Veo 3.1

Veo 3.1 is our latest line of video generation models. This pagedocuments the capabilities and features of Veo 3.1.

3.1 Generate

Model IDveo-3.1-generate-001
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Video
Capabilities
Usage types
Technical specifications
Videos
  • Video lengths: 4, 6, or 8 seconds; reference image to video only supports 8 seconds.
  • Maximum number of output videos per prompt: 4
  • Image-to-video maximum input image size: 20 MB
  • Supported aspect ratios: 9:16, 16:9
  • Supported input resolutions: 720p, 1080p
  • Supported output resolutions: 720p, 1080p
  • Supported framerates: 24 FPS
  • Supported MIME types:
    video/mp4
Prompt languages
  • English
Quotas
  • Regional online prediction requests per base model per minute per base model: 50

3.1 Fast Generate

Model IDveo-3.1-fast-generate-001
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Video
Capabilities
Usage types
Technical specifications
Videos
  • Video lengths: 4, 6, or 8 seconds.
  • Maximum number of output videos per prompt: 4
  • Image-to-video maximum input image size: 20 MB
  • Supported aspect ratios: 9:16, 16:9
  • Supported input resolutions: 720p, 1080p
  • Supported output resolutions: 720p, 1080p
  • Supported framerates: 24 FPS
  • Supported MIME types:
    video/mp4
Prompt languages
  • English
Quotas
  • Regional online prediction requests per base model per minute per base model: 50

Preview with production use

The Image-to-Video feature is a Generative AI Preview offering, subject to the "Pre-GA Offerings Terms" of theGoogle Cloud Service Specific Terms, as well as theAdditional Terms for Generative AI Preview Products. For this Generative AI Preview offering, Customers may elect to use it for production or commercial purposes, or disclose Generated Output to third-parties. Pre-GA products and features may have limited support, and changes to pre-GA products and features may not be compatible with other pre-GA versions. For more information, see thelaunch stage descriptions.

3.1 Generate

Model IDveo-3.1-generate-preview
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Video
Capabilities
Usage types
Technical specifications
Videos
  • Video lengths: 4, 6, or 8 seconds; reference image-to-video only supports 8 seconds.
  • Maximum number of output videos per prompt: 4
  • Image-to-video maximum input image size: 20 MB
  • Supported aspect ratios: 9:16, 16:9
  • Supported output resolutions: 720p, 1080p, 4k
  • Supported input resolutions: 720p, 1080p, 4k
  • Supported framerates: 24 FPS
  • Supported MIME types:
    video/mp4
Prompt languages
  • English Preview feature
Quotas
  • Regional online prediction requests per base model per minute per base model: 10

Preview with production use

The Image-to-Video feature is a Generative AI Preview offering, subject to the "Pre-GA Offerings Terms" of theGoogle Cloud Service Specific Terms, as well as theAdditional Terms for Generative AI Preview Products. For this Generative AI Preview offering, Customers may elect to use it for production or commercial purposes, or disclose Generated Output to third-parties. Pre-GA products and features may have limited support, and changes to pre-GA products and features may not be compatible with other pre-GA versions. For more information, see thelaunch stage descriptions.

3.1 Fast Generate

Model IDveo-3.1-fast-generate-preview
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Video
Capabilities
Usage types
Technical specifications
Videos
  • Video lengths: 4, 6, or 8 seconds.
  • Maximum number of output videos per prompt: 4
  • Image-to-video maximum input image size: 20 MB
  • Supported aspect ratios: 9:16, 16:9
  • Supported output resolutions: 720p, 1080p, 4k
  • Supported input resolutions: 720p, 1080p, 4k
  • Supported framerates: 24 FPS
  • Supported MIME types:
    video/mp4
Prompt languages
  • English Preview feature
Quotas
  • Regional online prediction requests per base model per minute per base model: 50

For Veo pricing information, see theVeosection of theCost of building and deploying AI models in VertexAIpage.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-02-19 UTC.