MiniMax-M2.5
by IteraCompute · family minimax · listed Feb 2026RTW
Prior MiniMax coding model for agent workflows, office edits, and automation
Current rates USD per 1M tokens
Input$0.27
Output$1.03
Cache read$0.03
Cache write—
Against the market
On the record
- Model id
minimax/minimax-m2.5- Context window
- 205K tokens
- Max output
- 16K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-12
- Last updated
- 2026-02-12
- Provider docs
- iteracompute.com/docs.html
Back of the envelope
≈
Also listed at
- Tencent Coding Plan (China)free in · free out
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- SCNet Token Planfree in · free out
- Alibaba Coding Plan (China)free in · free out
- Alibaba Coding Planfree in · free out
- MiniMax Token Plan (minimax.io)free in · free out
- MiniMax Token Plan (minimax.cn)free in · free out
- Deep Infra$0.15 in · $1.15 out
- DInference$0.22 in · $0.88 out
- OpenRouter$0.27 in · $0.95 out
- Kilo Gateway$0.27 in · $0.95 out
- NanoGPT$0.295 in · $1.20 out
- DevPass (LLM Gateway)$0.30 in · $1.20 out
- Ofox$0.30 in · $1.20 out