# Muvi

> Muvi is an AI model API platform providing access to 11 AI models for image generation, video generation, upscaling, and more. Pay-per-use pricing with no minimums.

## API Documentation

- [All Models](https://developer.pixelbyte.app/files/llms/models/llms.txt): Complete model catalog with pricing and documentation links
- [API Base URL](https://api.pixelbyte.app/v1): REST API base endpoint
- [Pricing](https://developer.pixelbyte.app/pricing): Plans and pricing information

## Quick Start

```bash
curl -X POST https://api.pixelbyte.app/v1/jobs/submit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "provider/model-id", "input": {"prompt": "your prompt"}}'
```

## Job Polling

Jobs are processed asynchronously. After submitting, poll for status:

```bash
curl https://api.pixelbyte.app/v1/jobs/{JOB_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

### Job Status Values

| Status | Description |
|--------|-------------|
| `pending` | Job submitted, waiting in queue |
| `processing` | Job is being processed by a worker |
| `completed` | Job finished successfully - outputs available |
| `failed` | Job failed - check `error.message` for details |
| `cancelled` | Job was cancelled |

### Polling Example (Python)

```python
import time, requests

# After submitting a job:
job_id = submit_response.json()["data"]["jobId"]

while True:
    resp = requests.get(f"https://api.pixelbyte.app/v1/jobs/{job_id}",
        headers={"Authorization": "Bearer YOUR_API_KEY"})
    data = resp.json()["data"]

    if data["status"] == "completed":
        print("Done!", data["outputs"][0]["url"])
        break
    elif data["status"] == "failed":
        raise Exception(f"Job failed: {data['error']['message']}")

    time.sleep(2)  # Poll every 2 seconds
```

### Success Response

```json
{
  "success": true,
  "data": {
    "id": "job_abc123",
    "status": "completed",
    "outputs": [
      {
        "url": "https://...",
        "type": "image"
      }
    ],
    "costMicroCents": 400000
  }
}
```

### Failed Response

```json
{
  "success": true,
  "data": {
    "id": "job_abc123",
    "status": "failed",
    "error": {
      "code": "PROCESSING_ERROR",
      "message": "Model processing failed"
    },
    "outputs": null
  }
}
```

> **Tip:** Use the `webhookUrl` parameter in your submit request to receive a callback when the job completes instead of polling.

## Available Models

- [Nano Banana](https://developer.pixelbyte.app/files/llms/models/google/nano-banana/llms.txt): text-to-image
- [Nano Banana](https://developer.pixelbyte.app/files/llms/models/google/nano-banana/edit-image/llms.txt): image-to-image
- [Nano Banana 2](https://developer.pixelbyte.app/files/llms/models/google/nano-banana-2/llms.txt): text-to-image
- [Nano Banana 2](https://developer.pixelbyte.app/files/llms/models/google/nano-banana-2/edit-image/llms.txt): image-to-image
- [Nano Banana Pro](https://developer.pixelbyte.app/files/llms/models/google/nano-banana-pro/edit-image/llms.txt): image-to-image
- [Nano Banana Pro](https://developer.pixelbyte.app/files/llms/models/google/nano-banana-pro/text-to-image/llms.txt): text-to-image
- [Veo 3.1](https://developer.pixelbyte.app/files/llms/models/google/veo-3.1/text-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1](https://developer.pixelbyte.app/files/llms/models/google/veo-3.1/reference-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://developer.pixelbyte.app/files/llms/models/google/veo-3.1-fast/image-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://developer.pixelbyte.app/files/llms/models/google/veo-3.1-fast/reference-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://developer.pixelbyte.app/files/llms/models/google/veo-3.1-fast/text-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.

## Categories

- [Text to Image](https://developer.pixelbyte.app/categories/text-to-image): Generate images from text prompts
- [Image to Image](https://developer.pixelbyte.app/categories/image-to-image): Transform existing images
- [Video Generation](https://developer.pixelbyte.app/categories/video-generation): Create videos from text or images
- [Image Upscale](https://developer.pixelbyte.app/categories/image-upscale): Enhance image resolution
- [Background Removal](https://developer.pixelbyte.app/categories/background-removal): Remove image backgrounds
- [Face Swap](https://developer.pixelbyte.app/categories/face-swap): Swap faces in images
- [Style Transfer](https://developer.pixelbyte.app/categories/style-transfer): Apply artistic styles
- [Inpainting](https://developer.pixelbyte.app/categories/inpainting): Edit specific parts of images

## Notes

- All costs are in micro-cents (1,000,000 = $1 USD)
- Jobs are processed asynchronously
- Poll `GET /v1/jobs/{jobId}` for status or use `webhookUrl` for callbacks
- Individual model documentation available at `/files/llms/models/{provider}/{model-id}/llms.txt`