Skip to main content

​
Model Pricing

​
K3 Series Models

All K3 series models support a 1,048,576-token context window. Note: The Kimi API automatically enables context caching billing for repeated request prefixes, with a default TTL (time-to-live) of 5m. For TTL settings and cost optimization tips, see Best Practices for Context Caching. Batch API Inference: kimi-k3.1-pro and kimi-k3 support batch inference for large-scale tasks that do not require real-time responses, billed at 60% of the standard price.

​
K2 Series Models

All K2 series models support a 262,144-token context window.
Dear Kimi Users, starting October 31, 2026, K2 series models will no longer be available to newly registered users; existing users are not affected. We plan to retire all K2 series models by the end of December 2026, please prepare your migration in advance.
1 MTok = 1,000,000 tokens. All prices above are per MTok consumed. Explanation: Prices exclude applicable taxes. Specific tax obligations are subject to local tax regulations and will be calculated at checkout based on your jurisdiction.

​
Concepts

Model inference on the Kimi API platform is billed on a pay-as-you-go basis, with no subscription plan. It differs from products such as the Kimi membership and Kimi Code. See the product comparison.

​
Billing Unit

Token: the basic unit of text processed by the model. A long word like “antidisestablishmentarianism” may be split into several tokens, while a common short word like “word” usually takes just one. For typical English text, 1 token is roughly equivalent to 3-4 characters. Use the Token Calculation API to get the exact token count of each call.

​
Billing Logic

Model inference APIs bill input and output tokens by usage. For K3 series models, cache writes are billed separately by TTL (5min / 1h); cached input is billed at the cache-hit price only, with no additional cache write charge. If you upload a document, extract its content, and pass the extracted content as model input, that content is also billed by usage. File-related APIs (file content extraction and file storage) are temporarily free: uploading and extracting a document alone incurs no file API charges. For tips on improving cache hit rates and choosing a TTL tier, see Best Practices for Context Caching.

​
Model Notes

See each model’s guide for capabilities and recommended use cases: