Kimi K2.7 Code HighSpeed: API pricing, providers and specs
Kimi K2.7 Code HighSpeed is a text model by Moonshot AI. 36 providers serve it, from $2.76 to $8 /1M; the lowest price is at Kenari.
How Kimi K2.7 Code HighSpeed compares
Against the 737 text models on the site priced the same way.
- Pricey for its class: at $2.76 /1M, its lowest price is above 69% of comparable models (median $1.10).
- Its 262K-token context window is larger than 45% of them (median 262K), about 390 pages of text.
- On LMArena's WebDev board it ranks #53 of the 64 comparable models scored there.
- 36 providers serve it; 99% of comparable models have fewer.
- Its weights are open under the modified-mit license: commercial use under the maker's terms.
Kimi K2.7 Code HighSpeed prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| $0.552/1M | $2.76/1M | $0.11/1M | — | |
| APIMart | $0.743/1M | $3.08/1M | — | — |
| $0.76/1M | $3.20/1M | $0.114/1M | — | |
Cortecs | $0.659/1M | $3.32/1M | $0.181/1M | — |
| OpenRouter | $0.671/1M | From$3.35/1M | $0.15/1M | 262K |
| $0.68/1M | From$3.40/1M | — | — | |
Requesty | $0.75/1M | From$3.50/1M | $0.20/1M | 256K |
| $0.75/1M | $3.50/1M | $0.16/1M | — | |
FastRouter | $0.74/1M | $3.50/1M | $0.15/1M | 262K |
| Moonshot AIOfficial | $0.903/1M | From$3.75/1M | $0.181/1M | — |
| $0.903/1M | $3.75/1M | — | — | |
| $0.859/1M | $3.80/1M | $0.18/1M | — | |
| $0.929/1M | $3.86/1M | — | — | |
CrazyRouter | $0.942/1M | $3.91/1M | — | — |
APIYI | $0.95/1M | $3.99/1M | — | — |
| $0.95/1M | $4/1M | $0.161/1M | 262K | |
OrcaRouter | $0.95/1M | $4/1M | $0.19/1M | 262K |
| Moonshot AIOfficial | $0.95/1M | From$4/1M | $0.19/1M | — |
| ZenMux | $0.95/1M | From$4/1M | $0.19/1M | 262K |
| $0.95/1M | $4/1M | $0.19/1M | 262K | |
| $0.95/1M | $4/1M | $0.19/1M | — | |
| $0.95/1M | $4/1M | — | — | |
| OpenCode | $0.95/1M | $4/1M | $0.19/1M | — |
| $0.95/1M | From$4/1M | $0.19/1M | — | |
| Vercel AI Gateway | $0.95/1M | $4/1M | $0.19/1M | 256K |
EmpirioLabs AI | $0.95/1M | $4/1M | $0.95/1M | 256K |
| DevPass (LLM Gateway) | $0.95/1M | From$4/1M | $0.19/1M | — |
| $0.95/1M | From$4/1M | — | — | |
| Atlas Cloud | $0.95/1M | $4/1M | $0.16/1M | — |
Jiekou.AI | $0.95/1M | $4/1M | $0.19/1M | — |
| AI/ML API | $0.95/1M | $4/1M | $0.19/1M | — |
Impossibl | $0.95/1M | $4/1M | $0.19/1M | — |
| $1/1M | $4.16/1M | $0.18/1M | — | |
Charm Hyper | $1.03/1M | $4.36/1M | $0.207/1M | — |
TensorX | $1.25/1M | $4.50/1M | $0.31/1M | — |
Prime Inference | $1.90/1M | $8/1M | — | — |
- Kenari$2.76
- APIMart$3.08
- CometAPI$3.20
- Cortecs$3.32
- OpenRouterFrom$3.35
- Hugging FaceFrom$3.40
- Venice AI$3.50
- FastRouter$3.50
- RequestyFrom$3.50
- SiliconFlow$3.75
- Moonshot AIOfficialFrom$3.75
- SiliconFlow$3.80
Specs
- Type
- Text
- Maker
- Moonshot AI
- Inputs
- Image, Text
- Outputs
- Text
- Context
- 262K≈ 390 pages of text
- Max output
- 262K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling, Vision
- Released
- Jun 11, 2026
- License
- modified-mitcommercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 1.03T
- Arena score
- 1474WebDev
- Monthly searches
- 6K
Alternatives to Kimi K2.7 Code HighSpeed
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Kimi K2.7 Code HighSpeedthis model | $2.76/1M | 262K | 1474 | 36 |
| $8/1M | 1.05M | 1673 | 26 | |
| GPT-6.1 Sol | $8/1M | 1.05M | 1749 | 27 |
| $1.10/1M | 1.05M | 1623 | 49 | |
| GPT-6 Sol | $8/1M | 1.05M | 1682 | 28 |
| $4.11/1M | 1M | — | 22 | |
| Grok 4.7 | $4.80/1M | 500K | 1637 | 28 |
| $2.40/1M | 1.05M | 1466 | 5 | |
| $2.09/1M | 1.05M | 1543 | 13 |
More from Moonshot AI
Kimi K2.7 Code HighSpeed FAQ
Moonshot AI charges $3.75 /1M for Kimi K2.7 Code HighSpeed. The lowest price across providers is $2.76 /1M, at Kenari.
Kenari, at $2.76 /1M. 36 providers serve Kimi K2.7 Code HighSpeed; the table above lists every one with its price.
Kimi K2.7 Code HighSpeed reads up to 262K tokens per request and writes up to 262K.
Yes. Kimi K2.7 Code HighSpeed's weights can be downloaded from its maker's Hugging Face page, under the modified-mit license.
About 1.03T, as the safetensors metadata of its official Hugging Face repo states.
36 API providers serve Kimi K2.7 Code HighSpeed. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us











