Alexey Shurov.
Free tool

MiniMax API pricing per million tokens

On 25 September 2026, MiniMax models on this list cost from $0.20 per million input tokens (MiniMax-01) to $0.40 (MiniMax M1), and from $1.08 per million output tokens (MiniMax M2.5) to $2.20 (MiniMax M1).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens
ModelInputOutputCached inputBatch in / outContextYour monthListed
MiniMax M3$0.30$1.20$0.061.04858M$36.002026-05-31
MiniMax M2.7$0.30$1.20$0.06205K$36.002026-03-18
MiniMax M2.5$0.27$1.08$0.027205K$32.402026-02-12
MiniMax M2-her$0.30$1.20$0.0366K$36.002026-01-23
MiniMax M2.1
retiring 2026-10-08
$0.30$1.20$0.03205K$36.002025-12-23
MiniMax M2$0.30$1.20205K$36.002025-10-23
MiniMax M1$0.40$2.201M$57.002025-06-17
MiniMax-01$0.20$1.101.00019M$28.502025-01-15

Compare MiniMax with every other provider

Common questions

How much does the MiniMax API cost?

On 25 September 2026, MiniMax models on this list cost from $0.20 per million input tokens (MiniMax-01) to $0.40 (MiniMax M1), and from $1.08 per million output tokens (MiniMax M2.5) to $2.20 (MiniMax M1).

What is the cheapest MiniMax model?

For a typical mix of three input tokens to every output token, the cheapest is MiniMax-01 at $0.20 per million input tokens and $1.10 per million output tokens.

What is the newest MiniMax model on the list?

MiniMax M3, listed on 31 May 2026, at $0.30 per million input tokens and $1.20 per million output tokens.

Which MiniMax model has the largest context window?

MiniMax M3, with 1.04858M tokens of context.

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.

shurco.aiGuidesFree toolsSolutionsInsightsRSSllms.txt