LTX-2.3-Fast

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

curl -X POST \
    -H "Authorization: bearer $DEEPINFRA_API_KEY"  \
    -F 'prompt=A handheld medium shot follows a golden retriever puppy bounding across a sunlit autumn backyard, dry leaves crunching loudly under its paws and the tag on its collar jingling with every step. Birds chirp in the trees overhead and a breeze rustles the branches. The puppy skids to a stop at a big pile of leaves, yips once, then leaps straight in with a loud rustling crunch. Leaves burst upward and drift down in slow spirals as its head pops out, a leaf stuck to one ear, while children laugh and cheer off-screen. The camera dips to eye level as the puppy gives a loud little sneeze and shakes itself off, collar jingling.'  \
    'https://api.deepinfra.com/v1/inference/Lightricks/LTX-2.3-Fast'
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