kimi-k2.7-code

kimi-k2.7-code

249K Downloads Updated 3 months ago

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.

vision tools thinking cloud

Cost /1M tokens

$0.95

input

$0.19

cached

$4.00

output

Context

256K tokens

Size

1.04T parameters

ollama run kimi-k2.7-code:cloud

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kimi-k2.7-code:cloud",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kimi-k2.7-code:cloud',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kimi-k2.7-code:cloud',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model kimi-k2.7-code:cloud

OpenCode

OpenCode ollama launch opencode --model kimi-k2.7-code:cloud

Hermes Agent

Hermes Agent ollama launch hermes --model kimi-k2.7-code:cloud

OpenClaw

OpenClaw ollama launch openclaw --model kimi-k2.7-code:cloud

Models

Name

1 model

Size / Usage

Context

Input

kimi-k2.7-code:cloud

- · 256K context window · Text, Image · 3 months ago

kimi-k2.7-code:cloud

-

256K

Text, Image

Readme

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

Key Features

Long-horizon coding: Substantial gains on realistic, end-to-end software engineering tasks across 10+ programming languages and a full production tech stack, spanning backend services, infrastructure, performance engineering, systems programming, security, frontend, and ML/data engineering.
Improved token efficiency: Reduces thinking-token usage by approximately 30% compared with Kimi K2.6, while improving task completion on complex workflows.
Stronger agentic tool use: Improved performance on multi-step tool calling and MCP-based environments, with interleaved thinking preserved across turns (preserve_thinking) for coherent multi-step coding sessions.
Native multimodal: Supports image and video input via the MoonViT vision encoder, with a 256K token context window.

Benchmarks

Benchmark	Kimi K2.6	Kimi K2.7 Code	GPT-5.5	Claude Opus 4.8
Coding
Kimi Code Bench v2	50.9	62.0	69.0	67.4
Program Bench	48.3	53.6	69.1	63.8
MLS Bench Lite	26.7	35.1	35.5	42.8
Agentic
Kimi Claw ²⁴⁄₇ Bench	42.9	46.9	52.8	50.4
MCP Atlas	69.4	76.0	79.4	81.3
MCP Mark Verified	72.8	81.1	92.9	76.4

Reference

Hugging Face

<img src="/assets/library/kimi-k2.5/3e4026fd-dc73-4a59-9322-7f015a92925e" width="180" />

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

### Key Features

- **Long-horizon coding**: Substantial gains on realistic, end-to-end software engineering tasks across 10+ programming languages and a full production tech stack, spanning backend services, infrastructure, performance engineering, systems programming, security, frontend, and ML/data engineering.
- **Improved token efficiency**: Reduces thinking-token usage by approximately 30% compared with Kimi K2.6, while improving task completion on complex workflows.
- **Stronger agentic tool use**: Improved performance on multi-step tool calling and MCP-based environments, with interleaved thinking preserved across turns (`preserve_thinking`) for coherent multi-step coding sessions.
- **Native multimodal**: Supports image and video input via the MoonViT vision encoder, with a 256K token context window.

### Benchmarks

| Benchmark            | Kimi K2.6 | Kimi K2.7 Code | GPT-5.5 | Claude Opus 4.8 |
| -------------------- | --------- | -------------- | ------- | --------------- |
| **Coding**           |           |                |         |                 |
| Kimi Code Bench v2   | 50.9      | 62.0           | 69.0    | 67.4            |
| Program Bench        | 48.3      | 53.6           | 69.1    | 63.8            |
| MLS Bench Lite       | 26.7      | 35.1           | 35.5    | 42.8            |
| **Agentic**          |           |                |         |                 |
| Kimi Claw 24/7 Bench | 42.9      | 46.9           | 52.8    | 50.4            |
| MCP Atlas            | 69.4      | 76.0           | 79.4    | 81.3            |
| MCP Mark Verified    | 72.8      | 81.1           | 92.9    | 76.4            |

### Reference

- [Hugging Face](https://huggingface.co/moonshotai/Kimi-K2.7-Code)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)