MoonshotAI: Kimi K2.6
moonshotai/kimi-k2.6
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| Io Net | q4· int4 | $0.7300 | $3.4900 | — | — | 97.58% | — |
| Chutes | q4· int4 | $0.7400 | $3.5000 | — | — | 97.97% | — |
| Cloudflare | undisclosed | $0.7400 | $3.5000 | — | — | 99.90% | — |
| Inceptron | q4· int4 | $0.7400 | $3.5000 | — | — | 96.31% | — |
| DeepInfra | q4· fp4 | $0.7500 | $3.5000 | — | — | 100.00% | — |
| Parasail | q4· int4 | $0.7500 | $3.5000 | — | — | 98.58% | — |
| SiliconFlow | q8· fp8 | $0.7700 | $4.0000 | — | — | 100.00% | — |
| Novita | undisclosed | $0.8000 | $3.4000 | — | — | 99.54% | — |
| Venice | q4· int4 | $0.8500 | $4.6550 | — | — | 100.00% | — |
| StreamLake | undisclosed | $0.9025 | $3.8000 | — | — | 100.00% | — |
| AkashML | q4· int4 | $0.9500 | $4.0000 | — | — | 100.00% | — |
| AtlasCloud | q4· int4 | $0.9500 | $4.0000 | — | — | 98.19% | — |
| Fireworks | undisclosed | $0.9500 | $4.0000 | — | — | — | — |
| Moonshot AI | q4· int4 | $0.9500 | $4.0000 | — | — | 99.89% | — |
| Nebius | q4· int4 | $0.9500 | $4.0000 | — | — | 100.00% | — |
| WandB | q4· fp4 | $0.9500 | $4.0000 | — | — | 99.60% | — |
| Phala | undisclosed | $1.0900 | $4.6000 | — | — | 97.32% | — |
| Together | undisclosed | $1.2000 | $4.5000 | — | — | 99.85% | — |
“—” 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.
- ·kimi family base
- ·top-11 on OpenRouter +1
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.