All models
All models below are called via the unified async endpoint POST /v1/videos. Open one to see its sizes, duration, reference-image rules and billing.
| Model | Type | Description |
gpt-image-2 | Image | General image generation, text/img-to-image, 27 fixed sizes. |
nano-banana-pro | Image | Any-size image generation, auto-snaps to nearest ratio. |
nano-banana-2 | Image | nano-banana family, any-size image generation. |
veo_3_1 | Video | Veo 3.1 text-to-video, 8 seconds. |
veo_3_1-fl | Video | Veo 3.1 image-to-video (first/last frame). |
veo_3_1-components | Video | Veo 3.1 image-to-video (reference images). |
grok-imagine-1.0-video | Video | Grok Imagine text/img-to-video, discrete durations. |
grok-imagine-video-1.5 | Video | Grok Imagine 1.5: text-to-video, image-to-video and multi-image reference, 4–15 s. |
omni_flash_8s | Video | Omni video (8s): text · image · first/last frame. |
omni_flash_10s | Video | Omni video (10s): text · image · first/last frame. |
omni_flash_abra_edit | Video | Omni video editing, per-resolution · per-call. |