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 / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| ModelRun | q4· fp4 | $0.4000 | $1.9000 | — | — | 99.96% | — |
| Chutes | q4· int4 | $0.4400 | $2.0000 | — | — | 97.95% | — |
| DeepInfra | q4· fp4 | $0.4500 | $2.2500 | — | — | 98.23% | — |
| SiliconFlow | q4· int4 | $0.4500 | $2.2500 | — | — | 99.46% | — |
| AtlasCloud | q4· int4 | $0.4900 | $2.5000 | — | — | 99.85% | — |
| StreamLake | undisclosed | $0.5400 | $2.7000 | — | — | 99.69% | — |
| Venice | undisclosed | $0.5600 | $3.5000 | — | — | 74.77% | — |
| Novita | undisclosed | $0.5700 | $2.8500 | — | — | 99.82% | — |
| Fireworks | undisclosed | $0.6000 | $3.0000 | — | — | — | — |
| Moonshot AI | q4· int4 | $0.6000 | $3.0000 | — | — | 100.00% | — |
| Parasail | q4· int4 | $0.6000 | $2.8000 | — | — | 99.19% | — |
| Phala | undisclosed | $0.6000 | $3.0000 | — | — | 96.62% | — |
“—” 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 mode sources MoonshotAI: Kimi K2.5
- Strict mode — pin MoonshotAI: Kimi K2.5 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently ModelRun at $0.40/1M.
- Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.