The board shows this model's cheapest measured offer ($0.338/1M); the smaller figure under it is the mean of the 20 offers listed below ($0.523/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Inceptron (fp8) | OpenRouter | $0.150 | $0.900 | 516ms | 62 | 100% | API-measured |
| DigitalOcean | OpenRouter | $0.225 | $0.900 | 567ms | 59 | 100% | API-measured |
| Venice | OpenRouter | $0.270 | $0.950 | 1137ms | 41 | 81.4% | API-measured |
| StreamLake | OpenRouter | $0.270 | $1.08 | 611ms | 111 | 100% | API-measured |
| requesty | Requesty | $0.280 | $1.10 | — | — | — | API-measured |
| Phala | OpenRouter | $0.200 | $1.38 | — | — | — | API-measured |
| openrouter | Pricebook (LiteLLM) | $0.300 | $1.10 | — | — | — | Official list |
| AtlasCloud (fp8) | OpenRouter | $0.295 | $1.20 | 1227ms | 59 | 100% | API-measured |
| baseten | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| minimax | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| wandb | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| tensormesh | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| novita | HuggingFace Router | $0.300 | $1.20 | 1012ms | 59 | — | API-measured |
| novita-ai | Novita AI | $0.300 | $1.20 | — | — | — | API-measured |
| burncloud | burncloud | $0.300 | $1.20 | — | — | — | API-measured |
| Friendli | OpenRouter | $0.300 | $1.20 | 491ms | 81 | 100% | API-measured |
| Minimax (fp8) | OpenRouter | $0.300 | $1.20 | 1049ms | 53 | 100% | API-measured |
| Novita (fp8) | OpenRouter | $0.300 | $1.20 | 1055ms | 43 | 100% | API-measured |
| SiliconFlow (fp8) | OpenRouter | $0.300 | $1.20 | 1029ms | 43 | 100% | API-measured |
| Minimax (highspeed) | OpenRouter | $0.600 | $2.40 | 1031ms | 48 | 100% | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.21 → $0.21 → $0.21 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375 → $0.3375
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/minimax-m2.5.json. Free reuse requires attribution to tkx.org.
About
MiniMax M2.5 is a machine-learning system designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces and is listed under the organization tag "minimax."
AI-generated summary from public information — is this yours?
FAQ
How much does MiniMax M2.5 cost?
Cheapest measured offer right now: $0.15/1M input, $0.9/1M output via Inceptron (fp8) — across 16 tracked providers, refreshed hourly.
Who serves MiniMax M2.5?
16 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of MiniMax M2.5 going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.