MiniMax-M2.7
by Nvidia · family minimax · listed Mar 2026RTW
MiniMax model for chat, coding, office work, and agentic tasks
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
minimaxai/minimax-m2.7- Context window
- 205K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-03-18
- Last updated
- 2026-04-11
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- MiniMax Token Plan (minimax.io)free in · free out
- MiniMax Token Plan (minimaxi.com)free in · free out
- OpenRouter$0.18 in · $0.72 out
- Deep Infra$0.25 in · $1.00 out
- Alibaba (China)$0.30 in · $1.20 out
- Vercel AI Gateway$0.30 in · $1.20 out
- Hugging Face$0.30 in · $1.20 out
- NovitaAI$0.30 in · $1.20 out
- Vultr$0.30 in · $1.20 out
- 302.AI$0.30 in · $1.20 out
- OpenCode Go$0.30 in · $1.20 out
- Merge Gateway$0.30 in · $1.20 out
- OrcaRouter$0.30 in · $1.20 out
- LLM Gateway$0.30 in · $1.20 out
- OpenCode Zen$0.30 in · $1.20 out