Kimi K3
> Kimi K3 is an OpenAI Responses–compatible endpoint that supports chat, function calling, image input, streaming, and reasoning, with a **1M-token** context window. <CardGroup cols={2}> <Card title="Reasoning" icon="brain"> Reasoning is on by default. `reasoning.effort` can be `low` / `medium` / `high`. </Card> <Card title="Image input" icon="image"> Mix text and images in a single message. </Card> <Card title="Function calling" icon="wand-magic-sparkles"> Custom function calling, with optional JSON-constrained answers. </Card> <Card title="Unified endpoint" icon="code"> Use the unified <code
chat Kimi price on request
Request
POST https://app.video-blade.com/api/v1/generations
X-API-Key: vb_…
Content-Type: application/json
{
"callback_url": "https://your-app.example/callbacks/video-blade",
"input": {},
"model": "kimi-kimi-k3"
}
Input parameters
Parameters for this model are documented on request.
Pricing
Price on request; the charge is settled from actual consumption with the chat coefficient ×1.25. See Pricing & tokens.