# Gemini Omni API

> Gemini Omni — high-quality AI video generation.

- **Provider**: Google
- **Model id**: `gemini-omni-video`
- **Modality**: video
- **Price**: 41.85–167.41 credits

## Overview

Gemini Omni is called in two steps: create a generation task, then poll the task until the result is ready.

## Authentication

All requests require a Bearer Token in the request header:

```
Authorization: Bearer YOUR_API_KEY
```

## Create Task

`POST https://you.bot/api/v1/generate`

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| modelId | string | Yes | Model id: `gemini-omni-video` |
| input | object | Yes | Input parameters object (see below) |
| callbackUrl | string | No | https URL to receive a signed webhook on completion |

### input object parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| prompt | string | Yes | Describe the image you want to generate. (default: A paper crane comes alive on a desk and flies out an open window into the sunset; a soft piano note plays on each wingbeat.) |
| image_urls | string[] | No | Reference images. The base limit is 7; a video uses 2 image slots and each character_id uses 1 image slot. (image URL) |
| audio_ids | string | No | Audio ID list. Up to 1 ID is allowed. |
| video_list | string | No | Optional video input. Only 1 video is allowed and it uses 2 image slots. |
| character_ids | string | No | Character ID list. Each character ID uses 1 image slot. |
| duration | string | No | Note: when video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect. (options: 4 | 6 | 8 | 10) (default: 8) |
| aspect_ratio | string | No | Video ratio (options: 16:9 | 9:16) (default: 16:9) |
| resolution | string | No | Output video resolution. Valid values: 720P(default), 1080P, 4k. (options: 720p | 1080p | 4k) (default: 720p) |
| seed | number | No | Random seed. Range: [0, 2147483647]. If not specified, the system generates a seed automatically. Fixing the seed can improve reproducibility, but results may still vary due to the model’s stochasticity. (default: 0) |

### Request example

```json
{
  "modelId": "gemini-omni-video",
  "input": {
    "prompt": "A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "audio_ids": "example",
    "video_list": "example",
    "character_ids": "example",
    "duration": "8",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "seed": "0"
  }
}
```

### Response example

```json
{
  "taskId": "281e5b0…f39b9",
  "creditsCharged": 24
}
```

## Query Task

`GET https://you.bot/api/v1/task/{taskId}?model=gemini-omni-video`

When `state` is `success`, the output is in `resultUrls`: `{ "state": "success", "resultUrls": [ ... ] }`. (Text models return inline in the create response.)

## Error Codes

| Code | Description |
|------|-------------|
| 200 | Request successful |
| 400 | Invalid request parameters |
| 401 | Authentication failed, check API Key |
| 402 | Insufficient account balance |
| 422 | Parameter validation failed |
| 429 | Request rate limit exceeded |
| 500 | Internal server error |