Generate video

All video models use POST /v1/video/generations. There are two flows: text-to-video and image-to-video.

Text to video#

Describe the scene in prompt. Choose resolution, aspect_ratio and duration. Cost is per second × duration.

curl -X POST "https://api18.dev/v1/generate?wait=true" \
  -H "Authorization: Bearer $API18_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"centaurus-1.0-text-to-video","prompt":"A cinematic shot of a city street at night, neon reflections on wet pavement, slow dolly-in","resolution":"720p","aspect_ratio":"16:9","duration":5}'

# → returns the finished job; the output URL is at .data[0].url

Image to video#

Pass an image (public URL) to animate. The video's aspect ratio follows the image. Some models also accept negative_prompt, shot_type or enable_prompt_expansion — see each model's page.

curl -X POST "https://api18.dev/v1/generate?wait=true" \
  -H "Authorization: Bearer $API18_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"centaurus-1.0-image-to-video","image":"https://example.com/your-image.jpg","prompt":"Gentle camera push-in, hair and fabric moving softly in the breeze","resolution":"720p","duration":5}'

# → returns the finished job; the output URL is at .data[0].url

The image must be a public URL reachable by our server (not a local path or data URI).

Video models#

Centaurus 1.0 — Text to Video · Centaurus 1.0 — Image to Video · Hera 1.0 — Image to Video · Zeus 1.0 — Image to Video · Zeus 1.0 — Image to Video 480p