Using Kimi K2.7-Code on Moonshot AI Kimi
Implementation guide · Kimi K2 · Moonshot AI
Moonshot AI Kimi exposes Kimi K2.7-Code through model ID kimi-k2.7-code. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-25. Next refresh: weekly.
Quick Start
- 1
- 2Use the Moonshot AI Kimi SDK or REST API to call
kimi-k2.7-code— see the documentation for request format. - 3
Code Examples
Pricing on Moonshot AI Kimi
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.95 |
| Output tokens | $4.00 |
| Image input | $1.00 |
Capabilities
About Kimi K2.7-Code
Kimi K2.7-Code is Moonshot AI's coding-focused multimodal model released June 12, 2026, built on Kimi K2.6. Uses the same 1-trillion-parameter MoE architecture (32B active parameters, 384 experts with 8 selected per token, 61 layers) with a 262K context window and MoonViT vision encoder (400M parameters). Reports +21.8% on Moonshot's Kimi Code Bench v2, +11.0% on Program Bench, +31.5% on MLS Bench Lite versus K2.6, with approximately 30% fewer reasoning tokens. Forces thinking mode on by default and preserves reasoning content across multi-turn interactions for agentic use. Available via Kimi platform API and HuggingFace under Modified MIT license.