Asynchronous Inference
Asynchronous inference is suitable for jobs that involve longer inference times. First, you need to create an generation job. Then, you can check the job status through another interface. Finally, you can download the inference results using the provided download link.
Support Models
hkchengrex/MMAudio
hunyuanvideo-community/HunyuanVideo
Pricing
Temporarily free
Create generation
Replace {{API_TOKEN}}
with your actual token.
Example Request:
Example Response:
Get generation
Replace {{API_TOKEN}}
with your actual token.
Replace {{GENERATION_ID}}
with "id" you got from previous step.
Example Request:
Example Response:
Now you can view or download you generated video through "meta_info.result_download_url".
List generations
Replace {{API_TOKEN}}
with your actual token.
Example Request:
Example Response:
Delete generation
Replace {{API_TOKEN}}
with your actual token.
Replace {{GENERATION_ID}}
with "job_id" you got from previous step.
Example Request:
Example Response:
Last updated