Briefing
Prompt to video, briefly.
You write a description and a model returns a short clip. Here is what you get, what it costs to try at two vendors, and what to check before you rely on the result.
Every figure below is quoted from the vendor’s own documentation and linked. Vendors change rates and limits, so check the source before you spend.
What “prompt to video” means.
The prompt is text. Google’s Veo documentation defines it as “The text description for the video. Supports audio cues.” The model turns that description into a generated clip.
Some models also take pictures. Veo accepts an image as “An initial image to animate.” Veo 3.1 and Veo 3.1 Fast also accept reference images: “Up to three images to be used as style and content references.” Veo 3.1 Lite does not.
Google Veo documentation ↗What you actually get.
Google describes Veo 3.1 as “a model for generating 8-second videos (720p, 1080p, or 4k) with natively generated audio.” The same page sets the details:
- A clip is 4, 6 or 8 seconds long.
- It must be 8 seconds when you use extension, reference images, 1080p or 4k.
- Audio is always on.
- The frame rate is 24fps.
- Each request returns one video.
So one request is one short clip. Anything longer than a single clip takes more than one generation, and each generation is billed.
Veo 3.1 parameters ↗What to put in the prompt.
Google’s prompt guide asks for a subject, an action and a style. You can add the camera, the composition, focus and lens, and the ambiance. Put spoken lines in quotes, and describe the sound effects and ambient noise you want.
For example: “A paper kite dips and climbs over a windy beach, handheld documentary look. Low angle, wide shot. A child shouts ‘Higher!’ Wind and gulls in the background.”
Veo prompt guide ↗What it costs to try: Google Veo 3.1.
Through the Gemini API, Veo 3.1 has no free tier: Standard, Fast and Lite are all listed as “Not available” on the free tier. Paid use is charged per second of video, so a clip costs its length times the rate below. The pricing page was last updated 2026-09-24 UTC.
| Model | 720p, per second | 1080p, per second | 4k, per second |
|---|---|---|---|
| Veo 3.1 Standard | $0.40 | $0.40 | $0.60 |
| Veo 3.1 Fast | $0.10 | $0.12 | $0.30 |
| Veo 3.1 Lite | $0.05 | $0.08 | Not supported |
You are not charged if the video is blocked from generating.
Gemini API pricing ↗What it costs to try: Runway.
Runway’s developer API is paid in credits: “Each generation you run on Runway Dev costs credits. Credits can be purchased for $0.01 per credit in the developer portal for a project.” gen4.5 uses 12 credits per second of video and gen4_turbo uses 5. A clip costs its length times the credits per second, times $0.01.
Runway Dev pricing ↗What to watch for.
These limits come from the Veo documentation.
- Watermark. If you are looking for a clip without a watermark, note that Veo videos are watermarked with SynthID, and the watermark can be verified on the SynthID platform.
- Storage. A generated video stays on the server for 2 days, then it is removed. Download anything you want to keep.
- Language. English is fully supported. Other languages have not been evaluated, so test a prompt in another language before you depend on it.
- People and region. In the EU, the UK, Switzerland and the Middle East and North Africa, allow_adult is the only allowed personGeneration value.
Sources.
Try your idea in Visual Rails.
Visual Rails is a studio for AI images, video and visual stories. Studio shows the available models and the cost before you generate.
Sign in, or create your account