NEWMEN
← back to all models

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

Moonshotopen-weight262K context3 providersIntelligence 69.5

Cheapest provider

$0.60 / 1M

AtlasCloud

Fastest provider (p95)

256 tok/s

Groq

Intelligence (composite)

69.5

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$0.6000$2.500020727ms / 60242ms18 / 23 tok/s99.92%99.8%
Novitaq8· fp8$0.6000$2.50001683ms / 15218ms8 / 15 tok/s99.88%99.6%
Groqundisclosed$1.0000$3.0000674ms / 5787ms104 / 256 tok/s98.96%94.1%

“—” 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

61.0

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

57.0

math accuracy

GPQA Diamond

77.0

hard reasoning

Source: Artificial Analysis (AA-aligned) via MiniMax-M2 benchmark table — Kimi K2 0905 (MMLU-Pro 82, GPQA-D 77, LiveCodeBench 61, AIME25 57); github.com/MiniMax-AI/MiniMax-M2

How Atlas routes MoonshotAI: Kimi K2 0905

  • 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 MoonshotAI: Kimi K2 0905 that’s currently AtlasCloud at $0.60/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.