LTX-2.5-Pro

You can use cURL or any other http client to run inferences:

curl -X POST \
    -H "Authorization: bearer $DEEPINFRA_API_KEY"  \
    -F 'prompt=A slow push-in frames a glassblowing workshop at night, the furnace glowing deep orange against soot-dark brick. A woman in her forties with tied-back grey hair, a leather apron and safety glasses turns a long blowpipe, a molten glass bulb glowing at its tip. She lifts the pipe and blows gently, and the bulb swells, its surface catching every flicker of the furnace. Sparks drift upward as she rolls it across a steel table, the glass cooling from white-hot to amber. The camera settles into a close-up of the glass as fine ripples form inside it. The roar of the furnace, the tick of cooling metal and her slow breathing fill the room. She murmurs, "Steady... there it is."'  \
    'https://api.deepinfra.com/v1/inference/Lightricks/LTX-2.5-Pro'
copy

which will give you back something similar to:

{
  "video_url": "/model/inference/pyramid_sample.mp4",
  "seed": "12345",
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0,
    "output_length": 0
  }
}

copy