MoonshotAI: Kimi K2.7 Code
Analysis Summary
Kimi K2.7 Code is MoonshotAI’s code-focused model, with strong coding results, a 262K context window, and support for vision, tool use, and function calling. Its measured reasoning is more limited than its coding capability, and its agentic performance is comparatively weak.
For agency work, it fits coding assistance, code review, and workflows that need image input or structured tool calls. The long context can support larger code and document inputs, while the available tool interfaces make it practical to connect to existing workflows. It is less suited to tasks that depend on consistently strong autonomous multi-step reasoning.
Pricing is moderate relative to premium models, so Kimi K2.7 Code can serve as a specialist coding option. Teams should test it on their own repositories and agent tasks before relying on it for unattended execution.
Assessed September 23, 2026
Editorial notes
Kimi K2.7 Code pairs strong coding results with vision, tool use, and a 262K context window; its reasoning and agentic performance are weaker than its coding capability.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Kimi K2.7 Code pairs strong coding results with vision, tool use, and a 262K context window; its reasoning and agentic performance are weaker than its coding capability.
Benchmarks
Artificial Analysis data refreshed Oct 23, 2026. Arena ratings from the Oct 20, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.
How MoonshotAI: Kimi K2.7 Code compares
MoonshotAI: Kimi K2.7 Code ranks #85 of 443 AI models we track for overall intelligence, #35 of 198 for coding, #69 of 181 for agentic tasks. Its 262K-token context window is larger than 74% of the models we list. At $0.67 per million input tokens it is cheaper than 30% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.67 | $0.000671 |
| Output | $3.35 | $0.003350 |
What would MoonshotAI: Kimi K2.7 Code cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 718 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save MoonshotAI: Kimi K2.7 Code for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout MoonshotAI: Kimi K2.7 Code
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts..
Frequently asked questions about MoonshotAI: Kimi K2.7 Code
How much does MoonshotAI: Kimi K2.7 Code cost?
MoonshotAI: Kimi K2.7 Code costs $0.67 per million input tokens and $3.35 per million output tokens.
What is the context window of MoonshotAI: Kimi K2.7 Code?
MoonshotAI: Kimi K2.7 Code has a context window of 262,144 tokens (262K).
Is MoonshotAI: Kimi K2.7 Code good for coding?
On our coding benchmark index, MoonshotAI: Kimi K2.7 Code ranks #35 of 198 models, placing it in the top quartile of the field for code generation and debugging.
What can MoonshotAI: Kimi K2.7 Code do?
MoonshotAI: Kimi K2.7 Code supports image/vision input, tool use, and function calling.
Who created MoonshotAI: Kimi K2.7 Code?
MoonshotAI: Kimi K2.7 Code is developed by MoonshotAI and was released on June 12, 2026.