| Model | Best for | Pricing |
|---|---|---|
| C1 | Cinematic quality, reference-based generation, action scenes | Per second |
| V6 | General generation, multi-clip output, video extension | Per second |
| Legacy models | Existing integrations that depend on older model behavior | Varies |
| I want to... | Use |
|---|---|
| Generate video from a text prompt | C1 or V6 |
| Animate an image | C1 or V6 |
| Generate video between a first and last frame | C1 or V6 |
| Use reference images to guide generation | C1 |
| Extend an existing video | V6 |
| Make a video template video | Image-to-video endpoint with template_id |
| Change the visual style of a video | Restyle endpoint |
| Swap a subject in a video | Swap endpoint |
| Match mouth movement to speech | Lip Sync endpoint |
| Add sound effects to a video | Sound Effects endpoint |
| Control or replicate motion | Mimic endpoint |
| Edit video content with a prompt | Modify endpoint |
model parameter in supported video generation endpoints.| Model | Best for | Key capabilities |
|---|---|---|
| C1 | Cinematic and reference-based generation | Text-to-video, image-to-video, transition, reference-to-video / Fusion |
| V6 | General generation and production workflows | Text-to-video, image-to-video, transition, video extension |
| Legacy models | Existing integrations | Support varies by model and endpoint |
| Capability | What it does |
|---|---|
| Restyle | Change the visual style of an existing video |
| Swap | Replace a subject or region in a video |
| Mimic | Replicate motion from a reference source |
| Modify | Edit video content using a text prompt |
| Sound Effects | Generate synchronized audio for a video |
| Lip Sync | Align speech to mouth movement in a video |
| Image Template | Generate images from predefined templates |