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

# Gemini Native (Video)

> Google Veo video generation models

## Introduction

Veo is Google Vertex AI's multimodal video generation model. It supports **text-to-video (T2V)**, **first-frame constraint**, and **first-and-last-frame constraint** (3.1 series only) for coherent video generation. Use LeapX's unified video API: [submit a task](/en/api-reference/endpoint/submit-video-task) to get a `task_id`, then [query the task](/en/api-reference/endpoint/query-video-task) to poll status and get the result.

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Supported models

| Model ID                        | Description                                                  |
| ------------------------------- | ------------------------------------------------------------ |
| `veo-3.0-fast-generate-001`     | Text-to-video, first-frame; fast (audio included by default) |
| `veo-3.1-fast-generate-preview` | Text-to-video, first/first+last frame; fast                  |
| `veo-3.0-generate-preview`      | Text-to-video, first-frame                                   |
| `veo-3.1-generate-preview`      | Text-to-video, first/first+last frame                        |

## Call flow

1. **Submit task**: `POST /v1/video/generations` with `model`, `prompt`, and Veo-specific parameters.
2. **Poll status**: `GET /v1/video/generations/{task_id}` until `status` is `succeeded` or `failed`.
3. **Get result**: On success, `url` in the response contains the video (Veo may return `data:video/mp4;base64,...` or an OSS link).

## Veo-specific parameters

<ParamField body="prompt" type="string" required>
  Video generation prompt describing the scene and motion.
</ParamField>

<ParamField body="durationSeconds" type="integer" default="4">
  Video duration in seconds; supported: `4`, `6`, `8`.
</ParamField>

<ParamField body="aspectRatio" type="string" default="16:9">
  Aspect ratio; only `16:9` and `9:16` supported.
</ParamField>

<ParamField body="resolution" type="string" default="1080p">
  Resolution: `720p`, `1080p`.
</ParamField>

<ParamField body="image" type="string">
  First-frame reference image (URL or Base64) for image-to-video / first-frame constraint.
</ParamField>

<ParamField body="lastFrame" type="string">
  Last-frame reference image (veo-3.1 series only); use with first frame for start-and-end constraint.
</ParamField>

<ParamField body="generateAudio" type="boolean" default="false">
  Whether to generate synchronized audio. Fast models ignore this and always include audio.
</ParamField>

<ParamField body="sampleCount" type="integer" default="1">
  Number of videos to generate per request, range `1-4`.
</ParamField>

For more parameters (e.g. `personGeneration`, `addWatermark`, `seed`), see [Submit Video Task](/en/api-reference/endpoint/submit-video-task).

## Request examples

**Submit Veo task (text-to-video):**

```bash theme={null}
curl -X POST "https://api.leapx-hub.com/v1/video/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1-fast-generate-preview",
    "prompt": "Morning light over a cyberpunk city skyline, camera slowly pushing in",
    "durationSeconds": 6,
    "aspectRatio": "16:9",
    "resolution": "1080p",
    "generateAudio": false
  }'
```

**Query task status:**

```bash theme={null}
curl -X GET "https://api.leapx-hub.com/v1/video/generations/{task_id}" \
  -H "Authorization: Bearer sk-xxxxxxxxxx"
```

For full request/response details and multi-model comparison, see [Submit Video Task](/en/api-reference/endpoint/submit-video-task) and [Query Video Task](/en/api-reference/endpoint/query-video-task).