# Veo 3.1 Fast

> Google's improved version of Veo 3 Fast with higher-fidelity video, context-aware audio generation, and last frame support for smooth video transitions.

- **Provider**: replicate
- **Model ID**: google/veo-3.1-fast
- **Category**: video_generation
- **Credits**: 1800 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `duration` (integer, optional): Video duration in seconds (5 or 8) (Default: `8`; Range: min: 5, max: 8)
- `aspect_ratio` (string, optional): Video aspect ratio (16:9, 9:16, 1:1) (Default: `16:9`)
- `image` (string, optional): Input image to start generating from. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280
- `seed` (integer, optional): Random seed for reproducibility
- `negative_prompt` (string, optional): Description of what to exclude from the generated video
- `last_frame` (string, optional): Ending image for interpolation. Creates a transition between input and last frame images
- `generate_audio` (boolean, optional): Generate audio with the video (Default: `True`)
- `prompt` (string, **required**): Text prompt for video generation
- `resolution` (string, optional): Resolution of the generated video (720p, 1080p) (Default: `720p`)

## Example Request

```json
{
  "model": "google/veo-3.1-fast",
  "input": {
    "duration": 8,
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "prompt": "a cat steals a fish from a supermarket and escapes",
    "resolution": "720p"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

google, veo, video-generation, text-to-video, audio, fast

## Documentation

https://replicate.com/google/veo-3.1-fast