minimax Open weights Reasoning

MiniMax M2.7 pricing & benchmarks

Released Mar 18, 2026 · served by 10 providers · ranked #35 by intelligence in our index

Input / 1M tokens$0.240
Output / 1M tokens$0.960
Context window205K
Cached input$0.050
Intelligence index38.1
Coding index52.6
Agentic index25.6
1M in + 300K out$0.53

What MiniMax M2.7 is

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Providers and prices for MiniMax M2.7

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
Maracheapest $0.240 $0.960 197K 86.8%
Novita $0.270 $1.08 205K fp8 99.4%
GMICloud $0.300 $1.20 197K fp8 99.7%
AtlasCloud $0.300 $1.20 197K fp8 98.0%
Fireworks $0.300 $1.20 197K 99.7%
Together $0.300 $1.20 197K fp4 99.4%
DeepInfra $0.380 $1.70 197K fp8 94.6%
Groq $0.600 $1.80 197K 99.1%
Minimax $0.600 $2.40 205K fp8 97.5%
SambaNova $0.600 $2.40 197K 99.7%

MiniMax M2.7 benchmark results

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

CategoryArenaRankEloWin rate
dataviz models #27 1261 53.2%
website models #27 1271 54%
gamedev models #28 1263 53%
codecategories models #30 1265 53.1%
3d models #34 1247 50.6%
svg models #34 1189 50.4%
uicomponent models #34 1247 50%
asciiart models #36 1178 48.1%

Cheaper models in the same class

Models scoring within 4 points of MiniMax M2.7 on the Intelligence Index, but with a lower output price.

FAQ

How much does the MiniMax M2.7 API cost?

$0.240 per 1M input tokens and $0.960 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.53.

Is MiniMax M2.7 free?

No. It is a paid model starting at $0.240 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for MiniMax M2.7?

Mara at $0.240 input / $0.960 output per 1M tokens.

Can I self-host MiniMax M2.7?

Yes — weights are published as MiniMaxAI/MiniMax-M2.7 on Hugging Face, so you can run it on your own hardware.