Moonshot
Kimi K2.7 Code
Specs
- Input price
- $0.95/M
- Cached input price
- $0.19/M
- Output price
- $4/M
- Context window
- 262.144K tokens
Moonshot's coding-specialized K2 model - 1T total parameters with 32B active per token and a 256K-token context window, tuned for long-horizon agentic coding at a mid-tier price.
Capabilities
- 1T total parameter MoE activating 32B parameters per token
- 256K-token context window for repository-scale coding agents
- Roughly 30% fewer reasoning tokens than K2.6, which lowers cost per completed task
- Higher coding scores than K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, +31.5% on MLS Bench Lite (vendor-reported)
- Function calling for multi-step agent and tool-use pipelines
Best for
- High-volume code generation, review, and refactoring pipelines
- Long-horizon coding agents that need to stay economical at scale
- Routing coding work alongside a reasoning flagship like Kimi K3
Limitations to keep in mind
- Coding-specialized K2-generation model - Kimi K3 is the current flagship for maximum reasoning depth
- At $4.00/M output it is priced above the flash-tier models in this catalog
- 256K context is generous for code but below the 1M-token contexts of newer flagships
HIPAA-compliant hosting
Kimi K2.7 Code is available under our HIPAA-compliant design-partner program, with a signed Business Associate Agreement (BAA), encryption in transit and at rest, and access controls. We are currently onboarding design partners, with general availability coming soon. Run the model behind a unified OpenRouter-style API and swap to another model with a single parameter. For the deployment requirements behind that, see our 2026 guide to HIPAA compliance for AI & LLM APIs.
Pricing in context
Open source models like Kimi K2.7 Code can be served efficiently on optimized inference infrastructure, with savings passed through to you. Exact savings depend on the model and your volume, but open source inference is typically a fraction of the per-token cost of closed-source frontier models on Azure OpenAI or AWS Bedrock - without cloud egress lock-in or minimum commitments. See the full pricing comparison or browse the model catalog.
Related models
Design partner program
Run Kimi K2.7 Code under HIPAA
Join the waitlist to be prioritized. We'll reach out with a qualification call and early access.