MiniMax API pricing per million tokens
On 10 November 2026, MiniMax models on this list cost from $0.15 per million input tokens (MiniMax M3.1 Flash) to $0.30 (MiniMax M3), and from $0.60 per million output tokens (MiniMax M3.1 Flash) to $1.20 (MiniMax M3).
| Model | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|
| MiniMax M3.1 Flash | $0.15 | $0.60 | $0.015 | 1.05M | $18.00 | 2026-10-19 | |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | $0.224 / $0.88 | 1.05M | $36.00 | 2026-05-31 |
| MiniMax M2.7 GMICloud, cheapest of 2 hosts | $0.30 | $1.20 | $0.06 | 197K | $36.00 | 2026-03-18 | |
| MiniMax M2.5 Venice, cheapest of 5 hosts | $0.27 | $0.95 | $0.03 | 200K | $30.45 | 2026-02-12 |
2 of these 4 models are not served by MiniMax itself on OpenRouter, so their price is the cheapest regular price among the hosts that run them, and the host is named under the model. Compare MiniMax with every other provider
Common questions
How much does the MiniMax API cost?
On 10 November 2026, MiniMax models on this list cost from $0.15 per million input tokens (MiniMax M3.1 Flash) to $0.30 (MiniMax M3), and from $0.60 per million output tokens (MiniMax M3.1 Flash) to $1.20 (MiniMax M3).
What is the cheapest MiniMax model?
For a typical mix of three input tokens to every output token, the cheapest MiniMax model on this list is MiniMax M3.1 Flash at $0.15 per million input tokens and $0.60 per million output tokens.
What is the newest MiniMax model on the list?
MiniMax M3.1 Flash, listed on 19 October 2026, at $0.15 per million input tokens and $0.60 per million output tokens.
Which MiniMax model has the largest context window?
MiniMax M3.1 Flash, with 1.05M tokens of context.
Does MiniMax offer batch pricing?
Yes, 1 of its models on this list show a batch price, with batch input at a median of 75 percent of the standard price. Batch suits work that can wait for its answer.
Choosing a model for a production agent
Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.