Veo 3 Fast
Veo 3 Fast is a video generation model from Google that supports image-to-video, audio generation, and flexible aspect ratios.
Fast video generation with audio support
Veo 3 Fast is a video generation model developed by Google, released in May 2025 under the full model identifier veo-3.0-fast-generate-001. It is designed for generating video content from text prompts and images, with a context window of 480 tokens. The model supports optional audio generation alongside video output, making it one of the few video generation models to natively handle both modalities in a single request.
Veo 3 Fast accepts a range of inputs including a starting image, a last-frame image for controlling the end of a clip, and multiple reference images, giving users control over visual consistency across a generation. Additional configuration options include aspect ratio selection, duration, negative prompts, seed values for reproducibility, and an auto-enhance prompt feature. The model is tagged as FAST, indicating it is optimized for lower-latency generation compared to standard variants, and it is suited for workflows that require rapid video output with configurable visual and audio parameters.
What Veo 3 Fast supports
Video Generation
Generates video clips from text prompts or input images, with a 480-token context window for prompt input.
Audio Generation
Optionally generates audio alongside video in a single request, controlled via the Include Audio input toggle.
Image-to-Video
Accepts a starting image URL as input to anchor the first frame of the generated video clip.
Last Frame Control
Accepts a separate last-frame image URL to define the ending frame, enabling controlled transitions between two visual states.
Reference Image Support
Accepts an array of reference images to guide visual style or subject consistency across the generated video.
Prompt Auto-Enhancement
Includes an optional auto-enhance prompt feature that rewrites or expands the input prompt to improve generation quality.
Negative Prompting
Supports a negative prompt text input to explicitly exclude unwanted visual elements or styles from the output.
Reproducible Outputs
Accepts a seed value input so that identical prompts and settings can produce consistent, reproducible video results.
Fast Generation
Tagged as FAST, this variant is optimized for reduced generation latency compared to the standard Veo 3 model.
Aspect Ratio Selection
Allows users to select from multiple aspect ratio options to match the target output format, such as landscape or portrait.
Ready to build with Veo 3 Fast?
Get Started FreeCommon questions about Veo 3 Fast
What is the context window for Veo 3 Fast?
Veo 3 Fast has a context window of 480 tokens, which applies to the text prompt input used to guide video generation.
Does Veo 3 Fast support audio in generated videos?
Yes. The model includes an Include Audio input option that, when enabled, generates audio alongside the video in the same request.
Can I use an existing image as the starting point for a video?
Yes. Veo 3 Fast accepts an Input Image URL to anchor the first frame of the generated clip, and a separate Last Frame Image URL to define the ending frame.
What is the difference between Veo 3 Fast and the standard Veo 3 model?
Veo 3 Fast is tagged as a fast variant, indicating it is optimized for lower-latency video generation. The full model identifier is veo-3.0-fast-generate-001.
What is the current status of Veo 3 Fast?
As of the catalog metadata, Veo 3 Fast has a status of deprecated, meaning it may no longer be actively supported or available for new use.
Is pricing information available for Veo 3 Fast?
No published pricing is listed in the model metadata. You should check Google's official pricing pages or MindStudio's billing documentation for current cost information.
Parameters & options
Optional URL of an input image to animate.
Optional URL of the last frame of the video.
Provide up to 10 references images of the scene, subject, objects, or anything else in the image.
Description of what to exclude from an image.
A specific value that is used to guide the 'randomness' of the generation.
Explore similar models
GoogleVeo 3.1 Lite
Veo 3.1 Lite is a video generation model from Google designed for fast, low-cost video creation with audio support.
GoogleVeo 3.1 Fast
Veo 3.1 Fast is a video generation model from Google designed for rapid text-to-video and image-to-video synthesis.
GoogleGemini Omni 1.1 Flash
Gemini Omni Flash is a video generation model from Google that supports image and video inputs with multimodal editing capabilities.
WanWan 3.0 Prime
KlingKling 3.0 Turbo Pro
Luma LabsRay Flash 2
Ray Flash 2 is a video generation model from Luma Labs designed for fast video creation with configurable resolution, aspect ratio, and keyframe inputs.
Start building with Veo 3 Fast
No API keys required. Create AI-powered workflows with Veo 3 Fast in minutes — free.