MiniMax M3
by NanoGPT · listed Jun 2026TV
MiniMax multimodal coding model for long-context reasoning and agent tasks
Current rates USD per 1M tokens
Input$0.30
Output$1.20
Cache read$0.06
Cache write—
Against the market
On the record
- Model id
minimax/minimax-m3- Context window
- 512K tokens
- Max output
- 80K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-06-01
- Last updated
- 2026-06-01
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- MiniMax Token Plan (minimax.io)free in · free out
- Kenarifree in · free out
- Nvidiafree in · free out
- MiniMax Token Plan (minimaxi.com)free in · free out
- Lilac$0.28 in · $1.10 out
- Vercel AI Gateway$0.30 in · $1.20 out
- Hugging Face$0.30 in · $1.20 out
- Fireworks AI$0.30 in · $1.20 out
- OpenCode Go$0.30 in · $1.20 out
- Deep Infra$0.30 in · $1.20 out
- OpenCode Zen$0.30 in · $1.20 out
- MiniMax (minimaxi.com)$0.30 in · $1.20 out
- Together AI$0.30 in · $1.20 out
- OpenRouter$0.30 in · $1.20 out
- MiniMax (minimax.io)$0.30 in · $1.20 out