Minimal text-to-video request
curl -X POST "https://api.oneinfer.ai/v1/ula/generate-video" \
-H "Authorization: Bearer $ONEINFER_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "Minimax/minimax-h3-max",
"prompt": "A cinematic tracking shot through a rain-lit night market",
"resolution": "768P",
"duration": 5,
"aspect_ratio": "16:9"
}'Core parameters
| Field | Value |
|---|---|
| model | Minimax/minimax-h3-max |
| prompt | Required text prompt |
| duration | 5 to 15 seconds |
| resolution | 480P or 768P |
| aspect_ratio | Text-to-video only |
Ready to test the workflow?
Do not send the upstream slug
The upstream fal slug is minimax/h3-max. When calling OneInfer, use Minimax/minimax-h3-max instead so catalog lookup, pricing and analytics resolve to the canonical model.