Name: Gemini Omni 1.1 API: AI Video Generation and Editing
Brand: magicapi
SKU: api-magicapi-multimodal-video-generation-editing-google-gemini-omni-1-1
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Video Generation and Editing API (Google Gemini Omni 1.1)

## Overview
Gemini Omni 1.1 is a multimodal video generation and editing model from Google. Its developer describes it as fast and as generating native audio with the video.

The fields you send choose the mode:
- **Text to video**: `prompt` only.
- **Image to video**: `prompt` and a starting `image`.
- **First and last frame**: `prompt`, `image` and `last_frame`; the model interpolates a smooth transition between the two frames.
- **Reference images**: `reference_images` guide the subject and style (they are not used as literal frames).
- **Video editing**: `prompt` and an existing `video`; describe the change and the model keeps the rest of the video.

Each request returns the URL of one video.

## Features
- **Resolutions**: `360p` (fast draft mode), `720p` (default), `1080p` and `4k`.
- **Aspect ratios**: `16:9` (default) and `9:16`. Ignored when editing an existing video.
- **Prompt-only control**: describe scene, camera movement, lighting, mood and audio in `prompt`. There is no negative prompt field; write what to avoid in the prompt, for example `no dialogue`.
- **Video editing**: send a `video` with a prompt such as `make the sky stormy, keep everything else the same`.
- **Characters and objects**: `reference_images` produce a video featuring specific characters or objects.

## Use Cases
1. **Social and ad clips**: short scenes from a text description in landscape or portrait format.
2. **Animating stills**: turn a product photo or illustration into a moving shot.
3. **Transitions**: generate the motion between a first and a last frame.
4. **Changing existing footage**: alter the weather, lighting or objects in a video while keeping the rest.

## Visual Examples
### Example Input
Prompt: "A cinematic drone shot through misty pine mountains at sunrise, gentle wind and birdsong. No dialogue."

Text to video at `720p` and `16:9`.

```json
{
  "prompt": "A cinematic drone shot through misty pine mountains at sunrise, gentle wind and birdsong. No dialogue.",
  "resolution": "720p",
  "aspect_ratio": "16:9"
}
```

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/10/gemini-omni-1-1-output-sqm43dnm-api-market-1.mp4)

The example returned a 10-second video after 66 seconds of processing.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt describing the video. Include details like scene, camera movement, lighting, mood and audio for best results. Put anything you want to avoid in the prompt too (for example 'no dialogue'). |
| `image` | string (URL) | No | none |  | URL of a starting image to animate into a video. When provided without last_frame, the video is generated from this image. |
| `last_frame` | string (URL) | No | none |  | URL of an ending image. When provided together with image, the model interpolates a smooth transition between the two frames. |
| `reference_images` | array of strings (URLs) | No | `[]` |  | URLs of reference images that guide the subject and style of the video (not used as literal frames). Use this to generate a video featuring specific characters or objects. |
| `video` | string (URL) | No | none |  | URL of an existing video to edit. Describe the change in the prompt (for example 'make the sky stormy, keep everything else the same'). The model applies the edit while preserving the rest of the video. |
| `aspect_ratio` | string | No | `16:9` | `16:9`, `9:16` | Video aspect ratio. Ignored when editing an existing video. |
| `resolution` | string | No | `720p` | `360p`, `720p`, `1080p`, `4k` | Resolution of the generated video. 360p is a fast draft mode. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.063 per API unit.
- **1 API unit = 1 second of output video at `360p`**; the video length is rounded up to whole seconds per request. Higher resolutions use more units per second: `720p` 3 units, `1080p` 4.6 units, `4k` 9 units.
- There is no duration field. You are billed on the length of the video returned; the example returned 10 seconds.
- **Example cost**: 10 seconds at `720p` = 30 units, $1.89.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

| `resolution` | Price per second of video | 10-second video |
| --- | --- | --- |
| `360p` | $0.063 | $0.63 |
| `720p` (default, used when `resolution` is omitted) | $0.189 | $1.89 |
| `1080p` | $0.2898 | $2.898 |
| `4k` | $0.567 | $5.67 |

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/multimodal-video-generation-editing-google-gemini-omni-1-1`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 2 seconds and an overall timeout of 1200 seconds (20 minutes) work well. The example took 66 seconds at 720p.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/multimodal-video-generation-editing-google-gemini-omni-1-1/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "google/gemini-omni-1.1",
    "input": {
      "prompt": "A cinematic drone shot through misty pine mountains at sunrise, gentle wind and birdsong. No dialogue.",
      "resolution": "720p",
      "aspect_ratio": "16:9"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "sqm43dnmgnrmw0d1ccqbmr8fpg",
  "version": "google/gemini-omni-1.1",
  "status": "starting",
  "created_at": "2026-10-22T10:36:07.821Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/multimodal-video-generation-editing-google-gemini-omni-1-1/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "sqm43dnmgnrmw0d1ccqbmr8fpg",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/gemini-omni-1-1-output-sqm43dnm-api-market-1.mp4",
  "error": null,
  "created_at": "2026-10-22T10:36:07.821Z",
  "started_at": "2026-10-22T10:36:08.821Z",
  "completed_at": "2026-10-22T10:37:14.883Z"
}
```

`output` is a single URL string pointing to the generated or edited MP4 video.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt` or a `resolution` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/multimodal-video-generation-editing-google-gemini-omni-1-1";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "google/gemini-omni-1.1", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 1200000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 20 minutes");
}

createAndWaitForPrediction({
  "prompt": "A cinematic drone shot through misty pine mountains at sunrise, gentle wind and birdsong. No dialogue.",
  "resolution": "720p",
  "aspect_ratio": "16:9"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/multimodal-video-generation-editing-google-gemini-omni-1-1"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "google/gemini-omni-1.1", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 1200
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 20 minutes")


output = create_and_wait_for_prediction({
    "prompt": "A cinematic drone shot through misty pine mountains at sunrise, gentle wind and birdsong. No dialogue.",
    "resolution": "720p",
    "aspect_ratio": "16:9"
})
print(output)
```

## FAQ
- **How long are the videos?**
  - There is no duration setting. The example returned a 10-second video, and you are billed for the length returned.
- **How do I keep something out of the video?**
  - Write it in the prompt, for example `No dialogue.` There is no separate negative prompt field.
- **How do I make a cheap draft?**
  - Set `resolution` to `360p`, the fast draft mode, at $0.063 per second of video.
- **How do I edit an existing video?**
  - Send its URL in `video` and describe the change in `prompt`. `aspect_ratio` is ignored when editing.
- **What is the difference between `image` and `reference_images`?**
  - `image` is used as the first frame of the video. `reference_images` only guide the subject and style and are not used as frames.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Generate videos from text, images or first and last frames, or edit a video with a prompt, using Google's Gemini Omni 1.1. Pay as you go, no monthly fee.