minimax Open weights Reasoning

MiniMax M2.1 pricing & benchmarks

Released Dec 23, 2025 · served by 2 providers

Input / 1M tokens$0.300
Output / 1M tokens$1.20
Context window205K
Cached input$0.030
1M in + 300K out$0.66

What MiniMax M2.1 is

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

Providers and prices for MiniMax M2.1

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Novitacheapest $0.300 $1.20 205K fp8 99.4%
Minimax $0.300 $2.40 205K fp8 99.9%

MiniMax M2.1 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
uicomponent models #32 1259 60.9%
dataviz models #35 1235 57%
svg models #37 1182 55.4%
codecategories models #39 1221 55.3%
website models #39 1226 55.4%
3d models #40 1222 57.5%
gamedev models #55 1191 50.4%

FAQ

How much does the MiniMax M2.1 API cost?

$0.300 per 1M input tokens and $1.20 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.66.

Is MiniMax M2.1 free?

No. It is a paid model starting at $0.300 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for MiniMax M2.1?

Novita at $0.300 input / $1.20 output per 1M tokens (fp8 quantization).

Can I self-host MiniMax M2.1?

Yes — weights are published as MiniMaxAI/MiniMax-M2.1 on Hugging Face, so you can run it on your own hardware.