Log in
← All models

Kimi K2.7 Code

Balanced

Open-weight model tuned for agentic coding — a community favourite for cheap, capable dev work.

Moonshot AI
Maker
88/100
Overall
67
Value score
$1.35
Blended /1M
262K
Context
Open
Weights
Pricing: $0.61 in · $3.07 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality8.6/10 · 75% community
Agentic Ability9.2/10 · 78% community
Speed7.8/10 · 71% community
Value for $9.2/10 · 78% community
Reliability8.9/10 · 77% community

Kimi K2.7 Code is Moonshot's coding-tuned open-weight model and a darling of the open agent community. It's strong at tool use and multi-file edits, with a 262K context, and undercuts the closed coding models on price.

Strengths
  • Tuned for agentic coding
  • Open weights
  • Strong tool use for the price
Trade-offs
  • Below the very top models on hard reasoning
  • Throughput varies by host

Agents that run Kimi K2.7 Code well

Cheap, capable open-weight coding agents.

Best model for ClineBest model for AiderBest model for Kilo CodeBest model for OpenCodeBest model for OpenClaw

Kimi K2.7 Code FAQ

Is Kimi K2.7 Code good for AI agents?
Cheap, capable open-weight coding agents. On our editorial scoring it rates 9.2/10 for agentic ability and 8.6/10 for output quality. Tuned for agentic coding.
How much does Kimi K2.7 Code cost?
Via OpenRouter, Kimi K2.7 Code is priced at $0.61 in · $3.07 out / 1M tokens — a blended rate of about $1.35 per 1M tokens for typical input-heavy agent use.
What is Kimi K2.7 Code's context window?
Kimi K2.7 Code has a 262K-token context window. Moonshot AI is the maker.
Is Kimi K2.7 Code open source?
Yes — Kimi K2.7 Code ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of Kimi K2.7 Code?
The main trade-offs: below the very top models on hard reasoning; throughput varies by host. It's strongest for cheap, capable open-weight coding agents.

Kimi K2.7 Code compared

Kimi K2.7 Code vs Sonnet 4.6Kimi K2.7 Code vs GPT-5.4Kimi K2.7 Code vs Gemini 3.5 FlashKimi K2.7 Code vs GPT-5.3-CodexKimi K2.7 Code vs MiniMax M3Kimi K2.7 Code vs Qwen3.7 PlusKimi K2.7 Code vs Devstral 2Kimi K2.7 Code vs GLM 4.7

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →