Models
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.
gpt-image-2Image
General image generation, text/img-to-image, 27 fixed sizes.
nano-banana-proImage
Any-size image generation, auto-snaps to nearest ratio.
nano-banana-2Image
nano-banana family, any-size image generation.
veo_3_1Video
Veo 3.1 text-to-video, 8 seconds.
veo_3_1-flVideo
Veo 3.1 image-to-video (first/last frame).
veo_3_1-componentsVideo
Veo 3.1 image-to-video (reference images).
sora-2-openai-12sVideo
Sora 2 text/img-to-video, 12 seconds.
grok-imagine-1.0-videoVideo
Grok Imagine text/img-to-video, discrete durations.
grok-imagine-video-1.5-previewVideo
Grok Imagine 1.5, img-to-video only, continuous duration.
omni_flash_8sVideo
Omni video (8s): text · image · first/last frame.
omni_flash_10sVideo
Omni video (10s): text · image · first/last frame.
omni_flash_abra_editVideo
Omni video editing, per-resolution · per-call.