MiniMax API pricing
Every MiniMax model we track, with the cheapest input and output rates per 1M tokens across 19 providers. Collected daily.
MiniMax API prices by model
Standard (real-time) rates per 1M tokens, newest first. The cheapest input and the cheapest output are often on different hosts, so each is shown with its own host. Batch and cached-input rates are on each model page.
| Model | Cheapest input | Cheapest output |
|---|---|---|
| MiniMax-M3.1-Flash | $0.079Runcrate | $0.315Runcrate |
| MiniMax-M3 | $0.200EcoHash | $0.900EcoHash |
| MiniMax M2.7205K context | $0.210OpenRouter | $0.840OpenRouter |
| MiniMax M2.5128K context | $0.270IteraCompute | $1.03IteraCompute |
| MiniMax M2.1197K context | $0.300Amazon AWS | $1.20Amazon AWS |
| MiniMax M1 80k | $0.550Novita AI | $2.20Novita AI |
| MiniMax M11.0M context | $0.550OpenRouter | $2.20OpenRouter |
MiniMax price history
Average input price per 1M tokens across the providers serving each model, last 90 days.
Frequently Asked Questions
Which MiniMax model has the lowest API prices?
Of the 7 MiniMax models we track, MiniMax-M3.1-Flash has the lowest input rate right now: $0.079 per 1M tokens on Runcrate. MiniMax-M3.1-Flash has the lowest output rate: $0.315 per 1M tokens on Runcrate. Which is cheaper for you depends on how many input tokens you send per output token. Prices are collected daily from 19 providers.
Where is MiniMax-M3.1-Flash cheapest?
MiniMax-M3.1-Flash is served by 11 providers we track. The lowest rates are $0.079 per 1M input tokens on Runcrate and $0.315 per 1M output tokens on Runcrate. Throughput, latency and context limits differ between hosts, so check the model page before committing.