# MiniMax: MiniMax M2.7 — price and measured latency by host

Updated July 25, 2026. Served by 13 providers; 7 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-07-25 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| deepinfra | $0.250 | $1.000 | 196,608 | 226 ms | us-central | 99.9% |
| novita | $0.270 | $1.080 | 204,800 | 71 ms | us-central | 100% |
| minimax | $0.300 | $1.200 | 204,800 | 198 ms | ap-tokyo | 100% |
| fireworks | $0.300 | $1.200 | 196,608 | 17 ms | ap-tokyo | 100% |
| together | $0.300 | $1.200 | 196,608 | 111 ms | us-central | 100% |
| sambanova | $0.300 | $1.500 | 196,608 | 24 ms | ap-tokyo | 99.8% |
| groq | $0.600 | $1.800 | 196,608 | 108 ms | us-central | 100% |

Source: https://llmlatency.dev/model/minimax-minimax-m2.7 · CC BY 4.0