Veo 3.1 at a lower price
Google gave Veo 3.1 Fast the same upgrades in audio, narrative control and image-to-video as Veo 3.1, and it costs less per clip.
The Veo 3.1 Fast API: Google's 8 second 720p clips with native sound, at one flat price per clip.
veo-3.1-fastimport os, time, requestsAPI = "https://api.zurelay.com/v1"headers = {"Authorization": f"Bearer {os.environ['ZURELAY_API_KEY']}"}res = requests.post(f"{API}/videos", headers=headers, json={ "model": "veo-3.1-fast", "prompt": "A red fox trotting through fresh snow at dawn, cinematic", "seconds": 5, "resolution": "720p", "aspect_ratio": "16:9",})res.raise_for_status()job = res.json()# Takes a few minutes: poll until it's donewhile job["status"] in ("queued", "in_progress"): time.sleep(5) job = requests.get(f"{API}/videos/{job['id']}", headers=headers).json()if job["status"] == "failed": raise SystemExit(job["error"]["message"])video = requests.get(f"{API}/videos/{job['id']}/content", headers=headers)with open("video.mp4", "wb") as f: f.write(video.content)print(f"Saved video.mp4 for ${job['cost']}")Base URL https://api.zurelay.com/v1. Plain JSON over HTTPS: start a job, poll it, download the MP4. Veo guide
Pricing
Pay as you go from prepaid credit, with no subscription. Top up from $10. A video is charged only once it's delivered; videos that fail cost nothing.
A clip costs its length in seconds times the price at its resolution. It's held from your balance when the job is accepted and charged when the video is delivered. A first frame and the aspect ratio don't change the price.
Every AI video model and pricePick a resolution and a length, and how many videos you make.
100 clips × $1.60
Overview
Veo 3.1 Fast is the lower-cost version of Google's Veo 3.1 video model, released on October 15, 2025. It turns a text prompt or a first frame into an 8 second 720p video with sound. The Zurelay Veo 3.1 Fast API charges one flat price per clip, only once the video is delivered.
Veo is Google's family of video generation models. Google released Veo 3.1 and Veo 3.1 Fast on October 15, 2025, with richer native audio, more narrative control and better results from images than Veo 3. Veo 3.1 Fast is the lower-cost of the two. On Zurelay it uses the model ID veo-3.1-fast, and also accepts veo-3.1-fast-generate-preview and google/veo-3.1-fast.
Every Veo 3.1 Fast clip on Zurelay is 720p and exactly 8 seconds long, in 16:9 or 9:16; from a first frame, the clip takes the image's shape. It makes video from a text prompt or a first frame. Zurelay doesn't offer a last frame for it, because clips made with one carry a visible Veo mark. Sound is always on: dialogue, sound effects and ambient noise come with the picture, and generate_audio can't be turned off. There's no visible watermark; like every Veo video, clips carry Google's invisible SynthID watermark. Google's own API also offers higher resolutions and shorter clips; on Zurelay, Veo 3.1 Fast makes 8 second 720p clips only.
Video takes time, so the API is asynchronous. POST https://api.zurelay.com/v1/videos returns a job right away; poll GET /v1/videos/{id} until its status is completed, then download the MP4 from /v1/videos/{id}/content or from the signed url in the job. An 8 second clip usually takes about 1.5 minutes. Videos are kept for 30 days.
Zurelay charges $0.20 per 8 second clip ($0.025 per second), against Google's $0.80 for 8 seconds of Veo 3.1 Fast at 720p. Every clip has the same length, resolution and sound, so every clip costs the same. The price is held from your balance when the job is accepted and charged only when the video is delivered. Videos that fail, including ones Google's filters block, cost nothing.
Strengths
Google gave Veo 3.1 Fast the same upgrades in audio, narrative control and image-to-video as Veo 3.1, and it costs less per clip.
Dialogue, sound effects and ambient noise are generated with the picture, so a clip is ready to use without a separate audio pass.
Animate a first frame: the clip opens on your image and takes its shape.
Every clip is 8 seconds at 720p, so every clip costs the same flat price and there's nothing to calculate.
Use cases
Vertical 9:16 clips with dialogue and effects for short-video feeds.
Short scenes with spoken lines written in quotes. Google supports English prompts best.
Start from a product photo and describe the camera move, the action and the sound.
Start from a product shot, a character or an illustration and describe the motion and the sound.
Get started
No waitlist and nothing to install: three HTTPS endpoints and your API key.
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Every video endpoint lives under this base URL. Send your key as a Bearer token.
https://api.zurelay.com/v1POST a prompt to /v1/videos, poll the job every few seconds until it's completed, then download the MP4. Videos are kept for 30 days.
veo-3.1-fastWorks with the tools you already use
Compare
from $0.042 per second
Pick Gemini Omni Flash, Google's other video model, for 4 to 10 second clips from 360p to 4K, reference images and video edits.
Gemini Omni Flash APIfrom $0.125 per second
Pick Kling 3.0 for 1080p, clips of 3 to 15 seconds and the option of a cheaper silent clip.
Kling 3.0 APIfrom $0.074 per second
Pick Seedance 2.0 Fast for clips of 4 to 15 seconds at 480p or 720p, with up to 9 reference images.
Seedance 2.0 Fast APIZurelay charges $0.20 per 8 second clip, $0.025 per second, against Google's $0.10 per second ($0.80 a clip) for Veo 3.1 Fast at 720p. Every clip is 720p with sound, so the price is the same for every video, and a first frame or the aspect ratio doesn't change it.
When Zurelay accepts the job, its price is held from your balance, so videos in progress can never spend more than you have. It's charged only when the video is delivered. If a video fails, including when Google's filters block the prompt, the images or the generated audio, you pay nothing.
Send POST https://api.zurelay.com/v1/videos with your Zurelay key as a Bearer token and a JSON body: model set to veo-3.1-fast, a prompt, and optionally aspect_ratio (16:9 by default, or 9:16; a first frame's shape when you give one). Every clip is 8 seconds at 720p, so you can leave out seconds and resolution. You get a job back right away. Poll GET /v1/videos/{id} every few seconds until its status is completed, then download the MP4 from /v1/videos/{id}/content. Any HTTP client works; there's no SDK to install.
An 8 second clip usually takes about 1.5 minutes. While you poll, the job's progress field gives an estimate from 0 to 100.
There's no visible watermark. Like every Veo video, clips carry Google's invisible SynthID watermark, which identifies them as AI-generated.
Always. Veo generates dialogue, sound effects and ambient noise with the picture, and the MP4 carries the soundtrack. generate_audio can't be turned off, so leave it out of the request. Put spoken lines in quotes and say who speaks them. Google supports English prompts best; other languages may work but haven't been evaluated.
Yes. Pass first_frame to animate an image. There's no last_frame on Zurelay: clips made with one carry a visible Veo mark, so it isn't offered. Images can be https URLs or base64 data URLs of PNG, JPEG or WebP files up to 10 MB. Leave out aspect_ratio and the clip takes the image's shape: 9:16 for a portrait image, 16:9 otherwise.
Every clip is 720p and exactly 8 seconds, in 16:9 or 9:16. Google's own API also offers higher resolutions and 4 or 6 second clips, but on Zurelay Veo 3.1 Fast makes 8 second 720p clips only.
30 days. The url in a completed job is a signed link that lasts 24 hours; fetch the job again for a fresh one, or download through /v1/videos/{id}/content. GET /v1/videos lists your recent videos.
Yes. Your requests run on Google's Veo 3.1 Fast, and Zurelay doesn't swap in a different or smaller model. Video generation varies from run to run, so the same prompt makes a different clip each time. Zurelay is an independent service and is not affiliated with Google.
Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.