Google · Video model

Veo 3 / Veo 3.1

Veo 3 is Google DeepMind's text-to-video and image-to-video model

Generate on Coinis Read the docs

One API key. Every model.

per second

Sample output

AI video

Commercial use included Verified June 4, 2026 Outputs are yours No training on your data

Endpoints

Start building with Veo 3 / Veo 3.1.

One model. Three ways to call it. Same key, same bill.

Veo 3 Fast (720p, audio on)

Video generation

One call. Same key. Same bill.

$0.13 / second

Veo 3 Fast (1080p, audio on)

Video generation

One call. Same key. Same bill.

$0.15 / second

Veo 3 Standard (720p, audio on)

Video generation

One call. Same key. Same bill.

$0.34 / second

Veo 3.1 Lite (720p, no audio)

Video generation

One call. Same key. Same bill.

$0.05 / second

Veo 3.1 Generate 001 (Vertex AI)

Video generation

One call. Same key. Same bill.

$0.34 / second

Examples

Veo 3 / Veo 3.1 examples. Real output. Real prompts.

Every clip below is one pass. No post-production.

Sneaker. Orange powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. A white sneaker erupts through an orange and gold powder burst in slow motion, then holds as hero as the powder settles, the gold infinity mark crisp on the heel.

Perfume. Gold powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. A frosted perfume bottle erupts through a gold and amber powder burst in slow motion, then the bottle holds as hero as the shimmer settles.

Headphones. Blue powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. Navy-and-gold headphones erupt through a deep blue and gold powder burst in slow motion, then hold as hero as the powder settles.

Watch. Gold powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. A luxury watch erupts through a gold and bronze powder burst in slow motion, the case gleaming, then holds as hero as the powder settles.

Coffee. Beans and powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. A kraft coffee bag erupts through a brown and gold coffee-powder burst with flying beans in slow motion, then holds as hero as the cloud settles.

Skincare. Pink powder burst.

Image-to-video (8s), Veo 3 by Google DeepMind. A ceramic skincare jar erupts through a soft pink and gold powder burst in slow motion, then holds as hero as the powder settles.

Branded can. Headline that reads.

Image-to-video (8s), Veo 3 by Google DeepMind. A matte-black product can on a warm cream studio backdrop, gold infinity mark on the front; a slow gentle push-in while the headline "AI AD CREATIVE" and the "Coinis" wordmark stay crisp and legible.

Capabilities

What it does best.

Veo 3 capabilities

Resolution and length

Generates 8-second clips at 720p, 1080p, or 4K resolution[^1]
Veo 3.1 Lite supports 720p and 1080p only. 4K is not available on that tier[^1]

Audio

Generates ambient noise, sound effects, and dialogue natively in the same pass. no post-production required[^2]
Supports scripted dialogue with accurate lip-sync for on-screen characters[^3]
Veo 3.1 Lite (variant veo-3-1-lite-720p) does not include native audio generation[^1]

Conditioning

Text-to-video: generate from a written prompt alone[^2]
Image-to-video: use an input image as the starting frame. optimal inputs are 1280×720 (16:9) or 720×1280 (9:16)[^4]
First-and-last-frame control: specify both the opening and closing frames to guide the generation[^4]
Up to three reference images can be provided to direct video content[^4]

Aspect ratios

Landscape 16:9 and portrait 9:16 are both supported via the aspect_ratio parameter[^4]

Editing

Video extension: previously generated Veo videos can be extended. extension is limited to 720p[^4]

Style controls

Prompt-driven shot composition, lens type, focus, camera motion, and genre or visual style[^2]
Strong real-world physics simulation and high prompt adherence across a wide range of cinematic styles[^2]

API

Call Veo 3 / Veo 3.1 in three lines.

One key. One base URL. Same SDK shape you already use.

curl JavaScript Python

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/video/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'

import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.video.generate({
  model: "models/google/veo-3",
  prompt: "neon city, rain, tracking shot",
});

from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.video.generate(
    model="models/google/veo-3",
    prompt="neon city, rain, tracking shot",
)

Response

{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/google/veo-3",
  "output": {
    "video_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Veo 3 / Veo 3.1 · Veo 3 Fast (720p, audio on)

1.3 tokens

per second · $0.13

Native audio

$0.13 / second

One key. Every model. One invoice. 1 token = $0.10

8s clip ≈ 10 tokens ($1.04)

Budget variant: Veo 3.1 Lite (720p, no audio) · $0.05/sec (≈4 tokens / 8s)

Start free. 25 tokens a week.

No credit card.

Why pay through Coinis

One wallet for every model. No API keys. No separate bills.
Generate ads. Launch to Meta. Track in one place.
On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

Veo 3 Fast (720p, audio on)

Final renders, studios

Resolution —

Price $0.13 / second

Veo 3 Fast (1080p, audio on)

Rapid tests, high volume

Resolution —

Price $0.15 / second

Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

AI short films and narrative video Script a scene, drop in dialogue, and get a lip-synced clip with synchronized ambient audio in one generation. Veo 3 Standard is the right tier when final quality matters.[^3]

Cinematic ads and marketing video Control shot composition, lens, and camera motion via the prompt to produce polished advertising content. Veo 3 Fast at 1080p (variant veo-3-fast-1080p) delivers high-resolution output at $0.153/sec for high-volume campaigns.[^2]

9:16 social and UGC content Portrait mode produces mobile-first vertical video in a single pass. Veo 3 Fast at 720p (variant veo-3-fast-720p) keeps cost at $0.127/sec for high-volume social pipelines.[^4]

Rapid preview and iteration Veo 3.1 Lite (variant veo-3-1-lite-720p) at $0.051/sec lets teams test dozens of creative directions before committing to a final render on a higher tier.[^1]

Developer-embedded video generation Veo 3.1 is available via the Gemini API and Vertex AI with Python, JavaScript, Go, Java, and REST clients. Teams can embed video generation directly into their products without managing inference infrastructure.[^4]

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Veo 3 / Veo 3.1 FAQs

How much does Veo 3 cost per second on Coinis?

Coinis bills per second of output video. Veo 3 Fast 720p is $0.127/sec. Veo 3 Fast 1080p is $0.153/sec. Veo 3 Standard 720p is $0.34/sec. Veo 3.1 Lite 720p is $0.051/sec. See the official Google pricing page for vendor-direct rates.

What is the difference between Veo 3, Veo 3 Fast, and Veo 3.1 Lite?

Veo 3 Standard delivers the highest output fidelity with native audio, dialogue, and lip-sync. Veo 3 Fast trades some quality for significantly lower cost per second. ideal for high-volume UGC or social pipelines. Veo 3.1 Lite is the lowest-cost tier at $0.051/sec but does not include native audio generation, making it best suited for visual iteration and preview workflows.

How does Veo 3 compare to OpenAI Sora for text-to-video?

Veo 3's primary differentiator is native audio generation. Dialogue, ambient sound, and sound effects are created in the same pass as the video, with accurate lip-sync for speaking characters. Sora does not generate audio natively. For campaigns that require synchronized speech or sound design without post-production work, Veo 3 Standard removes a full production step. You can compare both models on Coinis.

Does Veo 3 generate audio and dialogue natively, or do I need to add it in post?

Veo 3 generates audio natively. Ambient noise, sound effects, and scripted dialogue are all created in the same generation pass as the video. Characters can speak a scripted line with accurate lip-sync. No post-production audio work is required. Veo 3.1 Lite is the one exception. that tier does not include audio generation.

How do I make videos with Veo 3 / Veo 3.1 on Coinis?

No code. Create a free Coinis account, pick Veo 3 / Veo 3.1, describe your scene or animate a still image, and generate. 25 free tokens to start, no card.

Can I do image-to-video or extend an existing clip with Veo 3.1?

Yes to both. For image-to-video, supply an input image as the starting frame. optimal sizes are 1280×720 for landscape or 720×1280 for portrait. You can also specify both the first and last frames to bracket the generation. Video extension lets you lengthen a previously generated Veo clip, though extension is capped at 720p resolution. Image-to-video conditioning is billed separately by the vendor. see the official docs at ai.google.dev/gemini-api/docs/pricing.

What resolutions, aspect ratios, and clip lengths does Veo 3.1 support?

Veo 3.1 supports 720p, 1080p, and 4K resolutions. Veo 3.1 Lite supports 720p and 1080p only. Both landscape 16:9 and portrait 9:16 aspect ratios are available. Default clip length is 8 seconds. Video generation is an asynchronous operation. an 8-second clip typically completes in around 2 minutes.

Why is Veo 3 Standard the same price as Veo 3.1 Generate 001 on Coinis?

Veo 3 Standard 720p (variant veo-3-standard-720p) and Veo 3.1 Generate 001 (variant veo-3-1-generate-001) are both billed at $0.34/sec on Coinis. They share the same underlying Google wholesale rate of $0.40/sec. The two variant IDs represent the same capability tier accessed through different surfaces. marketplace and Vertex AI respectively.

Related

Pair it with.

Grok Imagine 1.5 Preview

Hailuo 02 / 2.3

Kling 2.5 (and 3.0)

All video models

Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 25 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-06-04. Read the docs .