minimax Open weights Reasoning

MiniMax M2 pricing & benchmarks

Released Oct 23, 2025 · served by 3 providers

Input / 1M tokens$0.255
Output / 1M tokens$1.02
Context window205K
Cached input
1M in + 300K out$0.56

What MiniMax M2 is

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Providers and prices for MiniMax M2

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
Minimaxcheapest $0.255 $1.02 205K fp8 99.7%
Google $0.300 $1.20 197K 99.9%
Novita $0.300 $1.20 205K fp8 99.6%

MiniMax M2 benchmark results

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

CategoryArenaRankEloWin rate
svg models #43 1150 55.3%
gamedev models #61 1174 48.1%
uicomponent models #61 1173 49.2%
3d models #62 1155 48.3%
dataviz models #62 1170 50%
codecategories models #67 1166 48.1%
website models #67 1167 48%

FAQ

How much does the MiniMax M2 API cost?

$0.255 per 1M input tokens and $1.02 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.56.

Is MiniMax M2 free?

No. It is a paid model starting at $0.255 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for MiniMax M2?

Minimax at $0.255 input / $1.02 output per 1M tokens (fp8 quantization).

Can I self-host MiniMax M2?

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