Kimi K2.7 Code HighSpeed

与 Kimi K2.7 Code 相同, 输出速度约 5-6 倍 (常规编程场景约 180 Token/s)

Model ID: kimi-k2.7-code-highspeed · Type: chat · Provider: Moonshot

Endpoints: /v1/chat/completions · /v1/messages · /v1/responses

Pricing

Input (per 1M tokens)$0.95 USD
Output (per 1M tokens)$4 USD
Cache read (per 1M tokens)$0.19 USD

Capabilities

from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="kimi-k2.7-code-highspeed",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Kimi K2.7 Code HighSpeed cost on 国际云宝子（Ai）?

Kimi K2.7 Code HighSpeed (`kimi-k2.7-code-highspeed`) is billed per usage at $0.95/1M in · $4/1M out, in USD. Current pricing is always listed at https://ai.yunbaozi.com/models/kimi-k2.7-code-highspeed.

How do I call Kimi K2.7 Code HighSpeed through 国际云宝子（Ai）?

Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "kimi-k2.7-code-highspeed"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does Kimi K2.7 Code HighSpeed support?

Kimi K2.7 Code HighSpeed can be called on: /v1/chat/completions; /v1/messages; /v1/responses.

What is Kimi K2.7 Code HighSpeed's context window?

Kimi K2.7 Code HighSpeed accepts up to 262,144 input tokens and can return up to 32,768 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Kimi K2.7 Code HighSpeed do?

Kimi K2.7 Code HighSpeed supports: function_calling, prompt_caching, reasoning.

Who makes Kimi K2.7 Code HighSpeed?

Kimi K2.7 Code HighSpeed is a chat model from Moonshot, available through the 国际云宝子（Ai） gateway with the same API key as every other model.

Call it through the 国际云宝子（Ai） OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can browse the catalog and call any text model through MCP (https://mcp.router.ai/mcp); for image, video and other modalities use the API above.

API reference · All models