# Wan 2.2 T2V Fast

> A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video

- **Provider**: replicate
- **Model ID**: wan-video/wan-2.2-t2v-fast
- **Category**: video_generation
- **Credits**: 240 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

- `num_frames` (integer, optional): Number of video frames. 81 frames give the best results (Default: `81`; Range: min: 81, max: 121)
- `resolution` (string, optional): Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px (Default: `480p`; Options: `480p`, `720p`)
- `frames_per_second` (integer, optional): Frames per second. Note that the pricing of this model is based on the video duration at 16 fps (Default: `16`; Range: min: 5, max: 30)
- `disable_safety_checker` (boolean, optional): Disable safety checker for generated video. (Default: `False`)
- `prompt` (string, **required**): Prompt for video generation
- `lora_weights_transformer_2` (string, optional): Load LoRA weights for transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA.
- `lora_weights_transformer` (string, optional): Load LoRA weights for transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/Viktor1717/scandinavian-interior-style1/resolve/main/my_first_flux_lora_v1.safetensors')
- `interpolate_output` (boolean, optional): Interpolate the generated video to 30 FPS using ffmpeg (Default: `True`)
- `sample_shift` (number, optional): Sample shift factor (Default: `12`; Range: min: 1, max: 20)
- `seed` (integer, optional): Random seed. Leave blank for random
- `lora_scale_transformer` (number, optional): Determines how strongly the transformer LoRA should be applied. (Default: `1`)
- `aspect_ratio` (string, optional): Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px (Default: `16:9`; Options: `16:9`, `9:16`)
- `lora_scale_transformer_2` (number, optional): Determines how strongly the transformer_2 LoRA should be applied. (Default: `1`)
- `go_fast` (boolean, optional): Go fast (Default: `True`)
- `optimize_prompt` (boolean, optional): Translate prompt to Chinese before generation (Default: `False`)

## Example Request

```json
{
  "model": "wan-video/wan-2.2-t2v-fast",
  "input": {
    "aspect_ratio": "16:9",
    "go_fast": true,
    "num_frames": 81,
    "frames_per_second": 16,
    "prompt": "A sports car is driving very fast along a beach at sunset",
    "resolution": "480p",
    "sample_shift": 12
  }
}
```

## 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

wan, prunaai, video-generation, text-to-video, fast, budget

## Documentation

https://replicate.com/wan-video/wan-2.2-t2v-fast