Video Generation

Generate videos with any model available on ImageRouter.

Unified endpoint

Supports both Text-to-Video and Image-to-Video generation. Requests are encoded as multipart/form-data.

Request

Curl

curl 'https://api.imagerouter.io/v1/openai/videos/generations' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-F 'prompt=YOUR_PROMPT' \
-F 'model=ir/test-video' \
-F 'size=auto' \
-F 'seconds=auto' \
-F 'response_format=url' \
-F 'image[]=@your_image1.webp'

Javascript

const formData = new FormData()
formData.append('prompt', 'YOUR_PROMPT')
formData.append('model', 'ir/test-video')
formData.append('size', 'auto')
formData.append('seconds', 'auto')
formData.append('response_format', 'url')

// Add your image files (up to 16)
const imageFile1 = await fetch('your_image1.webp').then(r => r.blob())
formData.append('image[]', imageFile1)

// or from local file
const imagePath = '/home/phoenics/projects/Image router/materials/logo.png'
const imageBuffer = fs.readFileSync(imagePath)
const imageBlob = new Blob([imageBuffer], { type: 'image/png' })
formData.append('image[]', imageBlob, path.basename(imagePath))

const response = await fetch('https://api.imagerouter.io/v1/openai/videos/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: formData
})

const data = await response.json()
console.log(data)

Python

import requests

url = "https://api.imagerouter.io/v1/openai/videos/generations"
headers = {
  "Authorization": "Bearer YOUR_API_KEY"
}

payload = {
  "prompt": "YOUR_PROMPT",
  "model": "ir/test-video",
  "size": "auto",
  "seconds": "auto",
  "response_format": "url"
}

with open("your_image1.webp", "rb") as img1:
  files = {
      "image[]": img1
  }
  response = requests.post(url, files=files, data=payload, headers=headers)
  print(response.json())

Parameters

• model required Video model to use for generation.

• prompt optional Text input for generating videos. Many models require prompt, but not all.

• size optional Accepted values are different for each model. Some models and providers completely ignore size.

  • auto [default] - Uses the default recommended size for each model.
  • WIDTHxHEIGHT (eg 1024x576)

• seconds optional Duration of the video in seconds. Accepted values vary by model.

  • auto [default] - Uses a default duration for each model.
  • Numeric value (eg 5, 10) - Specific duration in seconds (check model details page for supported values).

• response_format optional

  • url [default] - Returns the video URL hosted on ImageRouter’s servers. The video is saved in your logs. and is publicly accessible with the URL if you share it.
  • b64_json - Returns the video as base64-encoded JSON data. The video is saved in your logs. and is publicly accessible with the URL if you share it.
  • b64_ephemeral - Same as b64_json but the video is not saved in our system. The provider may still have it.

• image[] optional Input file for Image-to-Video generation. (Supported models have “image-to-video” label here.)

Response

The OpenAI compatible response makes sure you can use ImageRouter anywhere GPT-Image is already implemented.

{
  "created": 1769286389027, // timestamp
  "data":[
    {
      "url": "https://storage.imagerouter.io/fffb4426-efbd-4bcc-87d5-47e6936bf0bb.mp4"
      // or "b64_json": "...", if you select a different response_format
    }
  ],
  "latency": 6942,
  "cost": 0.004
}

JSON endpoint

This endpoint exists for compatibility reasons (so ImageRouter can be used with the OpenAI SDK). File uploads are not possible with application/json encoding, so Image-to-Video generation is not supported for this endpoint.

Endpoint comparison

Detail	Unified endpoint	JSON endpoint
Text-to-Video	✅	✅
Image-to-Video	✅	❌
Request encoding	multipart/form-data	application/json
Compatible with	GPT Image (edit)	GPT Image

Request

Curl

curl 'https://api.imagerouter.io/v1/openai/videos/generations' \
-H 'Authorization: Bearer YOUR_API_KEY' \
--json '{
  "prompt": "YOUR_PROMPT",
  "model": "ir/test-video",
  "size": "auto",
  "seconds": "auto",
  "response_format": "url"
}'

Javascript

const url = 'https://api.imagerouter.io/v1/openai/videos/generations'
const payload = {
  prompt: 'YOUR_PROMPT',
  model: 'ir/test-video',
  size: 'auto',
  seconds: 'auto',
  response_format: 'url'
}

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify(payload)
})

const data = await response.json()
console.log(data)

Python

import requests

url = "https://api.imagerouter.io/v1/openai/videos/generations"
payload = {
  "prompt": "YOUR_PROMPT",
  "model": "ir/test-video",
  "size": "auto",
  "seconds": "auto",
  "response_format": "url"
}
headers = {
  "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Parameters

Same as the parameters for the Unified Form-Data endpoint, except image parameters are not supported.

Response

Same as the response for Unified Form-Data endpoint.