← API pricing · Moonshot
Moonshot Kimi API pricing
What each of Moonshot's 2 live models costs on Moonshot AI's own API, in US dollars per million tokens: input, output and input read from the prompt cache. These are the published list prices in the models.dev catalog as of October 25, 2026, refreshed daily. The AW Index column is each model's standing on the bench index.
| Model | Input | Output | Cached input | Context | AW Index |
|---|---|---|---|---|---|
Kimi K3.1 ProMoonshot · kimi-k3.1-pro | $2 | $10 | $0.20 | 1.05M | 86 |
Kimi K3Moonshot · kimi-k3 | $3 | $15 | $0.30 | 1.05M | 27.3 |
What a workload costs on these models, side by side: the cost calculator, filtered to Moonshot.
Quick answers
What is the cheapest Moonshot model on the API?
Kimi K3.1 Pro, at $2 input / $10 output per million tokens, the lowest input and output price of Moonshot's 2 priced models.
What is Moonshot's most expensive model?
Kimi K3, at $3 input / $15 output per million tokens.
Does Moonshot discount cached input?
Yes. On every one of its 2 priced models, input read from the prompt cache costs 90% less than normal input.
Does Moonshot charge more for long prompts?
No. None of its 2 priced models lists a long-prompt rate in the catalog.
How do Moonshot's prices compare with other labs?
Its cheapest model by output price, Kimi K3.1 Pro, ranks 26 of the 39 priced models from every lab on output price. Prices are Moonshot's own list prices from the models.dev catalog as of October 25, 2026; clouds and resellers may charge differently.
Other labs: Anthropic · Google · OpenAI · Meta · xAI · Zhipu AI · Alibaba · MiniMax · Xiaomi · every model in one table · prompt caching prices
Cite this page
Writing about Moonshot's API prices? Copy a link or a citation.
<a href="https://artificialwatch.com/llm-pricing/moonshot">Moonshot Kimi API pricing</a>ArtificialWatch, "Moonshot Kimi API pricing", https://artificialwatch.com/llm-pricing/moonshotMoonshot ships often. Get an alert when its next model lands.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click