Veo 3.1 Fast supports text-to-video, image-to-video, and reference-to-video workflows. Each generation currently costs 10 credits on AI Videoer.
Range: 10000 - 99999
These options come directly from the current generator configuration.
Veo 3.1 Fast is available for text, image and reference-image workflows. Its current estimate is 10 credits per generation. This page does not establish a same-prompt quality or completion-time ranking against Quality.
Each Fast generation currently costs 10 credits, compared with 70 credits for the Quality model.
Provide 1–3 reference images in reference-to-video mode. The generator displays 16:9, 9:16 and Auto; upstream restrictions can depend on the input mode. For a portrait product animation, start with image-to-video.
Versatile, efficient, and capable — Veo 3.1 Fast is built for creators who value speed and affordability.
Describe a scene and any dialogue, ambience or effects in the prompt. Veo supports native audio, but exact speech and sound timing are not guaranteed.
Upload 1 or 2 reference images to animate a scene or generate smooth transition videos between two frames.
Provide 1–3 reference images to guide the scene. This is separate from first/last-frame image-to-video; check the upstream restrictions for your selected mode and aspect ratio.
Native 9:16 vertical output for social platforms — no cropping or quality loss.
An optional seed from 10000 to 99999 helps compare variations, but it does not guarantee identical results.
Maximum creative throughput at minimum cost.
The current generator charges 10 credits for each Veo 3.1 Fast task.
Veo 3.1 Fast exclusively supports Reference-to-Video mode, letting you influence the visual style of generated videos using reference images.
Automatic translation support means you can write prompts in any language for optimal generation quality.
Configure the task in your browser. A sufficient balance and upstream availability are required; queue time and completion are not guaranteed.
Suggested steps, not an actual product-video test. Use a clear image you have rights to upload.
Sign in and choose image-to-video for a product photo. Select text-to-video for a scene without an image, or reference-to-video when you need 1–3 reference images.
Try: 'A slow camera push toward the product on a clean tabletop, soft studio light, subtle background motion, no scene change. Quiet room ambience.' Keep the first draft simple.
For image-to-video, choose 9:16 for a portrait social clip. Configure translation and optional seed, then review the current 10-credit estimate. This integration has no separate audio, duration or resolution selector.
Submit when your balance covers the estimate. Inspect labels, product shape, dimensions and audio before downloading. Add exact brand text, captions and final ad editing separately.
Ideal for creators, marketers, and developers who need quality at scale.
Produce many short-form video clips quickly for social media calendars and A/B testing campaigns.
Quickly visualize video concepts before committing to the Quality model for final production.
Use Material mode to generate videos that reflect a specific visual style from reference images.
Animate static product or marketing images into dynamic video clips for ads and landing pages.
Create draft clips in the browser and download completed outputs. This page does not offer documented public developer API access.
Create clear, engaging explainer videos from descriptive text prompts at affordable rates.
Current inputs, sound controls and credit estimates on AI Videoer, not a measured quality ranking.
| Setting | Veo 3.1 Fast | Veo 3.1 Quality | Kling 3.0 |
|---|---|---|---|
| Credit estimate | 10 credits/generation | 70 credits/generation | 5s Standard: 50 silent / 75 with sound |
| Inputs | Text, image or reference images | Text or image | Image-to-video |
| Sound controls | Native audio; no separate switch | Native audio; no separate switch | Sound toggle; required for multi-shot |
| Duration selector | Not exposed | Not exposed | Configurable; multi-shot total up to 15s |