CheapestCoding Long-contextBest value Get an 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

MiniMax: MiniMax M3 — pricing & benchmarks

By minimax · Updated 2026-07-24 · long-context / RAGvision / documentsstep-by-step reasoning

MiniMax: MiniMax M3 costs $0.3 per 1M input tokens and $1.2 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, vision / documents, step-by-step reasoning, and is available through one OpenAI-compatible Appmo API key.
$0.3Input / 1M
$1.2Output / 1M
1MContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What MiniMax: MiniMax M3 is used for

MiniMax: MiniMax M3 is best suited for long-context / RAG, vision / documents, step-by-step reasoning. Access it through one Appmo API key alongside 390 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

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","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does MiniMax: MiniMax M3 cost?
MiniMax: MiniMax M3 costs $0.3 per 1M input tokens and $1.2 per 1M output tokens ($0.525 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is MiniMax: MiniMax M3 best for?
MiniMax: MiniMax M3 is best suited for long-context / RAG, vision / documents, step-by-step reasoning.

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