# Gemini Omni Flash

You keep talking to it and it edits the same scene turn after turn without losing the thread.

Model id: `gemini-omni-flash`
Type: Video
Made by: Google
Inputs: Text, References
Length: 3 to 10 s
Aspect ratio: 16:9, 9:16
Updated: Oct 28, 2026

## Pricing

| Setting | MiniAPI | fal | Difference |
| --- | ---: | ---: | ---: |
| 720p words only | $0.137 / s | $0.125 | +10% |
| 720p with references | $0.141 / s | $0.1285 | +10% |

You are not charged for a job that fails.

## Parameters

| Name | Required | Values | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | Yes | text |  | What to make, in plain words. |
| `image_urls` | For references | https URLs |  | Pictures to use as references. Only with references. |
| `aspect_ratio` | No | 16:9, 9:16 | 16:9 | Shape of the result, for example 16:9 or 9:16. |
| `duration` | No | 3 to 10 | 8 | Length in seconds. The price changes with it. |

## Quickstart

```bash
curl -X POST "https://api.minicut.ai/v1/queue/gemini-omni-flash" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox runs through snow at dawn","duration":5}'
```

```json
{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/gemini-omni-flash/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/gemini-omni-flash/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/gemini-omni-flash/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.685000",
  "currency": "USD"
}
```

Page: https://api.minicut.ai/models/gemini-omni-flash
API reference: https://api.minicut.ai/docs/api