Chat models › Deepseek

DeepSeek V4.1 Flash

> DeepSeek V4.1 Flash API is an OpenAI Responses–compatible endpoint that accepts a plain string or a structured input array, thinks deeply by default, and supports function calling, image understanding, and structured JSON output. <CardGroup cols={2}> <Card title="Thinking Control" icon="🧠"> Deep thinking is on by default, with seven effort levels to tune. </Card> <Card title="Multimodal Input" icon="🖼️"> Supports mixed text and image inputs in a single message. </Card> <Card title="Tools & Structured Output" icon="✨"> Custom function calling, and answers constrained to JSON. </Card> <Card ti

chat Deepseek 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": "deepseek-v4-1-flash"
}

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.