MiniMax M3.1 Flash
by MiniMax
Prices last updated November 22, 2026
MiniMax M3.1 Flash (October 2026) — a low-cost open-weight MoE (about 428B, 23B active) for agents, coding and computer use, with a 1M-token context window and image and video input.
Price Comparison
Compare pricing across 11 providers serving MiniMax M3.1 Flash
| Provider | Input $/1M | Output $/1M | Context | Speed | TTFT | Status |
|---|---|---|---|---|---|---|
OpenRouter | $0.135 ● | $0.540 | 1.0M | — | — | Live |
Novita AI | $0.150 | $0.600 | 1M | — | — | Live |
Nebius | $0.150 | $0.600 | 1.0M | — | — | Live |
WaveSpeed AI | $0.150 | $0.600 | 1.0M | — | — | Live |
Infron | $0.150 | $0.600 | 1M | — | — | Live |
Together AI | $0.150 | $0.600 | 1.0M | — | — | Live |
MiniMax | $0.150 | $0.600 | 1.0M | — | — | Live |
| KE Keln | $0.150 | $0.600 | — | — | — | Live |
Token Harbor | $0.150 | $0.600 | 1M | — | — | Live |
Venice AI | $0.188 | $0.750 | 1M | — | — | Live |
Sambanova | $0.300 | $1.20 | 1.0M | — | — | Live |
Benchmarks
Independent results for MiniMax M3.1 Flash, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.
| Benchmark | Score | Rank | As tested |
|---|---|---|---|
| Coding | |||
Code Arena (WebDev)LMArena Human votes on web apps the models build from a prompt. | 1,581±9 5,996 votes | #49 of 161 | MiniMax-M3.1-Flash Nov 2026 |
LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).
Rank is among all models the source ranks, including ones we don't list.