Veo

Veo is a video generation model family for realistic motion, cinematic camera movement, and short product storytelling.

Supported durations: seconds must be 4, 6, or 8.

API surface

Operation	Endpoint	Mode
Video generation task	POST /v1/async/videos/generations	Async only

Video generation is async-only. Pixapi returns a submitted task immediately.

Models

Model id	Tier	Notes
veo3.1-lite	Lite	Lowest cost. 4K is not supported by Google.
veo3.1-fast	Fast	Balanced speed and quality.
veo3.1-quality	Standard / Quality	Highest quality.

Pricing

Billed as n × seconds × rate(resolution) credits. Default resolution is 720p.

Model	720p	1080p	4K
veo3.1-lite	4/sec	7/sec	7/sec*
veo3.1-fast	8/sec	10/sec	24/sec
veo3.1-quality	32/sec	32/sec	48/sec

* Lite does not support 4K output; if requested, the 1080p rate applies.

Example: veo3.1-fast + 720p + seconds=8 + n=1 → 8 × 8 × 1 = 64 credits.

Request fields

Field	Type	Required	Description
model	string	Yes	One of veo3.1-lite, veo3.1-fast, or veo3.1-quality.
prompt	string	Yes	Describe the scene, subject, motion, and camera. 1–2000 characters.
seconds	integer	Yes	Duration in seconds. Only 4, 6, or 8.
resolution	string	No	720p (default), 1080p, or 4k.
n	integer	No	Number of outputs. Default 1, range 1–9.
image	string | string[]	No	Public http(s) image URL for image-to-video (jpg/jpeg/png/webp/gif).
providerOptions	object	No	Optional model extensions. See providerOptions below.

providerOptions

Field	Type	Description
aspect_ratio	string	Output aspect ratio: 16:9 or 9:16.

Example

cURL

curl https://api.pixapi.ai/v1/async/videos/generations \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo3.1-fast",
  "prompt": "A slow dolly shot around a premium coffee bag on a cafe table",
  "n": 1,
  "seconds": 8,
  "resolution": "720p"
}'

Python

import os
import requests

response = requests.post(
    "https://api.pixapi.ai/v1/async/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['PIXAPI_KEY']}",
        "Content-Type": "application/json",
    },
    json={
    "model": "veo3.1-fast",
    "prompt": "A slow dolly shot around a premium coffee bag on a cafe table",
    "n": 1,
    "seconds": 8,
    "resolution": "720p"
},
)
response.raise_for_status()
task = response.json()
print(task["id"])

JavaScript

const response = await fetch('https://api.pixapi.ai/v1/async/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.PIXAPI_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "veo3.1-fast",
  "prompt": "A slow dolly shot around a premium coffee bag on a cafe table",
  "n": 1,
  "seconds": 8,
  "resolution": "720p"
}),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const task = await response.json();
console.log(task.id);

Go

package main

import (
  "bytes"
  "fmt"
  "io"
  "net/http"
  "os"
)

func main() {
  body := []byte(`{
  "model": "veo3.1-fast",
  "prompt": "A slow dolly shot around a premium coffee bag on a cafe table",
  "n": 1,
  "seconds": 8,
  "resolution": "720p"
}`)

  req, err := http.NewRequest(
    "POST",
    "https://api.pixapi.ai/v1/async/videos/generations",
    bytes.NewBuffer(body),
  )
  if err != nil {
    panic(err)
  }
  req.Header.Set("Authorization", "Bearer "+os.Getenv("PIXAPI_KEY"))
  req.Header.Set("Content-Type", "application/json")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer resp.Body.Close()

  result, _ := io.ReadAll(resp.Body)
  fmt.Println(string(result))
}

Response

Pixapi returns a submitted task. Poll GET /v1/tasks/{id} for the final result.

{
  "status": "submitted",
  "id": "task_01KPQ7J7DWB7QZ3WCEK3YVPBRA",
  "progress": 0,
  "created_at": 1703884800,
  "model": "veo3.1-fast"
}