Skip to main content
AIHubMix provides a unified video-generation API that allows developers to access multiple mainstream models, including:
  • veo series
  • sora series
  • wan seris

​
Request Example

curl -X POST "https://aihubmix.com/v1/videos" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "<model_path>",
    "prompt": "your prompt"
  }'

​
Model Paths

Supported values for model:

​
Parameters

​
prompt
String
required
Natural language description of the desired video. Include camera type, subject, actions, environment, lighting, and camera movement.
​
model
String
One of the supported model identifiers listed above.
​
size
String
Output resolution in width x height format.
  • sora：720×1280（默认）、1280×720
  • veo：720P（默认），1080P
  • wan：480P（832x480、480x832、624x624），720P（1088x832、832x1088、960x960、1280x720、720x1280）和 1080P（1248x1632、1632x1248、1440x1440、1080x1920、1920x1080）。
​
seconds
String
Duration of generated video.
  • sora：4s（default），8s，12s
  • veo：4s，6s，8s（default）
  • wan：5s，10s（0s only supported by wan2.5-t2v-preview）
​
input_reference
File
Reference image used as the first frame. Supported formats:image/jpeg,image/pbg ,image/webp 。
More details：Sora 2 API Reference

​
Usage Examples

​
Generate Without a Reference Image

curl -X POST "https://aihubmix.com/v1/videos" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "sora-2-pro",
    "prompt": "A astronaut floating in space, holding a glowing plant, with Earth and stars in the background, slow-motion movement",
    "size": "720x1280",
    "seconds": "4"
  }'

​
Generate With a Reference Image

curl --location --request POST 'https://aihubmix.com/v1/videos' \
--header 'Authorization: Bearer sk-***' \
--form 'prompt="The kitten is taking a nap under the tree."' \
--form 'model="sora-2"' \
--form 'size="1280x720"' \
--form 'seconds="4"' \
--form 'input_reference=@"xxx=/cat.jpeg"'