Veo 3.1 API

Meet Veo 3.1, Google DeepMind's latest video generation model with native audio, designed for filmmakers and storytellers. It delivers more realistic motion, better alignment with your creative intent, and stronger control over style, including cinematic looks and improved image-to-video quality. Build with Veo 3.1 on EvoLink to bring short scenes to life.

Model Type :

Veo 3.1 Fast Lite Veo 3.1 Pro Lite Veo 3.1 Fast Veo 3.1 Pro

Prompt

Estimated Cost

60 Credits

Sample Result

No sample available

Prompt

0 (suggested: 2,000)

Input Images

Upload up to 3 images

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 3

Aspect Ratio

Only 16:9 is supported when using reference images or 3 images.

Quality

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Veo 3.1 API - EvoLink video generation for short clips

Use the Veo 3.1 API to create 4, 6, or 8 second MP4 videos in 720p, 1080p, or 4K with 16:9, 9:16, or auto aspect ratios. Veo 3.1 API jobs run asynchronously and return a task ID; download links are valid for 24 hours, so teams can queue batches and collect results quickly.

EvoLink showcase of video generation model feature 1

Pricing

Model	Mode	quality	Price
Veo 3.1 Fast Lite	Video Generation	720p / 1080p	Popular $0.1681/ video(12.1 Credits)
Veo 3.1 Fast Lite	Video Generation	4K	$0.5042/ video(36.3 Credits)

Popular

Veo 3.1 Fast Lite

Video Generation

quality:720p / 1080p

Price:

$0.1681/ video

(12.1 Credits)

Veo 3.1 Fast Lite

Video Generation

quality:4K

Price:

$0.5042/ video

(36.3 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

What can you build with Veo 3.1 API?

Short-form growth content

With the Veo 3.1 API, growth teams can generate multiple ad or social variations in one sprint. Pick 4/6/8 second duration, 16:9 or 9:16 aspect ratio, and 720p/1080p/4K quality. Use veo3.1-fast for rapid iteration on hooks and formats, then keep the best-performing cuts for scale.

Start Using API

Social showcase of video generation model feature 2

Product demos with frame control

The Veo 3.1 API supports first and last frame image-to-video with 1 to 2 images, which is ideal for product walkthroughs, UI transitions, and storyboards. Auto aspect ratio can match your source image, and enhance_prompt can translate non-English prompts to English for more reliable results across global teams.

Start Using API

Product showcase of video generation model feature 3

Reference-led visual style

For style exploration, the Veo 3.1 API on EvoLink offers REFERENCE mode on fast endpoints, allowing up to three images for visual guidance. This mode is limited to 16:9 and is best for controlled, cinematic looks. Preview endpoints also support REFERENCE with fixed 8 second output, which is helpful for A/B testing looks.

Start Using API

Reference showcase of video generation model feature 4

Why developers choose Veo 3.1 API

The Veo 3.1 API on EvoLink combines predictable formats (4/6/8s, 720p/1080p/4K, 16:9/9:16/auto) with async task IDs and 24-hour download links, so teams can plan batch generation with reliable turnaround.

Predictable formats for delivery

Fixed durations and resolution options simplify storyboards, timelines, and publishing checks.

Async pipelines that scale

Task IDs, status queries, and callback_url support keep large queues stable and traceable.

Control with practical modes

TEXT, FIRST&LAST, and REFERENCE modes plus image limits make control explicit and consistent.

How to integrate Veo 3.1

A simple API flow to generate short videos and iterate quickly on EvoLink with the Veo 3.1 API.

Step 1 - Choose model settings

Pick veo3.1-pro or veo3.1-fast, then set duration, quality, aspect_ratio, and generation_type for your workflow.

Step 2 - Send prompt and images

Submit a prompt up to 2000 tokens, add image URLs if needed, enable enhance_prompt, and include callback_url.

Step 3 - Collect results

Poll task status or receive a callback, then download MP4 links within 24 hours and store them safely.

Open API Playground

Key Capabilities

Practical features available via the Veo 3.1 API endpoints on EvoLink

Models

Model choices on EvoLink

The Veo 3.1 API includes veo3.1-pro and veo3.1-fast Lite endpoints, plus preview models for deeper controls like generate_audio. This lets teams balance speed, cost, and control without changing their integration approach.

Modes

Multiple generation modes

Use TEXT for prompt-only generation, FIRST&LAST to bridge two frames, and REFERENCE for style guidance on fast endpoints. REFERENCE supports up to three images and is limited to 16:9; preview REFERENCE fixes duration to 8 seconds.

Formats

Quality and aspect control

Set quality to 720p, 1080p, or 4K and choose 16:9, 9:16, or auto aspect ratios. This makes the Veo 3.1 API suitable for both feed and story placements without extra editing steps.

Workflow

Async tasks and callbacks

Requests return a task ID for status checks. You can pass a callback_url for completion, failure, or cancellation events; HTTPS is required and internal IPs are blocked. Generated video links are valid for 24 hours, so download promptly.

Prompts

Prompt handling and translation

Prompts are limited to 2000 tokens. With enhance_prompt enabled, non-English prompts are automatically translated to English for better generation results, which is useful for global teams that need consistent output quality.

Audio

Preview audio and safety options

Preview endpoints support generate_audio (extra cost) along with parameters like negative_prompt, person_generation, and resize_mode for image-to-video. These options help teams refine output control while keeping the Veo 3.1 API integration consistent.

Frequently Asked Questions

Everything you need to know about the product and billing.

Veo 3.1 is EvoLink's video generation model family, with veo3.1-pro and veo3.1-fast options. It supports text-to-video and first-and-last-frame image-to-video, runs asynchronously, and returns short MP4 clips (4/6/8 seconds) with selectable aspect ratios and quality. Generated video links remain available for 24 hours, so teams can download and archive results quickly.

Veo 3.1 API offers veo3.1-pro and veo3.1-fast Lite endpoints. Use veo3.1-fast when you need quick iteration across many prompts or creative variants, and use veo3.1-pro when you want a more polished baseline for review. EvoLink also provides preview models like veo-3.1-fast-generate-preview, which add options such as generate_audio and other advanced parameters. The best approach is to test the same prompt on both and compare results for your use case.

The Veo 3.1 API accepts a text prompt up to 2000 tokens and optional image_urls for image-to-video. For veo3.1-pro, you can provide up to two images; for veo3.1-fast and preview endpoints you can provide up to three images depending on the mode. Images must be direct URLs, under 10MB, and in .jpg, .jpeg, .png, or .webp. You can also set generation_type, aspect_ratio, and enhance_prompt to improve results.

Veo 3.1 API outputs MP4 video in 4, 6, or 8 second lengths. You can choose 720p, 1080p, or 4K quality, and set aspect_ratio to 16:9, 9:16, or auto on Lite endpoints. The API is asynchronous, and the download links are valid for 24 hours after completion. This predictable spec set helps teams batch render assets for ads, social posts, and product previews.

With the Veo 3.1 API, FIRST&LAST mode lets you supply one or two images to guide the start and end of a clip, which is ideal for storyboarding and transitions. On fast endpoints, REFERENCE mode accepts up to three images for style guidance and is limited to 16:9. On preview endpoints, REFERENCE also fixes duration to 8 seconds and restricts advanced parameters (except generate_audio). Choose the mode that best fits your control needs.

Veo 3.1 API requests run asynchronously and return a task ID. You can poll the task status endpoint or provide a callback_url to receive completion, failure, or cancellation notifications after billing confirmation. The callback must use HTTPS, internal IPs are blocked, and EvoLink retries failed callbacks up to three times with a 10 second timeout. This design is reliable for queue-based pipelines and large batch jobs.

Audio generation is available on preview endpoints such as veo-3.1-fast-generate-preview. The generate_audio parameter controls whether audio is created and it adds extra cost. If you need audio for prototypes or demos, enable generate_audio on preview models, then confirm output quality before moving to production. For Lite endpoints, focus on video generation and add audio in post if needed.

The Veo 3.1 API supports prompts up to 2000 tokens, and enhance_prompt is enabled by default to automatically translate non-English prompts into English for better results. For the highest consistency, write clear English prompts with scene, camera, and style details. If you localize prompts, keep structure consistent and let enhance_prompt handle translation while you monitor output quality across regions.

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/videos/generations

Create Video

Veo 3.1 Fast Lite (veo3.1-fast) model supports text-to-video, first-frame image-to-video and other modes.

Asynchronous processing mode, use the returned task ID to .

Generated video links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: veo3.1-fast

Video generation model name.

Exampleveo3.1-fast

promptstringRequired

Prompt describing what kind of video to generate.

Notes

Limited to 2000 tokens

ExampleA cat playing piano

aspect_ratiostringOptionalDefault: auto

Video aspect ratio. When set to auto: image-to-video will automatically select based on the input image ratio, text-to-video will automatically select based on the prompt content.

Value	Description
auto	Automatic selection based on input
16:9	Landscape video
9:16	Portrait video

Exampleauto

image_urlsarrayOptional

Reference image URL list for image-to-video feature.

Notes

1 image for first-frame video generation
2 images for first-and-last-frame video generation
Up to 3 images for reference image to video
Max size: 10MB per image
Formats: .jpg, .jpeg, .png, .webp
URLs must be directly viewable by the server

Examplehttp://example.com/image1.jpg

generation_typestringOptional

Video generation mode, default matches based on image count.

Value	Description
TEXT	Text to video
FIRST&LAST	First and last frame to video (1-2 images)
REFERENCE	Reference image to video (up to 3 images, 16:9 only)

ExampleTEXT

enhance_promptbooleanOptionalDefault: true

Whether to automatically translate the prompt to English. When enabled, non-English prompts will be automatically translated to English for better generation results.

Exampletrue

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/video-task-completed

qualitystringOptionalDefault: 720p

Video resolution quality.

Value	Description
720p	HD resolution
1080p	Full HD resolution
4k	Ultra HD resolution (4K)

Example720p

Request Example

{
  "model": "veo3.1-fast",
  "prompt": "A cat playing piano",
  "aspect_ratio": "16:9"
}

Response Example

{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "veo3.1-fast",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 180,
    "video_duration": 8
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 60,
    "user_group": "default"
  }
}