NEWMEN
← back to all models

MiniMax: MiniMax M2

minimax/minimax-m2

MiniMaxopen-weight205K context4 providersIntelligence 80.5

Cheapest provider

$0.26 / 1M

AtlasCloud

Fastest provider (p95)

185 tok/s

Google

Intelligence (composite)

80.5

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
AtlasCloudq8· fp8$0.2550$1.00001723ms / 3145ms42 / 108 tok/s100.00%61.3%
Minimaxq8· fp8$0.2550$1.02001094ms / 2227ms59 / 123.4 tok/s100.00%100.0%
Googleundisclosed$0.3000$1.2000426ms / 3972ms102.5 / 185 tok/s71.8%
Novitaq8· fp8$0.3000$1.20001078ms / 1899ms62 / 120 tok/s100.00%95.0%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

82.0

broad reasoning

Code

83.0

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

78.0

math accuracy

GPQA Diamond

78.0

hard reasoning

Source: Artificial Analysis (AA-aligned) — MiniMax-M2 (MMLU-Pro 82, GPQA-D 78, LiveCodeBench 83, AIME25 78); github.com/MiniMax-AI/MiniMax-M2

How Atlas routes MiniMax: MiniMax M2

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For MiniMax: MiniMax M2 that’s currently AtlasCloud at $0.26/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.