The board shows this model's cheapest measured offer ($1.28/1M); the smaller figure under it is the mean of the 34 offers listed below ($1.66/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| StreamLake | OpenRouter ↗ | $0.713 | $3.00 | 1031ms | 42 | 100% | API-measured |
| openrouter | Pricebook (LiteLLM) ↗ | $0.706 | $3.21 | — | — | — | Official list |
| Inceptron (int4) | OpenRouter ↗ | $0.706 | $3.21 | 846ms | 63 | 99.8% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.680 | $3.40 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $0.680 | $3.40 | 1151ms | 26 | — | API-measured |
| DeepInfra (fp4) | OpenRouter ↗ | $0.680 | $3.40 | 1280ms | 57 | 100% | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $0.710 | $3.50 | — | — | — | Official list |
| CoreWeave (int4) | OpenRouter ↗ | $0.710 | $3.50 | 487ms | 221 | 100% | API-measured |
| requesty | Requesty ↗ | $0.750 | $3.50 | — | — | — | API-measured |
| Venice (int4) | OpenRouter ↗ | $0.750 | $3.50 | 2059ms | 43 | 100% | API-measured |
| ModelRun (fp4) | OpenRouter ↗ | $0.850 | $3.75 | 221ms | 189 | 100.0% | API-measured |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.859 | $3.80 | 1425ms | 23 | 100% | API-measured |
| Novita (int4) | OpenRouter ↗ | $0.912 | $3.84 | 1506ms | 39 | 100% | API-measured |
| cloudflare | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| dashscope | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| qwencloud | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| qwen_ai_platform | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| moonshot | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| nebius | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| azure_ai | Pricebook (LiteLLM) ↗ | $0.950 | $4.00 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $0.950 | $4.00 | 1504ms | 65 | — | API-measured |
| fireworks-ai | HuggingFace Router ↗ | $0.950 | $4.00 | 272ms | 91 | — | API-measured |
| baseten | HuggingFace Router ↗ | $0.950 | $4.00 | 344ms | 143 | — | API-measured |
| novita-ai | Novita AI ↗ | $0.950 | $4.00 | — | — | — | API-measured |
| Fireworks | OpenRouter ↗ | $0.950 | $4.00 | 413ms | 84 | 93.4% | API-measured |
| BaseTen (fp4) | OpenRouter ↗ | $0.950 | $4.00 | 266ms | 117 | 98.2% | API-measured |
| GMICloud (fp8) | OpenRouter ↗ | $0.950 | $4.00 | 4132ms | 42 | 99.8% | API-measured |
| Alibaba (fp8) | OpenRouter ↗ | $0.950 | $4.00 | 1651ms | 48 | 100% | API-measured |
| Cloudflare | OpenRouter ↗ | $0.950 | $4.00 | 602ms | 98 | 100.0% | API-measured |
| Moonshot AI (int4) | OpenRouter ↗ | $0.950 | $4.00 | 1246ms | 42 | 100% | API-measured |
| 0g-teetls | 0G Router ↗ | $1.08 | $4.50 | — | — | — | API-measured |
| Moonshot AI (highspeed) | OpenRouter ↗ | $1.90 | $8.00 | 2754ms | 103 | 100.0% | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $1.2938 → $1.2938 → $1.2938 → $1.2938 → $1.2938 → $1.2938 → $1.2938 → $1.2938 → $1.345 → $1.345 → $1.345 → $1.345 → $1.345 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844 → $1.2844
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-k2.7-code.json. Free reuse requires attribution to tkx.org.
About
Kimi-k2.7-code is an AI model that specializes in code generation and understanding, leveraging machine learning to assist developers in writing and optimizing code. It is served by multiple inference providers on AI model marketplaces, making it accessible for various applications.
AI-generated summary from public information — is this yours?
FAQ
How much does Kimi K2.7 Code cost?
Cheapest measured offer right now: $0.7125/1M input, $3/1M output via StreamLake — across 23 tracked providers, refreshed hourly.
Who serves Kimi K2.7 Code?
23 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of Kimi K2.7 Code going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.