Model API quickstart

All requests use your ModelFold API Key. Media generation can wait for results, or supported models can use async jobs, polling and callbacks. Use a client timeout of at least 20 minutes for long video requests.

Type	Endpoint
Image	POST /v1/images/generations
Video	POST /v1/videos/generations
Audio	POST /v1/audio/generations
Chat	POST /v1/chat/completions

bash

curl https://modelfold.ai/v1/images/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedream/5-pro-text-to-image","prompt":"A paper boat drifting down a rainy street.","aspect_ratio":"1:1","quality":"basic"}'

See the model list for model-specific required parameters and examples, and the gateway reference for responses, errors and billing. Model parameters go directly in the request body; do not wrap them in input. Replace sample media URLs with your own public files.

Model API quickstart ​

Model API quickstart