Text to video
Elo with audio · text-to-video arena
Veo 3.1 Lite overview
Veo 3.1 Lite specs
- Model ID
google/veo-3.1-lite-generate-001- Developer
- Input
- Text
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
What Is Veo 3.1 Lite?
Veo 3.1 Lite is a lightweight video generation model from Google DeepMind’s Veo family. It was designed to provide the core capabilities of modern generative video systems while significantly reducing compute cost and generation latency. While premium Veo models prioritize cinematic realism and long-form video, Veo 3.1 Lite focuses on short-form, scalable video generation suitable for digital products and automated pipelines. The model can generate realistic short videos directly from text prompts or animate images into dynamic clips.
One of the defining characteristics of Veo 3.1 Lite is the integration of synchronized audio generation. Many competing systems require separate pipelines for sound design, but this model can generate ambient sound effects that align with the generated visuals.
Output resolution is optimized for modern digital platforms. The model produces HD video suitable for social networks, marketing assets, previews, and application interfaces where responsiveness and cost efficiency matter more than ultra-high resolution. Because the model is optimized for performance, generation speeds remain consistently fast even under heavier workloads. This makes it well suited for applications where users generate content interactively.
Why Veo 3.1 Lite Is Important for Developers
The biggest problem with most AI video models is that they are too expensive to use in production. A tool may work well for a demo, but the cost becomes difficult to justify when you need hundreds or thousands of videos every day.
Veo 3.1 Lite changes that. It delivers video quality that is strong enough for commercial use, while costing substantially less than higher-end models in the same family. Google positions Veo 3.1 Lite as the model for high-volume AI video generation, where affordability and speed are more important than cinematic perfection. For many companies, that is exactly the right tradeoff.
Text-to-Video Generation
Veo 3.1 Lite can generate short-form videos directly from a written prompt. Developers can create promotional clips, visual concepts, storyboards, product teasers, or social media content in seconds. Because the model is optimized for rapid iteration, teams can test multiple prompt variations quickly. This is especially valuable for ad campaigns and A/B testing, where dozens of creative versions may be needed.
Image-to-Video Animation
The model also supports image-to-video generation. A single product image, illustration, or branded visual can be transformed into a dynamic video clip with movement and depth. This is particularly useful for e-commerce brands, digital artists, and marketing teams that want more engaging content without producing new footage manually.
Native Audio Included
Many AI video tools still require an additional text-to-speech or sound generation layer. Veo 3.1 Lite removes that extra step. The model can generate synchronized audio together with the video output. Depending on the scene, this may include ambient sounds, environmental effects, or background audio cues. By combining video and audio in one request, developers save time, simplify their architecture, and reduce overall processing cost.
Flexible Video Output
Veo 3.1 Lite supports multiple formats, which makes it easy to adapt content for different channels and platforms. These settings make it easy to generate content for TikTok, Instagram Reels, YouTube Shorts, display ads, product pages, and landing pages.
Use cases
Veo 3.1 Lite Generate Preview is documented as suited to high-efficiency, developer-first video generation with high-fidelity results and cinematic control. It is also documented for image-to-video workflows, including generating novel videos from an existing image as the first frame, optionally with descriptive text.
It is suited to creating videos with audio, since the model output is described as video with audio and sound generation is listed as supported. It is also documented for first-and-last-frame video generation, where a start and end image are used to generate the transition between them.
A further documented use case is high-volume video generation, with one source describing it as a fast, cost-efficient model designed for high-volume use cases. Another documented use case is programmable video creation for creators and enterprises, where the model offers a scalable interface for professional-grade video AI.
Veo 3.1 Lite benchmarks by 
Artificial Analysis
Human-preference results for Veo 3.1 Lite in text to video, silent video and image to video, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Models on AI/ML API
Arena results for models you can call with the same API key.
Text to video
Blind votes on clips with generated sound, made from a text prompt. Veo 3.1 Lite ranks #24 of 31.
Silent video
The same text-to-video task, judged as silent video. Veo 3.1 Lite ranks #25 of 36.
Image to video
Blind votes on clips with sound animated from a start image. Veo 3.1 Lite ranks #24 of 29.
Silent image to video
Clips animated from a start image, judged as silent video. Veo 3.1 Lite ranks #24 of 34.
Veo 3.1 Lite API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.03 | per second |
| Additional | $0.065 | per /sec |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Veo 3.1 Lite vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Veo 3.1 Lite | $0.03 |
| Veo 3.1 Lite Generate Preview | $0.03 |
| Veo 3.1 Fast | $0.08 |
| Gemini Omni 1.1 Flash | $0.1014 |
| Veo 3.1 | $0.2 |
How to use the Veo 3.1 Lite API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/veo-3.1-lite-generate-001",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/veo-3.1-lite-generate-001",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "google/veo-3.1-lite-generate-001",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to Veo 3.1 Lite
Related articles
Veo 3.1 Lite FAQ
What inputs and outputs does Veo 3.1 Lite support?
Veo 3.1 Lite takes image, text as input and returns video.
When was Veo 3.1 Lite released?
Veo 3.1 Lite became available on April 6, 2026.
How much does Veo 3.1 Lite cost?
Veo 3.1 Lite costs $0.03 per second on AI/ML API, billed as you go with no subscription.
How is Veo 3.1 Lite billed?
Veo 3.1 Lite costs $0.03 per second on AI/ML API, billed as you go with no subscription.
Can Veo 3.1 Lite take an existing image as input?
Yes, Veo 3.1 Lite accepts image input as well as a text prompt.
Who created Veo 3.1 Lite?
Veo 3.1 Lite was built by Google.
How do I call Veo 3.1 Lite on AI/ML API?
Use google/veo-3.1-lite-generate-001 as the model id on AI/ML API.
Is Veo 3.1 Lite available through a single API key?
Yes. Veo 3.1 Lite is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is the Veo 3.1 Lite model ID?
Use google/veo-3.1-lite-generate-001 as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.