wan3.0-video-prime

Request parameters and examples for wan3.0-video-prime.

POST /v1/async/videos/generations

Send JSON with Authorization: Bearer <PIXAPI_KEY> and Content-Type: application/json.

Request fields

Send the common fields at the top level. Put the model-specific controls listed below inside providerOptions.

Field	Type	Required	Description
model	string	Yes	wan3.0-video-prime
prompt	string	No	Describe motion, scene, camera, and dialogue; at most 20,000 characters. Optional when valid media is supplied; provide prompt or media.
seconds	integer	Yes	Integer 2–30 seconds; explicitly required.
resolution	string	No	480p / 720p / 1080p. Pixapi default: 1080p.
n	integer	No	Default 1; only integer 1 is supported.
image	string / string[]	No	One public first-frame image URL; JPEG/PNG/WebP/BMP.
providerOptions	object	No	Model-specific options; see the table below.

providerOptions

All fields in this table are nested inside providerOptions, not alongside model.

Field	Type	Description
aspect_ratio	string	adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Default adaptive; image-to-video follows the input image ratio.
seed	integer	-1 (random) or 0–2147483647; matching seeds do not guarantee identical output.
prompt_extend	boolean	Rewrite and expand the prompt for generation; default true.
watermark	boolean	Add a visible AI watermark. Default false.
audio	boolean	Default true; false generates silent video. If false, supplied audio is not used.
last_frame_url	string	Public last-frame image URL. A first frame is required; do not also specify the same frame in media.
media	object[]	Each item contains type and public url; see the media rules below.

Input rules

All media must be publicly accessible HTTP(S) URLs. No Base64, local paths, or external asset IDs. seconds must be a positive number.

media.type: first_frame ≤1, last_frame ≤1; or reference_image ≤10, reference_video ≤5, reference_audio ≤5, file ≤1, link ≤1. First/last frames cannot mix with references/files/links. A last frame requires a first frame. Do not duplicate frames via image / last_frame_url.

Reference videos: MP4/MOV, 1–15s each, total ≤15s, ≥16fps, 240–4096px, ≤100 MB each. Input video duration plus seconds ≤30s. Audio: WAV/MP3, 1–15s each, total ≤15s, ≤15 MB each.

Use either file or link, not both; these require prompt_extend=true. Files ≤100 MB: DOC/DOCX, XLS/XLSX, PPT/PPTX, PDF, TXT, KEY, PAGES, NUMBERS, MD. PDF/Word/presentations/KEY/PAGES ≤50 pages. Links must be accessible without login.

Reference images: JPEG/PNG (no alpha)/BMP/WebP, each edge 240–8000px, ratio 1:8–8:1, ≤20 MB. Address references in the prompt as Image 1, Video 1, etc., numbered separately by media type.

Example

cURL

curl https://api.pixapi.ai/v1/async/videos/generations \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan3.0-video-prime",
  "prompt": "A cinematic scene with smooth camera motion",
  "seconds": 5,
  "resolution": "720p",
  "n": 1,
  "providerOptions": {
    "prompt_extend": true,
    "watermark": false
  }
}'

Python

import os
import requests

response = requests.post(
    "https://api.pixapi.ai/v1/async/videos/generations",
    headers={"Authorization": f"Bearer {os.environ['PIXAPI_KEY']}"},
    json={
  "model": "wan3.0-video-prime",
  "prompt": "A cinematic scene with smooth camera motion",
  "seconds": 5,
  "resolution": "720p",
  "n": 1,
  "providerOptions": {
    "prompt_extend": True,
    "watermark": False
  }
},
)
response.raise_for_status()
print(response.json())

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": "wan3.0-video-prime",
  "prompt": "A cinematic scene with smooth camera motion",
  "seconds": 5,
  "resolution": "720p",
  "n": 1,
  "providerOptions": {
    "prompt_extend": true,
    "watermark": false
  }
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Go

package main

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

func main() {
  body := []byte(`{
  "model": "wan3.0-video-prime",
  "prompt": "A cinematic scene with smooth camera motion",
  "seconds": 5,
  "resolution": "720p",
  "n": 1,
  "providerOptions": {
    "prompt_extend": true,
    "watermark": false
  }
}`)
  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, err := io.ReadAll(resp.Body)
  if err != nil { panic(err) }
  if resp.StatusCode >= 400 { panic(string(result)) }
  fmt.Println(string(result))
}

For asynchronous requests, save the returned id and poll GET /v1/tasks/{id} until completed or failed. See task results and billing.