Google Gemini Omni Flash Video Edit API Documentation

Google Gemini Omni Flash Video Edit API Documentation

Playground

Gemini Omni Flash Video Edit applies natural-language edit instructions to existing videos, enabling prompt-guided changes to scenes, style, motion, and visual details while preserving the original video context. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Gemini Omni Flash Video Edit edits an existing source video using a natural-language instruction while preserving scene coherence. Upload a video, describe the edit you want, and generate an edited video through the standard WaveSpeed prediction response.

> A newer version is available. Gemini Omni 1.1 Flash Video Edit supports output resolutions from 360p to 4k. Both versions charge $0.02 per input-video second, plus an output video fee. See each model’s pricing table for details.

Why Choose This?

• Prompt-based video editing
  Edit an existing video using a simple natural-language instruction.

• Scene-aware transformation
  Apply visual changes while keeping the overall scene structure coherent.

• Simple input workflow
  Only a source video and edit prompt are required.

• Preservation-friendly edits
  Use clear instructions to change specific elements while keeping the rest of the video consistent.

• Standard video output
  Edited videos are returned as URLs in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Upload your video — Provide the source video you want to edit.
2. Write your edit prompt — Describe the change you want to apply to the video.
3. Submit — Generate the edited video.
4. Use the result — Retrieve the generated video URL from the standard WaveSpeed prediction response.

Pricing

Total price = input video fee + output video fee.

• Input video: $0.02 per second, independent of output resolution. Source duration is rounded up to the next whole second and capped at 10 seconds.
• Output video: billed using the same rounded source duration, with a 3-second minimum and a 10-second maximum. This is the billing duration; the final generated clip may vary in length.
• The input fee does not have the output fee’s 3-second minimum. A 1.2-second source bills 2 input seconds and 3 output seconds.
• Text prompts and generated audio have no separate charge.

Output is 720p at $0.13 per billed second.

Best Use Cases

• Video restyling — Change the visual style, lighting, mood, or atmosphere of a source video.
• Scene refinement — Apply focused edits while preserving the original scene structure.
• Creative iteration — Test different edit directions from the same source video.
• Short-form content editing — Create polished edited clips for social media, ads, and creative workflows.
• Visual transformation — Modify the look or presentation of a video using prompt-based instructions.

Pro Tips

• Use simple, focused edit prompts for better results.
• Describe the exact change you want to apply to the source video.
• Add instructions such as Keep everything else the same when you want to preserve the original scene.
• Use clear source videos with visible subjects and stable framing.
• Keep prompts focused on visual edits rather than unrelated changes.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: `completed` is successful; `failed`, `cancelled`, `timeout`, and `deleted` are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |