Kimi API pricing

Every Kimi model from Moonshot AI we track, with input, cached input and output cost in USD per 1M tokens. Moonshot’s Kimi models target long-context work at a fraction of Western flagship pricing.

9 models · updated 2026-08-11 · prices in USD per 1,000,000 tokens

9
Models tracked
$0.475
Cheapest input — Kimi K2.7 Code (batch)
$3.00
Priciest input — Kimi K3
1M
Largest context — Kimi K3

Listed in the order Moonshot AI (Kimi) publishes them.

Kimi models with input, cached input and output pricing per million tokens
Kimi K3Via OpenRouter$3.00$0.300$15.001M
Kimi K2.7 CodeVia OpenRouter$0.700$0.150$3.50262K
Kimi K2.7 Code (batch)Via OpenRouter$0.475$0.095$2.00262K
MoonshotAI Kimi LatestVia OpenRouter$2.80$0.290$14.001M
Kimi K2.6Via OpenRouter$0.580$0.098$2.44262K
Kimi K2.5Via OpenRouter$0.570$0.095$2.85262K
Kimi K2 ThinkingVia OpenRouter$0.600$0.150$2.50262K
Kimi K2 0905Via OpenRouter$0.600$2.50262K
Kimi K2 0711Via OpenRouter$0.570$2.30131K

Kimi pricing questions

How much does the Kimi API cost?
Kimi pricing runs from $0.475 to $3.00 per 1M input tokens depending on the model. Kimi K3 costs $3.00 per 1M input and $15.00 per 1M output tokens.
What is the cheapest Kimi model?
Kimi K2.7 Code (batch) is the cheapest Kimi model we track, at $0.475 per 1M input tokens and $2.00 per 1M output tokens.
Does Kimi charge less for cached tokens?
Yes. Cached input is billed at a lower rate than fresh input — for Kimi K3 it is $0.300 per 1M versus $3.00, about 90% cheaper. Caching applies to repeated prompt prefixes.
How often is this Kimi pricing updated?
Every day. Prices are read directly from the published pricing page, normalized to USD per 1,000,000 tokens, and only recorded when a number actually changes — so the history shows real price movements rather than daily noise.

Compare with other providers