Moonshot API Complete Guide: From Kimi K2 to K3 and Beyond
Moonshot AI has rapidly evolved from a promising Chinese AI lab into one of the most important model...
Tag archive
Moonshot AI has rapidly evolved from a promising Chinese AI lab into one of the most important model...
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...

A buyer opens your marketplace app and says: "Find me running shoes under $120, size 10, from a...
Kimi K2.7 Code for Local AI in 2026: VRAM Requirements, the 1T-Parameter Reality, and Which GPU Crosses Into Usable Speed
Composer 2.5 scores 62 on the Coding Index at 60× lower cost than top rivals. How to select it, set the right billing tier, prompt with succ
Moonshot AI's Kimi K2.7 Code drops into Claude Code with three environment variables. I tested it on real coding benchmarks — here's how it stacks up against Claude Sonnet 4 and Opus 4.
Kimi K2.6 for Local AI in 2026: What VRAM and System RAM You Need to Actually Run the 1T-Parameter MoE Coding Leader
Kimi K2 needs 24GB+ VRAM for Q4 local inference. RTX 4090 at $1,600 is the consumer sweet spot. 5 GPUs ranked for agentic workflows in 2026.
Moonshot AI's Kimi K2.6 hits 80.2% SWE-bench with 300 parallel sub-agents. Developer guide: architecture, API access, Kimi Code CLI, and self-hosting.