The board shows this model's cheapest measured offer ($0.787/1M); the smaller figure under it is the mean of the 21 offers listed below ($1.10/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| DigitalOcean | OpenRouter | $0.375 | $2.02 | 750ms | 16 | 99.8% | API-measured |
| DeepInfra (fp4) | OpenRouter | $0.450 | $2.25 | 915ms | 17 | 100% | API-measured |
| SiliconFlow (int4) | OpenRouter | $0.450 | $2.25 | 2616ms | 31 | 85.0% | API-measured |
| deepinfra | HuggingFace Router | $0.450 | $2.25 | 820ms | 36 | — | API-measured |
| requesty | Requesty | $0.450 | $2.25 | — | — | — | API-measured |
| AtlasCloud (int4) | OpenRouter | $0.490 | $2.50 | 1542ms | 39 | 99.9% | API-measured |
| together_ai | Pricebook (LiteLLM) | $0.500 | $2.80 | — | — | — | Official list |
| StreamLake (fp8) | OpenRouter | $0.540 | $2.70 | 1312ms | 59 | 99.9% | API-measured |
| Novita | OpenRouter | $0.570 | $2.85 | 3497ms | 29 | 100.0% | API-measured |
| azure_ai | Pricebook (LiteLLM) | $0.600 | $3.00 | — | — | — | Official list |
| baseten | Pricebook (LiteLLM) | $0.600 | $3.00 | — | — | — | Official list |
| moonshot | Pricebook (LiteLLM) | $0.600 | $3.00 | — | — | — | Official list |
| openrouter | Pricebook (LiteLLM) | $0.600 | $3.00 | — | — | — | Official list |
| wandb | Pricebook (LiteLLM) | $0.600 | $3.00 | — | — | — | Official list |
| novita | HuggingFace Router | $0.600 | $3.00 | 767ms | 44 | — | API-measured |
| novita-ai | Novita AI | $0.600 | $3.00 | — | — | — | API-measured |
| Moonshot AI (int4) | OpenRouter | $0.600 | $3.00 | 1077ms | 63 | 100% | API-measured |
| Amazon Bedrock (us-east-2) | OpenRouter | $0.600 | $3.00 | 965ms | 63 | 99.6% | API-measured |
| Phala | OpenRouter | $0.600 | $3.00 | 2072ms | 20 | 8.0% | API-measured |
| burncloud | burncloud | $0.574 | $3.16 | — | — | — | API-measured |
| Venice | OpenRouter | $0.560 | $3.50 | 1639ms | 73 | 98.4% | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.775 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875 → $0.7875
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/kimi-k2.5.json. Free reuse requires attribution to tkx.org.
About
Kimi K2.5 is a language model AI system designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces under the org tag "moonshotai".
AI-generated summary from public information — is this yours?
FAQ
How much does Kimi K2.5 cost?
Cheapest measured offer right now: $0.375/1M input, $2.025/1M output via DigitalOcean — across 17 tracked providers, refreshed hourly.
Who serves Kimi K2.5?
17 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of Kimi K2.5 going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.