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

# Gemini Omni 1.2 Flash video API is live

> Gemini Omni 1.2 Flash (gemini-omni-1.2-flash) is live on LaoZhang API: per-video prices by resolution, a first request, and how it compares with Muse.

Google's Gemini Omni 1.2 Flash video model is now available on LaoZhang API. Put a spoken line in the prompt and the person in the clip says it, at up to 1080p. Any `default`-group token can call it: \$0.10 per video at 360p, \$0.30 at 720p, and \$0.45 at 1080p.

* **Published**: November 11, 2026
* **Last checked**: November 11, 2026
* **Status**: Active; available in the `default` group

## Key facts

| Item | Details |
| - | - |
| Model ID | `gemini-omni-1.2-flash` |
| Released by Google | November 5, 2026 |
| Live on LaoZhang API | November 11, 2026 |
| Create a task | `POST /v1/videos` |
| Get a task | `GET /v1/videos/{id}` |
| Token | `default` group; Usage first or Per-call billing mode |
| Price | \$0.10, \$0.30, or \$0.45 per video for 360p, 720p, or 1080p |
| Output | 3–10 seconds, 16:9 or 9:16, with a soundtrack |
| Capabilities | Text-to-video, image-to-video, up to 6 reference images, spoken dialogue |
| Route | Integrated independently and priced per video; no Google account needed |

<video controls preload="none" poster="/images/samples/gemini-omni-en-t2v.jpg" src="https://media.laozhang.ai/samples/video/gemini-omni-en-t2v-720p-10s.mp4" />

gemini-omni-1.2-flash, 720p, 10 seconds, 16:9. The prompt includes the line "This one is for you.", which the musician says on camera

## What it is good for

| Use case | How to ask for it | Result |
| - | - | - |
| Talking-head, product pitch, or scripted dialogue | Put the line in `prompt`, in quotes | The person says the line; English, Chinese, Japanese, Korean, and Russian all work |
| Testing prompts in bulk | `"resolution": "360p"` | \$0.10 per video, usually ready in 30–60 seconds |
| Keeping a product or character consistent | Up to 6 images in `reference_images` | The people and objects in the images appear in one clip |
| Finished vertical clips in HD | `"size": "1080x1920"` | 1080p portrait, \$0.45 per video |

## Pricing

Billing is per video. The price depends only on resolution, and any length from 3 to 10 seconds costs the same:

| `resolution` | Per video | Google's price for 10 seconds |
| - | -: | -: |
| `360p` | \$0.10 | \$0.23 |
| `720p` (default) | \$0.30 | \$0.70 |
| `1080p` | \$0.45 | \$1.04 |

* A 10-second clip costs about 43% of Google's list price. Google bills per second; its prices come from the Gemini API pricing page, checked on November 11, 2026.
* Adding images does not change the price.
* Failed tasks are refunded in full, and requests rejected at submission are not charged.
* For the full billing rules, see [Pricing in the Gemini Omni guide](https://docs.laozhang.ai/en/api-capabilities/gemini-omni-video-generation.md#pricing).

## Who is affected

* **If you want to call Gemini Omni**: your existing `default`-group token works. You do not need a Google account or a new token group.
* **Tokens set to Usage-based only**: they cannot call this model. Switch the billing mode to Usage first or Per-call.
* **Other video models**: prices and requests for Muse, MiniMax H3, Wan, and Seedance are unchanged.

## Get started

**1. Prepare a token**

In [Token management](https://api.laozhang.ai/token), use or create a token in the `default` group with the Usage first billing mode.

**2. Create a task**

```bash theme={null}
curl -s -X POST "https://api.laozhang.ai/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "A street musician plays the violin under a street lamp on a rain-soaked cobblestone street at dusk. The camera slowly pushes in. She stops, smiles at the camera and says: \"This one is for you.\" Soft rain and violin in the background.",
    "resolution": "720p",
    "seconds": "10"
  }'
```

The response returns the task `id`.

**3. Poll and download**

Call `GET /v1/videos/{id}` every 5–10 seconds. When `status` is `completed`, download the MP4 from `video_url`. Video links stay available for 7 days.

For image-to-video, reference images, and portrait requests, see the [Gemini Omni 1.2 Flash video API guide](https://docs.laozhang.ai/en/api-capabilities/gemini-omni-video-generation.md).

## Gemini Omni or Muse

Both models use `POST /v1/videos`, so the same token and code can switch between them.

| | `gemini-omni-1.2-flash` | `muse-video` family |
| - | - | - |
| 10-second clip | 360p \$0.10, 720p \$0.30, 1080p \$0.45 | 720p \$0.30 |
| Clip length | 3–10 seconds | 5–60 seconds, with continuation |
| Aspect ratios | 16:9, 9:16 | 16:9, 9:16, 1:1, 4:3, 3:4 |
| Sound | Speaks the lines in your prompt | Music and sound effects |
| Reference images | Up to 6 | Up to 4 |

* Choose Gemini Omni 1.2 Flash for spoken dialogue, 1080p, or a lower price per video.
* Choose [Muse](https://docs.laozhang.ai/en/api-capabilities/muse-video-generation.md) for continuous 20–60 second clips, video continuation, or built-in visual styles.

## FAQ

### What is the model ID for Gemini Omni 1.2 Flash?

`gemini-omni-1.2-flash`, called through `POST /v1/videos`.

### Do I need a Google account or a Gemini API key?

No. A LaoZhang API token in the `default` group is enough. Use the Usage first billing mode.

### How long does one video take?

A short 360p clip usually takes 30–60 seconds, a 10-second 720p clip about a minute, and a 10-second 1080p clip about 1.5–2 minutes. The API is asynchronous, so the create and status requests return right away.

### Can Gemini Omni 1.2 Flash make clips longer than 10 seconds, or 4K?

No. Clips are 3–10 seconds at up to 1080p. For continuous 20–60 second clips use [Muse](https://docs.laozhang.ai/en/api-capabilities/muse-video-generation.md); for 2K use [MiniMax H3](https://docs.laozhang.ai/en/api-capabilities/minimax-h3-video-generation.md).

### Are the videos watermarked?

There is no visible watermark. Each file carries Google's C2PA content credentials and an invisible SynthID watermark that mark it as AI-generated.

## Sources and related pages

* [Gemini Omni 1.2 Flash video API guide](https://docs.laozhang.ai/en/api-capabilities/gemini-omni-video-generation.md): request examples, fields, task states, and common errors.
* [Compare video APIs and prices](https://docs.laozhang.ai/en/api-capabilities/video-generation-guide.md)
* [Google: introducing Gemini Omni 1.2 Flash](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/) (checked November 11, 2026)
* [Google: Gemini API pricing](https://ai.google.dev/gemini-api/docs/pricing) (per-second list prices, checked November 11, 2026)
* [Models and pricing](https://docs.laozhang.ai/en/models.md)
* [LaoZhang API announcements](https://docs.laozhang.ai/en/changelog.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.