veo31 is the quality-first video model in the Google Veo 3.1 series, suitable for turning text concepts, product stills, and storyboard images into dynamic shots. It supports text-to-video, first-frame and first-and-last-frame image-to-video, and can continue extending generated clips. Compared with Fast models designed primarily for rapid drafting, veo31 is better suited for quality-first asset production and shot review.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Clarify capacity, inputs and outputs, and invocation methods before selecting a model.
The above are the veo31 invocation specifications on this platform; generation and extension each use their own resolution options, and series capabilities should not be considered universally supported across all operations.
Learn what veo31 can bring to your work.
Image-to-video can begin from a single first frame, or use two images to define the start and end points. Compared with using text alone, this approach establishes the composition at both ends of the shot first, then uses prompts to describe the action in between, camera movement, and the transition process. It is suitable for product reveals, scene transitions, and storyboard previews.
veo31 belongs to Quality mode and is suitable for tasks where review focuses on visual presentation rather than rapid drafting. During generation, you can choose landscape or portrait aspect ratios and resolution options such as 1080p and 4k, allowing the same concept to serve both landscape displays and portrait content; compositions should be redesigned for the target aspect ratio.
Generated clips can continue to develop through extension, with new prompts guiding subsequent visuals—for example, pulling the camera back or having the subject continue moving. Asynchronous tasks and callbacks make it easy to connect generation, review, extension, and asset archiving into a workflow, without requiring the application to keep waiting for video generation requests to finish.
Start with specific tasks to find where the model can be effective.
Use a product still as the first frame, describe subject motion, camera angles, and lighting changes, and create dynamic assets for advertising edits. If a clear ending composition already exists, you can add a last-frame constraint for the shot endpoint. After delivery, focus on checking the product's shape, branding, and details, then combine it with subtitles and music.
Submit the starting and ending images from a storyboard as the first and last frames, and generate transition shots for discussion by describing character actions, spatial changes, and camera direction. It is suitable for validating whether visual continuity works, helping directors and design teams evaluate shot plans before formal production, rather than directly replacing the production of an entire film.
Select generated clips that have already passed review, use their video ID to start an extension, and describe the action or shot size desired in the next segment. The returned video link can enter the editing asset library; extension results can also be extended further. Keep the original clips during production to facilitate continuity comparisons and fallback plans.
Choose based on task complexity, input materials, and expected results.
When a task already has a clear composition and you want to conduct quality reviews around a small number of options, prioritize veo31. If you first need to explore many prompts and shot directions, consider veo31-fast, then select options for quality-first production. The two are independent models; when comparing them, keep the image, aspect ratio, and prompt consistent, and do not assume a fixed speed difference.
If the task is to animate existing images or create a transition between specified starting and ending images, veo31's first-frame and first/last-frame methods are more direct. If you want to combine elements from multiple assets into one creation, consider veo31-fast-ingredients. The latter uses multi-image fusion and requires images to be uploaded; it is not equivalent to veo31's first/last-frame control.
From a small-scale task to formal integration.
Define objectives, 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.
Yes. Use /veo/videos, specify model as veo31, action as text2video, and provide a scene prompt. It is recommended to clearly describe the subject, actions, environment, and camera direction; if the composition is already determined, you can also use image2video, using an image as the starting point for the shot.
One image is used for the first frame, allowing the video to begin from a specified image; two images are used for the first and last frames, guiding the shot to connect the start and end points. Submit image links through image_urls, then use prompt to describe the transition. veo31 should not be used as though it fuses three images.
You can set resolution to 4k when generating videos, but the resolution options for /veo/extend are 720p or 1080p; the two operations cannot share the same settings. If the project requires a consistent delivery resolution, determine the extension requirements first, then plan asset generation and final output.
Submit model=veo31 and data[].id from the generation result to /veo/extend, and you can add prompt to guide the subsequent footage. This uses the video ID, not the asynchronous task_id. The new video ID obtained after extension can also be used for the next extension.
You can describe scenes in Chinese and enable automatic translation through translation. After setting async=true, first obtain task_id, then query the task result; you can also set callback_url to receive completion notifications. The video_url in the completed result is used to retrieve the video, while data[].id is used for subsequent video operations.
Model information · Updated: 2026-10-01. For call parameters and billing rules, see the API and pricing sections.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗
↗
↗This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs