AI Model Family

google/veo-3.1-fast-t2v

Google Veo 3.1 Fast text-to-video model. Supports `prompt`, `negativePrompt`, `aspectRatio`, `durationSeconds`, `resolution` (up to 4k), and `personGeneration`.

$0.1200~$0.3500/sec

google/veo-3.1-t2v

text-to-video

Google Veo 3.1 flagship text-to-video model. Supports `prompt`, `negativePrompt`, `aspectRatio`, `durationSeconds`, `resolution` (up to 4k), and `personGeneration`.

$0.4600~$0.6900/sec

google/veo-3.1-fast-i2v

image-to-video

Google Veo 3.1 Fast image-to-video model. Supports two input modes: `image` mode (with optional `lastFrame` and `negativePrompt`) or `referenceImages`-only mode. Resolution up to 4k. See each parameter's description for detailed constraints.

$0.1200~$0.3500/sec

google/veo-3.1-i2v

image-to-video

Google Veo 3.1 flagship image-to-video model. Supports two input modes: `image` mode (with optional `lastFrame` and `negativePrompt`) or `referenceImages`-only mode. Resolution up to 4k. See each parameter's description for detailed constraints.

$0.4600~$0.6900/sec

google/veo-3.1-lite-t2v

text-to-video

Google Veo 3.1 Lite text-to-video model. Supports `prompt`, `negativePrompt`, `aspectRatio`, `durationSeconds`, `resolution` (up to 1080p), and `personGeneration`.

$0.0520~$0.0840/sec

google/veo-3.1-lite-i2v

image-to-video

Google Veo 3.1 Lite image-to-video model. Supports `prompt`, `negativePrompt`, `aspectRatio`, `durationSeconds`, `resolution` (up to 1080p), and `personGeneration`.

$0.0520~$0.0840/sec