veo31-fast is the Fast video model in the Google Veo 3.1 series, suitable for turning text concepts or static images into dynamic shots and quickly comparing different creative directions. It supports text-to-video, single-image first-frame guidance, two-image first-and-last-frame transitions, and visual extension of existing videos. With landscape and portrait aspect ratios and asynchronous task processing, it can be used for ad drafts, product showcases, and storyboard previews.
Clarify capacity, inputs and outputs, and invocation methods before choosing a model.
The above lists the actual creation and invocation specifications for veo31-fast on this platform; native capabilities of the series are not automatically considered all features available through this entry point.
Discover what veo31-fast can bring to your work.
Text-to-video is ideal for the creative stage when visual assets are not yet available. Enter the subject, environment, action, and camera changes to generate videos for review. You can keep the scene fixed while adjusting only camera movement or action descriptions to compare different creative directions; Fast is better suited to this workflow of exploring first and selecting afterward.
Image-to-video is not simply about adding reference images: one image defines the start of a shot, while two images guide both the start and end. Combined with prompts that describe the intermediate action, it can create product reveals, scene changes, or storyboard transitions. It is suited to projects with existing key visuals and makes it more intuitive to compare different transition options.
With video extension, you can continue actions or camera changes after an already generated clip and use new prompts to guide subsequent content. Extension results can also be extended again, making it suitable for building shots segment by segment. Both generation and extension support asynchronous processing, so applications can first save the task identifier, then receive the completed result and video link.
Start with specific tasks to find where the model can make an impact.
Enter a product theme, usage environment, and opening action to create different shot drafts for the same advertising concept. Vertical videos can be used for mobile creative reviews, while horizontal videos can be used for presentations or storyboard discussions. The deliverables are playable video candidates that help teams assess visual direction instead of relying only on written scripts to imagine the final result.
Use a product image as the first frame, describe the presentation action and camera movement, and generate a dynamic presentation draft; if a target end image already exists, you can submit both the first and last images to explore the change between the two states. It is suitable for product displays, packaging reveals, and concept demonstrations, though product form and details should still be checked before final use.
Turn storyboard keyframes into video to see whether scene transitions match the narrative intent; if a shot needs to continue moving forward, use the video ID from the generated result to call the extension feature. The deliverables can be used for director discussions, preliminary editing rhythm tests, or concept presentations, helping clarify how shots connect before formal production.
Choose based on task complexity, input materials, and expected results.
When the task focuses on comparing multiple prompts, opening actions, or first-to-last-frame transitions, prioritize veo31-fast. If you place greater emphasis on the refined presentation of the final visuals, use the same materials to compare with veo31 in Quality mode. The trade-off between the two should be based on specific shot results; do not interpret Fast as a version with fixed processing time or as better suited for every task.
veo31-fast is suitable for text-only creation, as well as using one or two images to control the start and end of a shot. If the task is to combine elements from multiple images, choose veo31-fast-ingredients, whose creation method requires image input. The two solve different problems: the former emphasizes temporal start-to-end changes, while the latter emphasizes combining content from multiple images, so their image rules should not be interchanged.
From a small-scale task to production integration.
Define the goal, required inputs, and output requirements, using real business examples as a starting point.
Open the trial page, confirm the parameters supported by this entry point, then submit a small-scale task to review the results.
Keep the complete model ID, use the request format specified in the documentation, and confirm billing rules on the Pricing page.
Before formal use, understand the output quality and capability scope.
Answers to common questions about using veo31-fast.
Submit model=veo31-fast, action=text2video, and prompt to /veo/videos. The prompt can be organized by subject, scene, action, and camera changes; set aspect_ratio=9:16 when you need portrait orientation. After completion, get the video from video_url in the result.
When using image2video, one image is used for first-frame guidance, while two images are used for first-and-last-frame guidance. Put the image links in image_urls, and use prompt to describe the desired actions or transitions in between. This model is not a blending mode that freely combines multiple images into a scene.
You can select resolution=1080p during generation, or use the get1080p action on an already generated video and submit the corresponding video_id. Generation, obtaining a higher-resolution version, and extending are different actions; extension requests use the 720p or 1080p option of /veo/extend.
Submit model=veo31-fast and data[].id from the generation result as video_id to /veo/extend, and you can optionally add prompt to guide the subsequent footage. Extension results can also be extended further; save the task ID and video ID separately to avoid using the task query identifier for extension.
You can enter Chinese prompts and enable automatic translation with translation=true. For application integration, you can set async=true, obtain task_id first, and then query the result; you can also provide callback_url to receive completion notifications, then save the video ID and download link for subsequent production.
Model information · Updated: 2026-10-01. See the API and pricing sections for call parameters and billing rules.
Start with a clear goal and evaluate whether it suits your work based on real results.
Pricing
$0.0685–$0.48· per generation
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs