Kimi K2.7-Code

kimi-k2.7-code

Open sourceKimi series

Overview

262K ContextCode generationReasoningMCP

Kimi K2.7-Code is a Moonshot AI model fine-tuned specifically for coding, scoring at the top of mainstream code benchmarks including HumanEval, MBPP and BigCodeBench. It supports 70+ programming languages and the major IDE protocols, handling completion, unit tests, bug fixes and cross-file refactoring in one flow — a capable assistant for day-to-day engineering and automated code workflows.

Code completion

Speaks the major IDE completion protocols with millisecond latency and cross-file context awareness.

Code generation

Generates complete functions and classes from a natural-language description, including comments, unit tests and edge-case handling.

70+ programming languages

Native support for 70+ languages including Python, JavaScript, Go, Rust and Java.

Tool calling

Function calling and the MCP protocol connect it to code search, CI/CD and internal tooling.

Features

Tool calling✓

Structured output✓

Context caching✓

Batch✓

Web search✓

Streaming✓

Reasoning✓

MCP✓

Prefix completion✕

Fine-tuning✕

Pricing

Input¥6.5/M tokens

Input (cache hit)¥1.3/M tokens

Output¥27/M tokens

Rate Limits & Context

Context Window262K

Max Output262K

RPM (requests/min)500

TPM (tokens/min)1M

Built-in Tools

web_search

Responses API

code_interpreter

Responses API

web_extractor

Responses API

API Reference

ENDPOINT

POST https://api.tokenfab.cn/v1/chat/completions

Request Example

curl https://api.tokenfab.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKENFAB_API_KEY" \
  -d '{
    "model": "kimi-k2.7-code",
    "messages": [
      {"role": "system", "content": "You are a coding assistant."},
      {"role": "user", "content": "把上面这个 Python 函数改写成 Go 语言，并补充单元测试和错误处理。"}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.tokenfab.cn/v1"
)

response = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "把上面这个 Python 函数改写成 Go 语言，并补充单元测试和错误处理。"}
    ]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKENFAB_API_KEY,
  baseURL: "https://api.tokenfab.cn/v1"
});

const response = await client.chat.completions.create({
  model: "kimi-k2.7-code",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "把上面这个 Python 函数改写成 Go 语言，并补充单元测试和错误处理。" }
  ]
});

console.log(response.choices[0].message.content);

Response Example

JSON

{
  "id": "chatcmpl-kimi-code-9d2k7f1",
  "object": "chat.completion",
  "created": 1784950000,
  "model": "kimi-k2.7-code",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "下面是 Go 版本实现，包含单元测试和错误处理：\n\nfunc QuickSort(arr []int) ([]int, error) {\n  if len(arr) == 0 { return nil, errors.New(\"empty input\") }\n  // ... (完整代码)\n}"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 312,
    "completion_tokens": 248,
    "total_tokens": 560
  }
}

Request Parameters

Parameter	Type	Required	Description
model	string	✓	Model ID, e.g. kimi-k2.7-code
messages	array	✓	List of chat messages, each with role and content
temperature	float	—	Sampling temperature, 0–2, default 0.7
top_p	float	—	Nucleus sampling, 0–1, default 0.9
max_tokens	int	—	Maximum output tokens
stream	bool	—	Whether to stream the response, default false
tools	array	—	Tool definitions for function calling
tool_choice	string	—	Tool choice policy: auto / none / a named function