> ## Documentation Index
> Fetch the complete documentation index at: https://docs.yelinai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Veo-3.1 Overview

> Google Veo 3.1 API: AI video generation supporting text-to-video and image-to-video. From $0.15/generation, 8 model variants, OpenAI-compatible format.

## Prerequisites

1

Get API Key

Log in to [YeLIn AI console](https://api.yelinai.com) to obtain your API key

2

Configure Billing Mode

Edit token settings and choose one of the following billing modes (same price for both):

* **Volume Priority** (Recommended): Uses balance billing first, automatically switches when balance is insufficient. Suitable for most users
* **Pay-per-call**: Direct deduction for each call. Suitable for strict budget control scenarios

Both modes have **exactly the same price**, Veo-3.1 series $0.15-$0.25/call, only the billing method differs.

<Note>
  请在 **Console** 查看对应界面截图。
</Note>

If billing mode is not configured, API calls will fail. You must complete this configuration first!

## Introduction

Veo-3.1 is Google’s latest generation video generation model series, supporting high-quality video content generation through text descriptions or image inputs. The entire series is fully compatible with OpenAI Chat Completions API format, making it easy for developers to integrate quickly.

## Core Features

## Text-to-Video

Generate videos from pure text descriptions, supporting complex scenes and action descriptions

## Image-to-Video

Generate transition videos or animation effects based on 1-2 reference images

## OpenAI Compatible

Uses standard Chat Completions API format, no need to learn new interfaces

## Streaming Response

Supports streaming returns for real-time generation progress and results

## Model Series

Veo-3.1 provides multiple model variants to meet different scenario requirements:

### Standard Models

veo-3.1 - Standard

**Price:** \$0.25 / request**Features:**

* Excellent overall performance
* Suitable for most scenarios
* Stable generation quality

**Use Cases:** General video generation, content creation

veo-3.1-fast - Fast

**Price:** \$0.15 / request**Features:**

* Faster generation speed
* High cost-effectiveness
* Suitable for rapid iteration

**Use Cases:** Batch generation, quick testing

### Image-to-Video Models (Support Image Input)

veo-3.1-fl - Image-to-Video Standard

**Price:** \$0.25 / request**Features:**

* Supports 1-2 image inputs
* Can generate image transition animations
* Bring static images to life

**Use Cases:** Image animation, image transition videos

veo-3.1-fast-fl - Image-to-Video Fast

**Price:** \$0.15 / request**Features:**

* Fast image-to-video generation
* Supports image input
* High cost-effectiveness

**Use Cases:** Batch image animation production

### Landscape Models

veo-3.1-landscape - Landscape Standard

**Price:** \$0.25 / request**Features:**

* Optimized for landscape scenarios
* 16:9 or wider aspect ratio
* Suitable for professional production

**Use Cases:** Film production, commercial videos

veo-3.1-landscape-fast - Landscape Fast

**Price:** \$0.15 / request**Features:**

* Fast landscape video generation
* Maintains picture quality
* Efficient batch processing

**Use Cases:** Batch landscape content production

veo-3.1-landscape-fl - Landscape Image-to-Video

**Price:** \$0.25 / request**Features:**

* Landscape + image input support
* Professional-grade output
* Excellent detail preservation

**Use Cases:** Landscape image animation, professional landscape production

veo-3.1-landscape-fast-fl - Landscape Image-to-Video Fast

**Price:** \$0.15 / request**Features:**

* Fast + image input + landscape
* Triple feature combination
* Extremely high cost-effectiveness

**Use Cases:** Large-scale landscape image animation production

## Price Comparison

| Model Name                | Price  | Speed    | Aspect Ratio | Image Support | Recommended Use                 |
| ------------------------- | ------ | -------- | ------------ | ------------- | ------------------------------- |
| veo-3.1                   | \$0.25 | Standard | General      | ❌             | Text-to-video general scenarios |
| veo-3.1-fast              | \$0.15 | Fast     | General      | ❌             | Text-to-video quick testing     |
| veo-3.1-fl                | \$0.25 | Standard | General      | ✅             | Image-to-video standard quality |
| veo-3.1-fast-fl           | \$0.15 | Fast     | General      | ✅             | Image-to-video fast processing  |
| veo-3.1-landscape         | \$0.25 | Standard | Landscape    | ❌             | Landscape text-to-video         |
| veo-3.1-landscape-fast    | \$0.15 | Fast     | Landscape    | ❌             | Landscape text-to-video fast    |
| veo-3.1-landscape-fl      | \$0.25 | Standard | Landscape    | ✅             | Landscape image-to-video        |
| veo-3.1-landscape-fast-fl | \$0.15 | Fast     | Landscape    | ✅             | Landscape image-to-video fast   |

## Generation Methods

### Text-to-Video

Generate video content through natural language descriptions:

```
{
  "messages": [{
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": "Generate a video of two cats and a dog fighting"
      }
    ]
  }],
  "model": "veo-3.1",
  "stream": true,
  "n": 2
}
```

### Image-to-Video

Generate video content based on reference images:

```
{
  "messages": [{
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": "Generate a smooth transition video based on two images"
      },
      {
        "type": "image_url",
        "image_url": {
          "url": "Start frame image URL or base64"
        }
      },
      {
        "type": "image_url",
        "image_url": {
          "url": "End frame image URL or base64 (optional)"
        }
      }
    ]
  }],
  "model": "veo-3.1-fl",
  "stream": true
}
```

## Core Parameters

model

string

required

Select the Veo-3.1 model variant to use

messages

array

required

Message array containing user input, supporting text and image types

stream

boolean

default:"false"

Whether to enable streaming response, recommended to set to `true` for real-time progress

n

integer

default:"1"

Number of videos to generate, range 1-4, can generate multiple different results simultaneously

## Billing Information

**Important:** Veo-3.1 models require **pay-per-use tokens**, not pay-as-you-go tokens. Please create a “pay-per-use” type token in the [Console](https://api.yelinai.com/token).

**Pay-per-request:** Each successful API call is charged at the selected model’s unit price, failed requests are not charged

### Billing Rules

* **Single Request:** Charged at model price (0.15or0.15 or 0.15or0.25)
* **Multiple Results:** Setting `n=2` generates 2 videos, charged for 2 requests
* **Failed Retries:** Failed generations are not charged, can retry for free
* **Streaming Response:** No additional charge

## Technical Advantages

## High-Quality Output

Advanced video generation algorithms ensure smooth and natural footage

## Fast Response

Fast series models can return results in seconds

## Flexible Control

Supports text and image combination input for precise content control

## Standard Interface

Fully compatible with OpenAI API, zero learning curve

## Batch Processing

Supports generating multiple results simultaneously through n parameter

## Real-time Progress

Streaming response provides real-time generation status feedback

## Quick Start

## Quick Start Guide

View complete quick start tutorial with detailed code examples

## Use Cases

* Content Creation

* Professional Production

* Batch Generation

* Social media short videos

* Marketing clips

* Product showcase animations

* Educational training content

* Film visual effects preview

* Ad creative testing

* Animation prototyping

* Concept validation videos

* Automated content production

* A/B testing materials

* Multi-version rapid iteration

* Dataset generation

## Next Steps

## Quick Start

Get started with Veo-3.1 API in 5 minutes

## Code Examples

View complete example code in various languages

## Best Practices

Learn how to write better prompts

## Troubleshooting

Check common issues and errors