MiniMax API pricing
Live API prices for every MiniMax model SF·SIX tracks: per 1M tokens at the standard tier from the cheapest provider, or per image, second or character in the provider’s own unit.
MiniMax has 63 models with live API prices on SF·SIX, 8 models priced per 1M tokens and 55 models in native units (per image, second or character). The cheapest is MiniMax M2.7 at $0.21 per 1M input and $0.84 per 1M output tokens, via GMI Cloud (fp8). The most used on OpenRouter is MiniMax M3 (210.13B tokens on 2026-10-16).
- Models with live prices
- 63 (8 per token, 55 per native unit)
- Cheapest language model
- MiniMax M2.7$0.21 / $0.84 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- MiniMax M3210.13B tokens
- Newest model
- H3 Max Relight2026-10-07
- Providers serving these models
- 18
MiniMax token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Blended 3:1 | Cheapest standard provider | Providers | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|---|
| MiniMax M3 | $0.23 | $0.96 | $0.4125 | CoreWeavefp4 | 13 | 1,048,576 | 210.13B |
| MiniMax M2.5 | $0.27 | $0.95 | $0.44 | Venice AI | 8 | 204,800 | Not in named rows |
| MiniMax M2.7 | $0.21 | $0.84 | $0.3675 | GMI Cloudfp8 | 5 | 204,800 | Not in named rows |
| MiniMax M2 | $0.255 | $1.02 | $0.4463 | MiniMaxfp8 | 2 | 204,800 | Not in named rows |
| MiniMax M1 | $0.40 | $2.20 | $0.85 | MiniMax | 2 | 1,000,000 | Not in named rows |
| MiniMax M2.1 | $0.30 | $1.20 | $0.525 | MiniMaxfp8 | 1 | 204,800 | Not in named rows |
| MiniMax-01 | $0.20 | $1.10 | $0.425 | MiniMax | 1 | 1,000,192 | Not in named rows |
| MiniMax M2-her | $0.30 | $1.20 | $0.525 | OpenRouter (auto-routed) | 0 | 65,536 | Not in named rows |
Each model’s headline price: the cheapest qualifying provider at the standard tier in the default region. Most widely served first.
MiniMax prices in native units
Image, video, audio and other endpoints priced in the provider’s own unit; never converted with assumptions. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.