Grok Imagine Video v1.5 Developer Reference-to-Video by XAI
xai/grok-imagine-video-v1.5-developer/reference-to-videoxAI Grok Imagine Video v1.5 generates video guided by 1-7 reference images plus an optional reference voice, with native synchronized audio. Up to 15s at 480p or 720p.
Set up the model and run your first generation.
Ctrl ⏎Examples
Runs published with this model. Load one into the playground and change whatever you like.
Handheld UGC-style clip. The person from <IMAGE_0> looks at the camera and speaks warmly. Casual phone-camera framing, soft indoor light, short social clip.
duration: 5resolution: 720paspect_ratio: 9:16image_urls: 1 file(s)
Providers
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | not verified | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.
Grok Imagine Image 2.0 Developer Edit$0.014Grok Imagine Image 2.0 Developer Text-to-Image$0.014Grok Imagine Image 2.0 Edit$0.040Grok Imagine Image 2.0 Text-to-Image$0.040xAI TTS v1$0.015Grok Imagine Video v1.5 Reference-to-Video$0.400Grok Imagine Video v1.5 Developer Text-to-Video$0.140Grok Imagine Video v1.5 Text-to-Video
Questions
- $0.140 per generation on ElliSekiz — the provider's own price, billed 1:1 from a prepaid USD balance with no markup and no subscription. Failed generations are free.
- POST to https://ellisekiz.ai/api/v1/generations with "model": "xai/grok-imagine-video-v1.5-developer/reference-to-video" and your prompt, authenticated with an ElliSekiz API token. The API tab on this page has the full request for this model, including its own parameters.
- image_urls, voice_ids, duration, resolution, aspect_ratio — each one is in the playground form on this page and in the API example.
$0.140 per generation (≈5s clip) · billed 1:1 at provider cost · compare providers