llm.ing

MiniMax-M2.1

MiniMax (minimax.io)open weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

Earlier MiniMax agent model for practical coding and productivity tasks

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence31.4independentaaJul 24, 2026
Design Arena — 3dpreference1225mirroropenrouterJul 23, 2026
Design Arena — codecategoriespreference1223mirroropenrouterJul 24, 2026
Design Arena — datavizpreference1240mirroropenrouterJul 24, 2026
Design Arena — gamedevpreference1193mirroropenrouterJul 23, 2026
Design Arena — svgpreference1181mirroropenrouterJul 24, 2026
Design Arena — uicomponentpreference1263mirroropenrouterJul 24, 2026
Design Arena — websitepreference1229mirroropenrouterJul 24, 2026
Median output speedspeed77 tok/sindependentaaJul 24, 2026
Median time to first tokenspeed1.68sindependentaaJul 24, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Minimaxfp8205K$0.3 · $1.299.81%
Minimaxfp8205K$0.3 · $2.4100.00%
Novitafp8205K$0.3 · $1.299.15%