MiniMax

MiniMax M3.1 Flash

Launched 2026-10-19 · Listed on OpenRouter 2026-10-19

Prices updated . Benchmarks updated .

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,...

You send / 1M

$0.150

tokens in

It replies / 1M

$0.600

tokens out

Context

1M

tokens it can read at once

Typical request

$0.0005

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Arena Elo (webdev)1,582Independent2026-10-28LMArena

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
Inferact vLLM · nvfp4$0.075$0.300100%Read
Wafer · nvfp4$0.135$0.540100%Read
Makora · fp4$0.150$0.600100%n/a
Fireworks$0.150$0.60099%Read
InferenceNet · fp4$0.150$0.600100%Read
DigitalOcean$0.150$0.600100%Read
Nebius · fp4$0.150$0.60099%Read
SambaNova$0.150$0.60087%Read
ModelRun · fp4$0.150$0.600100%Read
Parasail · fp8$0.150$0.600100%Read
InferenceNet · fp4$0.150$0.60099%Read
Together$0.150$0.600100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image, video
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 524K tokens
  • Repeated text is billed at $0.015 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with MiniMax M3.1 Flash

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.