Skip to content
Kimi K3: Query a Million-Token Repo for Pennies — ContentBuffer guide

Kimi K3: Query a Million-Token Repo for Pennies

K
Kodetra Technologies··8 min read Intermediate

Summary

Point the OpenAI SDK at Moonshot's 2.8T K3, load a whole repo, and cut cost with caching.

Kimi K3: Query a Million-Token Repo for Pennies

On July 16, 2026 Moonshot AI shipped Kimi K3, a 2.8-trillion-parameter open Mixture-of-Experts model with a 1M-token context window. It is the largest open-weight model released to date, and on Artificial Analysis it lands at an Elo of 1,547, sitting just behind Claude Fable 5 and ahead of most closed frontier systems. Within a day it was the top thread across the local-model and coding communities, and for good reason: it is genuinely useful and it is cheap to run through the API.

Keep reading — it's free

Enter your email to keep reading — plus the best of AI & tech, daily. Free, forever.

or

Already a member? Sign in

Comments

Subscribe to join the conversation...

Be the first to comment