# MiniMax-M2.5-highspeed API prices

MiniMax-M2.5-highspeed (minimax) — 205k context, 131k max output.
8 metered per-token offers from 11 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.6 | $2.4 | $0.03 | 205k |
| LLM Gateway | $0.6 | $2.4 | $0.03 | 205k |
| Merge Gateway | $0.6 | $2.4 | $0.06 | 205k |
| MiniMax (minimax.io) | $0.6 | $2.4 | $0.06 | 205k |
| MiniMax (minimaxi.com) | $0.6 | $2.4 | $0.06 | 205k |
| NovitaAI | $0.6 | $2.4 | $0.03 | 205k |
| OrcaRouter | $0.6 | $2.4 | $0.03 | 205k |
| ZenMux | $0.6 | $4.8 | $0.06 | 205k |

## Summary

- Cheapest input: $0.6 per 1M tokens (DevPass (LLM Gateway))
- Cheapest output: $2.4 per 1M tokens (DevPass (LLM Gateway))
- First-party: $2.4 per 1M output tokens (MiniMax (minimax.io))
- Free offers: MiniMax Token Plan (minimaxi.com), MiniMax Token Plan (minimax.io)
- Subscription plans (not per-token): MiniMax Token Plan (minimaxi.com), MiniMax Token Plan (minimax.io)
- Released: 2026-02-13
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/minimax-m2-5-highspeed/
Full dataset: https://llmprice.gitlab.io/data/catalog.json