NEWMEN
← back to all models

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6

Moonshotopen-weight262K context18 providersIntelligence 75.4· est.

Cheapest provider

$0.73 / 1M

Io Net

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

75.4

Family + generation + popularity + price tier

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
Io Netq4· int4$0.7300$3.490097.58%
Chutesq4· int4$0.7400$3.500097.97%
Cloudflareundisclosed$0.7400$3.500099.90%
Inceptronq4· int4$0.7400$3.500096.31%
DeepInfraq4· fp4$0.7500$3.5000100.00%
Parasailq4· int4$0.7500$3.500098.58%
SiliconFlowq8· fp8$0.7700$4.0000100.00%
Novitaundisclosed$0.8000$3.400099.54%
Veniceq4· int4$0.8500$4.6550100.00%
StreamLakeundisclosed$0.9025$3.8000100.00%
AkashMLq4· int4$0.9500$4.0000100.00%
AtlasCloudq4· int4$0.9500$4.000098.19%
Fireworksundisclosed$0.9500$4.0000
Moonshot AIq4· int4$0.9500$4.000099.89%
Nebiusq4· int4$0.9500$4.0000100.00%
WandBq4· fp4$0.9500$4.000099.60%
Phalaundisclosed$1.0900$4.600097.32%
Togetherundisclosed$1.2000$4.500099.85%

“—” 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 estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas routes MoonshotAI: Kimi K2.6

  • 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 K2.6 that’s currently Io Net at $0.73/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.