MiniMax M3.1 Flash
NEWMiniMax · Open weights · Released Oct 19, 2026 · minimax/minimax-m3.1-flash
Best $0.10 in / $0.55 out via InferenceNet · fp4 · 1M ctx at this price (headline 1.05M)
1.05M contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · PRICES 7 MINUTES AGO · SPEED JUST NOW
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 InferenceNet | $0.10 | $0.55 | $0.01 | 1M | fp4 | — | — | 100.0% |
 Minimax1ST PARTY | $0.15 | $0.60 | $0.015 | 1.05M | — | — | — | 99.7% |
 Parasail | $0.15 | $0.60 | $0.015 | 1.05M | fp8 | ✕ | ✕ | 100.0% |
 Together | $0.15 | $0.60 | $0.015 | 1.05M | — | — | — | 100.0% |
 Wafer | $0.15 | $0.60 | $0.015 | 1.05M | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured just now
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.10 / $0.55
per MTok in / out
CACHE READ $0.01
Recent changesRSS ↗
Oct 23, 2026price increased · output0.5 → 0.55
Oct 23, 2026model added
About
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
Specifications
Context window1,048,576
Max output524,288
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedOct 19, 2026
TokenizerOther
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/minimax/minimax-m3.1-flash)Sources
OpenRouter API7 minutes ago
AGGREGATORHugging Face7 minutes ago
COMMUNITYModelIndex benchmarksjust now
MEASUREDVerified 7 minutes ago · list prices, not negotiated rates.