Model board / Kimi K3
Kimi K3
latest Moonshot · KimiVerified 2026-10-15 against the pages listed below. Prices are USD per 1M tokens, list rate — no committed-use, enterprise or volume discount.
flat across the full window — no length tiering. cache write $3.00 at the default 5-minute TTL, $6.00 for 1 hour; a hit refreshes the entry at no write charge
cache hit at 10% of input
Licence: Kimi K3 License — a separate agreement above $20M MaaS revenue over 12 months; on-screen credit above 100M MAU or $20M monthly revenue
Watch out
The weights ship under the Kimi K3 License, not the Modified MIT the K2 line carries: a model-as-a-service operator above $20M revenue over any 12 months needs a separate agreement with Moonshot. Reasoning is always on and defaults to max effort. Batch is not offered on K3
What we would use it for
A 1M window with no long-context premium, and weights you can host
What this has cost, week by week
Output price at each refresh since 2026-07-30. A vendor change is the provider changing its price. Our correction means this board changed what it prints and the provider's charge did not move — the two are never merged, because publishing the second as the first would be a price rise that never happened.
Where these numbers came from
https://platform.kimi.ai/docs/pricing/chathttps://huggingface.co/moonshotai/Kimi-K3https://platform.kimi.ai/docs/guide/kimi-k3-quickstart
No number on this page was written that was not read from one of those pages on 2026-10-15. If one is wrong, send us the source URL and it is corrected in the next weekly refresh, with a changelog line saying what was wrong — contact@naderu.com.
Jobs this is one of our picks for
- Deep reasoning — Hard problems that reward thinking tokens (
deep-reasoning)
The rest of the board
This row sits alongside 69 others on the model board, refreshed every week. The same data as JSON, and the terms for using it, are at /board-data.