CrossModel
Kimi K2.7 Code
moonshot/kimi-k2.7-code
Back to model catalog

Moonshot · Model guide

Kimi K2.7 Code

Compare
moonshot/kimi-k2.7-code

Moonshot's open coding-specialized multimodal Agent model, retaining the 1T/32B-active K2 architecture while concentrating on repository work, tool orchestration and persistent long-horizon execution.

Modalities
TextImageVideoText
Context
262K
Max output
262K
Price / 1M tokens
$ 1.00in$ 4.16out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA coding model built for autonomous software-engineering and tool-rich agent workflows.source

Best for

  • Repository-scale coding · Official evaluations focus on real repository changes, command-line execution and long task trajectories.(vendor claim)source

  • Tool orchestration · Designed to sustain multi-step MCP and agent tool use across long sessions.(vendor claim)source

Neighbouring models
  • moonshot/kimi-k2.6sibling —Choose K2.6 for broader general-purpose multimodal and research work.(vendor claim)source
  • moonshot/kimi-k3successor —Choose K3 for the newest flagship and a 1M-token context window.(vendor claim)source
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 1.00
Output$ 4.16
Cache read$ 0.18
Cache write$ 1.00
Estimate a request
$ 0.0183
Estimated cost per request
10.0K × $ 1.00
+ 2.0K × $ 4.16
≈ $ 18.32 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
262.0K tokens
Max output
262.0K tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specshuggingface.coCapabilitieshuggingface.co

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Kimi Code Bench v2
    score·Moonshot AI · 2026-06-12Kimi Code CLIsetup not fully disclosed

    Evaluated with a 262,144-token context window.

    62%
Agentic tasks
  • Kimi Claw 24/7
    score·Moonshot AI · 2026-06-12OpenClaw3 runssetup not fully disclosed
    46.9%
Coding
  • MLS Bench Lite
    score·Moonshot AI · 2026-06-12Kimi Code CLIsetup not fully disclosed
    35.1%
  • ProgramBench
    score·Moonshot AI · 2026-06-12Kimi Code CLIsetup not fully disclosed
    53.6%
Tool use
  • MCP Atlas
    score·Moonshot AI · 2026-06-123 runssetup not fully disclosed

    Maximum 100 tool calls.

    76%
  • MCPMark Verified
    score·Moonshot AI · 2026-06-123 runssetup not fully disclosed

    Maximum 100 steps.

    81.1%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Kimi K2.7 Code?
Kimi K2.7 Code is available on CrossModel as moonshot/kimi-k2.7-code. It has a 262K-token context window and can return up to 262K tokens per request.
How much does Kimi K2.7 Code cost?
Currently $ 1.00 per 1M input tokens and $ 4.16 per 1M output tokens. Cached input is billed at $ 0.18 per 1M.
Does Kimi K2.7 Code support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.