MoonshotAI: Kimi K2.5
moonshotai/kimi-k2.5
Cheapest provider
$0.40 / 1M
ModelRun
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
74.0
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 |
|---|---|---|---|---|---|---|---|
| ModelRun | q4· fp4 | $0.4000 | $1.9000 | — | — | 100.00% | — |
| Chutes | q4· int4 | $0.4400 | $2.0000 | — | — | 99.53% | — |
| DeepInfra | q4· fp4 | $0.4500 | $2.2500 | — | — | 98.99% | — |
| SiliconFlow | q4· int4 | $0.4500 | $2.2500 | — | — | 100.00% | — |
| AtlasCloud | q4· int4 | $0.4900 | $2.5000 | — | — | 99.33% | — |
| Venice | undisclosed | $0.5600 | $3.5000 | — | — | 99.09% | — |
| Novita | undisclosed | $0.5700 | $2.8500 | — | — | 99.94% | — |
| StreamLake | undisclosed | $0.5700 | $2.8500 | — | — | 98.02% | — |
| Cloudflare | undisclosed | $0.6000 | $3.0000 | — | — | 97.30% | — |
| Fireworks | undisclosed | $0.6000 | $3.0000 | — | — | — | — |
| Moonshot AI | q4· int4 | $0.6000 | $3.0000 | — | — | 99.77% | — |
| Parasail | q4· int4 | $0.6000 | $2.8000 | — | — | 99.79% | — |
| Phala | undisclosed | $0.6000 | $3.0000 | — | — | 99.42% | — |
“—” 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
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes MoonshotAI: Kimi K2.5
- 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 K2.5 that’s currently ModelRun at $0.40/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.