The board shows this model's cheapest measured offer ($0.420/1M); the smaller figure under it is the mean of the 18 offers listed below ($0.516/1M). Add those up and divide — it matches. 24h token volume (253B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| GMICloud (fp8) | OpenRouter | $0.240 | $0.960 | 2076ms | 22 | 99.8% | API-measured |
| 0g-teetls | 0G Router | $0.270 | $1.08 | — | — | — | API-measured |
| fireworks_ai | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| minimax | Pricebook (LiteLLM) | $0.300 | $1.20 | — | — | — | Official list |
| novita | HuggingFace Router | $0.300 | $1.20 | 982ms | 99 | — | API-measured |
| together | HuggingFace Router | $0.300 | $1.20 | 1291ms | 15 | — | API-measured |
| fireworks-ai | HuggingFace Router | $0.300 | $1.20 | 708ms | 108 | — | API-measured |
| deepinfra | HuggingFace Router | $0.300 | $1.20 | 385ms | 33 | — | API-measured |
| novita-ai | Novita AI | $0.300 | $1.20 | — | — | — | API-measured |
| requesty | Requesty | $0.300 | $1.20 | — | — | — | API-measured |
| Novita (fp8) | OpenRouter | $0.300 | $1.20 | 1747ms | 55 | 99.7% | API-measured |
| Venice (fp8) | OpenRouter | $0.300 | $1.20 | 1096ms | 148 | 99.6% | API-measured |
| Minimax (fp8) | OpenRouter | $0.300 | $1.20 | 1088ms | 71 | 97.9% | API-measured |
| AtlasCloud (fp8) | OpenRouter | $0.300 | $1.20 | 1651ms | 19 | 99.8% | API-measured |
| Together | OpenRouter | $0.300 | $1.20 | 824ms | 42 | 99.8% | API-measured |
| Morph | OpenRouter | $0.300 | $1.20 | 2294ms | 21 | 99.9% | API-measured |
| DeepInfra (fp8) | OpenRouter | $0.300 | $1.20 | 2480ms | 4 | 99.9% | API-measured |
| Parasail (fp8) | OpenRouter | $0.300 | $1.20 | 1325ms | 62 | 90.8% | API-measured |
Volume trend
Last 30 days: 529B → 253B (-52%); range 215B–680B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
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-m3.json. Free reuse requires attribution to tkx.org.
About
Minimax-M3 is an AI model that specializes in decision-making and optimization tasks. It is served by multiple inference providers on AI model marketplaces, making it accessible for various applications that require strategic planning and risk management.
AI-generated summary from public information — is this yours?
FAQ
How much does MiniMax M3 cost?
Cheapest measured offer right now: $0.24/1M input, $0.96/1M output via GMICloud (fp8) — across 12 tracked providers, refreshed hourly.
Who serves MiniMax M3?
12 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is MiniMax M3 used?
MiniMax M3 routed 253B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.