API

Call P-Video

Every model takes the same request, so switching to P-Video is a change to the model field. These samples are written for its own contract and send as they are.

import Mynth from "@mynthio/sdk";

const mynth = new Mynth();

const task = await mynth.video.generate({
  model: "prunaai/p-video",
  prompt: "A lighthouse beam sweeping over waves at night",
  duration: 5,
  size: "16:9_720p",
});

console.log(task.urls[0]);

Specifications

What P-Video accepts

Read from the same registry the API validates against. A request outside it is refused when the task is created, before anything is charged.

Modes and inputs

Text → Video: Prompt only
Image → Video: 1 first frame image · required

Input roles

first_frame: The frame the video opens on

A role goes in inputs[].as. Leave it out, or send auto, and Mynth assigns one the model accepts.

Output

Resolution: 720p (default), 1080p
Duration: 1–10 s · default 5 s
Audio: Generated · on by default

Prompt

Negative prompt: Not supported. Dropped before the provider call, no error

The contract as GET /models returns it

{
  "modes": {
    "txt->vid": {},
    "img->vid": {
      "inputs": {
        "rules": [
          {
            "type": "image",
            "kind": "first_frame",
            "min": 1,
            "max": 1
          }
        ],
        "maxTotal": 1
      }
    }
  }
}

Pricing

What it costs

Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works

Rates

720p: $0.005 / sec
1080p: $0.01 / sec
Audio: Included

Estimate a request

Resolution

Duration

5 s

$0.0255 s × $0.005

Held when the task is created, and charged only if the video renders.

Seedance 2.0 Mini
bytedance/seedance-2.0-mini
Text → VideoImage → VideoAudio
from $0.036 / sec
Grok Imagine Video 1.5
xai/grok-imagine-video-1.5
Text → VideoImage → VideoAudio
from $0.08 / sec
Gemini Omni Flash 1.1
google/gemini-omni-flash-1.1
Text → VideoImage → VideoAudio
from $0.10 / sec