Centaurus 1.0 — Text to Video
Cinematic text-to-video with crisp detail, stable motion and strong instruction-following. 720p/1080p, multiple aspect ratios, 2–15s clips.
centaurus-1.0-text-to-videovideo$0.20/s @ 720p · $0.30/s @ 1080p (× duration)
Endpoint#
POST /v1/video/generations · Bearer authentication · the response is a job (see jobs & polling).
Parameters#
| Parameter | Type | Details |
|---|---|---|
| model* | string | The model id. Options: "centaurus-1.0-text-to-video". |
| prompt* | string | What to generate. Max 2500 characters. |
| resolution | string | Output resolution. Options: 720p, 1080p. Default: 720p. |
| aspect_ratio | string | Frame shape. Options: 16:9, 9:16, 1:1, 4:3, 3:4. Default: 16:9. |
| duration | integer | Clip length in seconds. Options: 2–15. Default: 5. |
| seed | integer | Reproducible results. Omit for a random seed. |
| negative_prompt | string | Things to avoid in the output. |
| enable_prompt_expansion | boolean | Auto-expand a short prompt into a richer script. Default: false. |
* required. model and prompt are always needed.
Example#
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].urlIntegrating with an AI assistant? Paste this model's llms.txt into your assistant — it contains just this model, ready to use.