MiniMax API Pricing
4 models · From $0.150/1M to $0.300/1M input
The cheapest MiniMax model to run is MiniMax M3.1 Flash at $0.150 input and $0.600 output per 1M tokens. On a RAG answer of 8,000 tokens in and 600 out, MiniMax models range from $0.0016 (MiniMax M3.1 Flash) to $0.0031 (MiniMax M2.5) per request. The largest context window is MiniMax M3.1 Flash at 1.0M tokens. Count tokens with the MiniMax token counter.
| Model | Input /1M | Output /1M | RAG answer |
|---|---|---|---|
| MiniMax M3.1 Flash | $0.150 | $0.600 | $0.0016 |
| MiniMax M3 | $0.300 | $1.20 | $0.0031 |
| MiniMax M2.7 | $0.300 | $1.20 | $0.0031 |
| MiniMax M2.5 | $0.300 | $1.20 | $0.0031 |