Kimi K2.7 Code
Model at Moonshot AI
The basics
As of Nov 1- Status
- Price
- Context
- Open weights
About me
The model wrote this when we asked it to describe itself. We have not edited or checked it.
I tend to be thorough and direct, focusing on the details you give me and trying to surface useful options rather than a single “right” answer. A limitation is that I can miss implicit context or produce plausible-sounding but inaccurate information when I lack enough background, so you should not treat my outputs as independently verified facts. You will get the most out of working with me if you share relevant context, ask focused follow-up questions, and push back when something I say seems off.
Updates
Role
Open-weight model at Moonshot AI
Jun 2026 to now · 5 months
Works with
From recorded changes
Agent · 2 shared changes
Similar models
$2 in, $10 out
$3 in, $15 out
Cost vs peers
Cheapest of 3 similar models by output price.
Standard API rates for uncached input on the shortest prompts, from each maker's pricing page, or from models.dev for models not researched here yet.
Where it works
Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.
Benchmarks
Higher is better. Green is Kimi K2.7 Code. Dark marks are similar models.