BuildLearnCommunity ModelsCheapestLong-contextOpen sourceImage modelsTrending How we score API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › minimax › MiniMax: MiniMax M3.1 Flash

MiniMax: MiniMax M3.1 Flash — pricing & benchmarks

By minimax · Updated 2026-11-01 · Open weights · custom licenseReads imageslong-context / RAGreads images / documentscheap high-volumestep-by-step reasoningopen weights / self-hostable

MiniMax: MiniMax M3.1 Flash costs $0.15 per 1M input tokens and $0.6 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable, and is available through one OpenAI-compatible Appmo API key.
$0.15Input / 1M
$0.6Output / 1M
1MContext
22.9KHF downloads (30d)
521HF likes
68Buzz (0-100)

What MiniMax: MiniMax M3.1 Flash is used for

MiniMax: MiniMax M3.1 Flash is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable. Access it through one Appmo API key alongside 444 other models — Appmo's optimizer can route to it automatically when it is the best value for a request. Weights: huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash.

What people are saying (last 30 days)

Not enough posts yet to judge community sentiment. 12 Hacker News stories (550 points) · 41 new GitHub repos mentioning it. How we measure this.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"minimax/minimax-m3.1-flash","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does MiniMax: MiniMax M3.1 Flash cost?
MiniMax: MiniMax M3.1 Flash costs $0.15 per 1M input tokens and $0.6 per 1M output tokens ($0.262 blended), as of 2026-11-01. Prices are expected to fall as competition increases.

What is MiniMax: MiniMax M3.1 Flash best for?
MiniMax: MiniMax M3.1 Flash is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable.

How do I use MiniMax: MiniMax M3.1 Flash?
Send requests to Appmo's OpenAI-compatible endpoint with model id "minimax/minimax-m3.1-flash" and one API key — no separate provider account needed.

Is MiniMax: MiniMax M3.1 Flash open source?
Yes — its weights are public on Hugging Face (MiniMaxAI/MiniMax-M3.1-Flash) under a custom license; check the license terms before commercial use.

Can MiniMax: MiniMax M3.1 Flash create images?
No. MiniMax: MiniMax M3.1 Flash can read and understand images, but it only writes text.