Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Comparison of MiniMax: MiniMax M2.1
1 modelminimaxMiniMax: MiniMax M2.1Remove ×
What’s differentMiniMax-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…
DateDec 23, 2025Listed
Listed rate$0.30 in / $1.20 out/ 1M tokensMinimax · via OpenRouter · all routes ↗minimax/fp8 · quantization=fp8
Provider endpoints3 endpoints →
Context window204.8K
Max output131.1K
Parameters—
Tool callingSupported
Structured outputSupported
ReasoningSupported
Prompt cachingSupported
Open weightsSupported

Add another model

Search all models →