Kimi K2.7 Code Highspeed
kimi-k2.7-code-highspeedPricing
List prices at AIHubMix, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.90 | $8.00 | |
| Cached input 83% off input | $0.322 | 83% off input |
What it costs a month
At AIHubMix list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,028
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$821
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,434
- Overnight batch20,000 requests a day, 4K in / 0.4K out$6,480
Where to run it
4 hosts serve Kimi K2.7 Code Highspeed. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AIHubMixGateway kimi-k2.7-code-highspeed | $1.90 / $8.00 | kimi-k2.7-code-highspeed | |
EmpirioLabs AICloud kimi-k2-7-code-highspeed | $1.90 / $8.00 | kimi-k2-7-code-highspeed | |
Tencent TokenHubCloud kimi-k2.7-code-highspeed | $1.90 / $8.00 | kimi-k2.7-code-highspeed | |
GMI CloudInference kimi-k2.7-code-highspeed | $1.90 / $8.00 | kimi-k2.7-code-highspeed |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Modified MIT LicenseRuntimes: SGLang, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than AIHubMix.
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 12% less
- 12% less
- 42% less
- 94% less
Open-weight picks
- 34% less
- 50% less
- 80% less
- 85% less
Call it
Using AIHubMix's API.
from litellm import completion
response = completion(
model="aihubmix/kimi-k2.7-code-highspeed",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K2.7 Code Highspeed cost?
On AIHubMix, Kimi K2.7 Code Highspeed costs $1.90 per million input tokens and $8.00 per million output tokens. Cached input costs $0.322 per million tokens.
Which APIs offer Kimi K2.7 Code Highspeed?
Kimi K2.7 Code Highspeed runs on 4 APIs: AIHubMix, EmpirioLabs AI, Tencent TokenHub and GMI Cloud.
What is Kimi K2.7 Code Highspeed's context window?
262K tokens, with up to 33K tokens in one reply.
Is Kimi K2.7 Code Highspeed being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Kimi K2.7 Code Highspeed?
Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (12% less), Grok 4.7 on xAI (12% less) and Qwen4 Max on Alibaba DashScope (34% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Kimi K2.7 Code Highspeed's API model id?
Use kimi-k2.7-code-highspeed with AIHubMix. Other hosts use their own ids: kimi-k2-7-code-highspeed on EmpirioLabs AI.
Sources
- EmpirioLabs AI pricing
- AIHubMix pricing
- GMI Cloud pricing
- Tencent TokenHub pricing
- LiteLLM model map
Raw catalog entry for kimi-k2.7-code-highspeed on AIHubMix
{
"cache_read_input_token_cost": 3.2167e-7,
"input_cost_per_token": 0.0000019,
"litellm_provider": "aihubmix",
"max_input_tokens": 262144,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 0.000007999,
"source": "https://aihubmix.com/api/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true
}