 Flash benchmark scores
MiniMax M3.1 Flash price, speed & context
Input price
$0.14
per 1M tokens
Output price
$0.56
per 1M tokens
Speed
170
tok/s
Context
1.0M
tokens
About MiniMax M3.1 Flash
MiniMax M3.1 Flash reached the MiniMax API on October 19 with open weights promised later. It posts 73.7% on DeepSWE v1.1 plus 61.7 on OSWorld V2 and 29.6 on Agents’ Last Exam, first among Chinese models on both computer-use benchmarks, at about $0.14/$0.56 per million tokens and 170+ tok/s median output.
Models around MiniMax M3.1 Flash in the rankings
More MiniMax models
MiniMax M3.1 Flash FAQ
Where does MiniMax M3.1 Flash rank?
MiniMax M3.1 Flash ranks #13 of 44 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 76.5. Its strongest dimension is AMR at 76.5.
How much does MiniMax M3.1 Flash cost?
MiniMax M3.1 Flash costs $0.14 per million input tokens and $0.56 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.46 per million tokens.
What is the MiniMax M3.1 Flash context window?
MiniMax M3.1 Flash supports a 1.0M token context window and generates at a median 170 output tokens per second. That context fits roughly 699 standard documents in a single prompt.
Is MiniMax M3.1 Flash open source?
No — MiniMax M3.1 Flash is a closed model available only through MiniMax’s official API and authorized cloud partners.
What is better than MiniMax M3.1 Flash?
DeepSeek V4.1 Flash 1017 ranks one place higher at #12 with an AMR score of 77.1. MiniMax M3.1 Flash still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.