Kimi K2.7 Code Review: The First Open-Weight Model in GitHub Copilot

·
review kimi moonshot coding

An Open-Weight Model Just Entered GitHub Copilot

On July 1st, GitHub dropped a quiet announcement: Kimi K2.7 Code is now generally available in GitHub Copilot. It’s the first open-weight model to appear in the Copilot model picker.

Until now, Copilot only offered closed-source models — GPT, Claude, Gemini. Now a model from Moonshot AI, a Chinese AI lab, sits right next to them. You can select it in VS Code 1.127+, Visual Studio 17.14.6+, JetBrains 1.9.1+, Copilot CLI, and even GitHub Mobile.

For enterprise users, Copilot Business and Enterprise plans have it disabled by default — administrators must explicitly enable the Kimi K2.7 Code policy. GitHub recommends reviewing it against your security and compliance requirements first. Standard language, but the fact that it’s there at all says something about the model’s quality.

From K2.6 to K2.7 Code: What Changed

Kimi K2.7 Code is built on K2.6 but serves a different purpose — K2.6 is a general-purpose model, K2.7 Code is coding-specialized.

Benchmark data from the official page and HuggingFace model card:

BenchmarkK2.6K2.7 CodeImprovement
Kimi Code Bench v250.962.0+21.8%
Program Bench48.353.6+11.0%
MLS Bench Lite26.735.1+31.5%
Kimi Claw 24/7 Bench42.946.9+9.3%
MCP Atlas69.476.0+9.5%
MCP Mark Verified72.881.1+11.4%

Two things worth noting:

  1. Coding gains are much larger than agentic gains. MLS Bench Lite jumped 31.5% — this benchmark asks models to invent generalizable ML methods, so K2.7 Code improved most on complex research-oriented coding tasks.
  2. Thinking-token usage dropped ~30%. The model reaches answers with less internal deliberation, which directly impacts response speed and API costs.

How It Stacks Up Against Top Closed-Source Models

The honest comparison (from the same official benchmarks):

BenchmarkK2.7 CodeGPT-5.5Claude Opus 4.8
Kimi Code Bench v262.069.067.4
Program Bench53.669.163.8
MLS Bench Lite35.135.542.8
MCP Atlas76.079.481.3
MCP Mark Verified81.192.976.4

There’s a real gap. On Program Bench — which asks models to rebuild program behavior from compiled binaries — GPT-5.5 scores 69.1 versus K2.7 Code’s 53.6. That’s significant.

But look at the other side:

  • On MLS Bench Lite, K2.7 Code (35.1) is virtually tied with GPT-5.5 (35.5)
  • On MCP Mark Verified, K2.7 Code (81.1) beats Claude Opus 4.8 (76.4)
  • K2.7 Code is open-source. GPT-5.5 and Opus 4.8 are not.

An open-weight model matching or beating the most expensive closed-source models on some benchmarks — that’s a meaningful signal regardless of where you stand on the open vs closed debate.

1T Parameters, 32B Active — Architecture Details

ParameterValue
ArchitectureMixture-of-Experts (MoE)
Total Parameters1T
Activated Parameters per Token32B
Layers61
Experts384
Experts per Token8
Context Length256K
AttentionMLA (Multi-head Latent Attention)
Vision EncoderMoonViT (400M params)

384 experts, 8 active per token — classic MoE tradeoff of capacity versus compute. The MLA attention mechanism (originally from DeepSeek V2) keeps KV cache memory in check.

The MoonViT vision encoder is worth mentioning — K2.7 Code accepts text, image, and video input. You can screenshot a UI design and have it write the frontend code, or photograph a whiteboard architecture diagram for analysis.

Pricing: Open-Source But Not Free

Via the Kimi API:

ModelInput (cache miss)Input (cache hit)OutputContext
kimi-k2.7-code$0.95/M$0.19/M$4.00/M262,144 tokens

Compare that to Claude Sonnet 4.6 at $3.00/$15.00 — input is 3x cheaper, output nearly 4x cheaper. The API supports automatic context caching, so repeated context drops to $0.19/M. Long multi-turn sessions get significantly cheaper.

Since the weights are open (Modified MIT License), you can also self-host with vLLM, SGLang, or KTransformers. A 1T-parameter model isn’t trivial to deploy, but native INT4 quantization is available, and the community has Ollama builds and various quantized versions ready.

Kimi Code subscription plans (annual billing, monthly price):

PlanPriceBest for
Moderato$15/moRegular coding, weekly refreshed quota
Allegretto$31/moLarger quota + higher concurrency
Allegro$79/moIntensive development, complex projects
Vivace$159/moMaximum quota, large codebases

Practical Gotchas

A few things to watch out for:

  1. Thinking mode is mandatory. K2.7 Code doesn’t support non-thinking mode. If you disable thinking in Kimi Code, requests automatically fall back to K2.6.
  2. It’s a coding model, period. For writing, analysis, or general conversation, Moonshot AI recommends K2.6 instead.
  3. Temperature and sampling. The recommended settings are temperature=1.0 and top-p=0.95 — higher than most models’ defaults. Adjust accordingly.

Who Should Try K2.7 Code

ScenarioRecommendationWhy
GitHub Copilot usersTry itSelect it directly in the model picker, zero migration cost
Cost-conscious teamsRecommendedAPI pricing is ~1/3 to 1/4 of Claude
Bilingual (CN/EN) projectsStrongly recommendedChinese coding comprehension is a genuine strength
Self-hosting requirementsWorth evaluatingOpen weights, Modified MIT license
Maximum coding performanceNot yetProgram Bench and other hard benchmarks still trail GPT-5.5
Non-coding tasksNot recommendedMoonshot AI explicitly says use K2.6 for general-purpose work

The Bottom Line

Kimi K2.7 Code isn’t just another open-source model release. It’s the first open-weight model in GitHub Copilot’s model picker. It beats Claude Opus 4.8 on MCP Mark Verified. It costs roughly a third of mainstream closed-source models. And it uses 30% fewer thinking tokens than its predecessor.

The weaknesses are clear too — it trails GPT-5.5 on the hardest coding benchmarks, forced thinking mode limits flexibility, and self-hosting a 1T model still requires serious infrastructure.

But for most real-world development workflows, K2.7 Code offers something that didn’t exist before: a good enough, cheap enough, open-source coding model that sits right in your existing tools. That changes the competitive landscape.