MiniMax M2.5 Highspeed
by routing.run · family minimax · listed Feb 2026TW
High-speed MiniMax model for low-latency coding and agent workflows
Current rates USD per 1M tokens
Input$0.193
Output$1.24
Cache read$0.06
Cache write$0.375
Against the market
On the record
- Model id
route/minimax-m2.5-highspeed- Context window
- 100K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-13
- Last updated
- 2026-02-13
- Provider docs
- docs.routing.run/api-reference/models
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
- Vercel AI Gateway$0.60 in · $2.40 out
- NovitaAI$0.60 in · $2.40 out
- Merge Gateway$0.60 in · $2.40 out
- OrcaRouter$0.60 in · $2.40 out
- LLM Gateway$0.60 in · $2.40 out
- MiniMax (minimaxi.com)$0.60 in · $2.40 out
- MiniMax (minimax.io)$0.60 in · $2.40 out
- Qiniu— in · — out