reasoning_effort takes low, high, or max (default max); temperature and top_p are fixed upstream.
Try it in the browser: Kimi K3.1 Pro API playground. For a faster serving of the same weights, use moonshotai/kimi-k3.1-pro-highspeed.
Model
Supported Endpoints
All three API formats are supported:- Chat Completions —
POST /v1/chat/completions - Responses —
POST /v1/responses - Messages —
POST /v1/messages
Example
Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.