# Muvi

> Muvi is an AI model API platform providing access to 132 AI models for image generation, video generation, upscaling, and more. Pay-per-use pricing with no minimums.

## API Documentation

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

## Quick Start

```bash
curl -X POST https://api.muvi.video/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.muvi.video/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.muvi.video/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.muvi.video/files/llms/models/google/nano-banana/llms.txt): text-to-image
- [Nano Banana](https://developer.muvi.video/files/llms/models/google/nano-banana/edit-image/llms.txt): image-to-image
- [Nano Banana 2](https://developer.muvi.video/files/llms/models/google/nano-banana-2/llms.txt): text-to-image
- [Nano Banana 2](https://developer.muvi.video/files/llms/models/google/nano-banana-2/edit-image/llms.txt): image-to-image
- [Nano Banana Pro](https://developer.muvi.video/files/llms/models/google/nano-banana-pro/edit-image/llms.txt): image-to-image
- [Nano Banana Pro](https://developer.muvi.video/files/llms/models/google/nano-banana-pro/text-to-image/llms.txt): text-to-image
- [Grok Imagine](https://developer.muvi.video/files/llms/models/xai/grok-imagine/image-to-video/llms.txt): Generate videos from images with audio using xAI's Grok Imagine Video model.
- [Grok Imagine](https://developer.muvi.video/files/llms/models/xai/grok-imagine/text-to-video/llms.txt): Generate videos from images with audio using xAI's Grok Imagine Video model.
- [GPT Image 2](https://developer.muvi.video/files/llms/models/openai/gpt-image-2/text-to-image/llms.txt): Generate images from text prompts using OpenAI gpt-image-2 , OpenAI Images Generations API.
- [Veo 3.1](https://developer.muvi.video/files/llms/models/google/veo-3.1/start-end-frame-to-video/llms.txt): Google Veo 3.1 start-end frame to video generation via Pixelbyte. Creates smooth video transitions between start and end frames with natural motion.
- [Veo 3.1 (ECL)](https://developer.muvi.video/files/llms/models/google/veo-3.1-ecl/image-to-video/llms.txt): Google Veo 3.1 image-to-video generation via ECL API
- [Veo 3.1 (ECL)](https://developer.muvi.video/files/llms/models/google/veo-3.1-ecl/start-end-frame-to-video/llms.txt): Google Veo 3.1 start-end frame to video generation via ECL API
- [Veo 3.1 Fast](https://developer.muvi.video/files/llms/models/google/veo-3.1-fast/start-end-frame-to-video/llms.txt): Google Veo 3.1 Fast start-end frame to video generation via Pixelbyte. Faster processing with smooth video transitions between start and end frames.
- [HappyHorse 1.0](https://developer.muvi.video/files/llms/models/alibaba/happyhorse-1-0/text-to-video/llms.txt): Alibaba HappyHorse 1.0 text-to-video — synchronized native audio (6 dil), 3-15s
- [HappyHorse 1.0](https://developer.muvi.video/files/llms/models/alibaba/happyhorse-1-0/image-to-video/llms.txt): Alibaba HappyHorse 1.0 image-to-video - no audio, aspect ratio derived from input image, 3-15s
- [HappyHorse 1.0](https://developer.muvi.video/files/llms/models/alibaba/happyhorse-1-0/reference-to-video/llms.txt): Alibaba HappyHorse 1.0 reference-to-video — 1-9 reference images, native audio, 3-15s
- [Omni Flash](https://developer.muvi.video/files/llms/models/google/omni-flash/reference-to-video/llms.txt): Google DeepMind's latest video generation with high fidelity and diverse styles.
- [Omni Flash](https://developer.muvi.video/files/llms/models/google/omni-flash/text-to-video/llms.txt): Google DeepMind's latest video generation with high fidelity and diverse styles.
- [Veo 3.1](https://developer.muvi.video/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.muvi.video/files/llms/models/google/veo-3.1/image-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1](https://developer.muvi.video/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.muvi.video/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.muvi.video/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.muvi.video/files/llms/models/google/veo-3.1-fast/text-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Pixel Image 1.0 Pro](https://developer.muvi.video/files/llms/models/pixelbyte-plus/pixel-image-1.0-pro/image-to-image/llms.txt): Pixel Image 1.0 Pro image editing via PixelByte - professional quality
- [Pixel Image 1.0 Pro](https://developer.muvi.video/files/llms/models/pixelbyte-plus/pixel-image-1.0-pro/text-to-image/llms.txt): Pixel Image 1.0 Pro text-to-image via PixelByte - professional quality
- [Pixel Image 1.0](https://developer.muvi.video/files/llms/models/pixelbyte-plus/pixel-image-1.0/image-to-image/llms.txt): Pixel Image 1.0 image editing via PixelByte
- [Pixel Image 1.0](https://developer.muvi.video/files/llms/models/pixelbyte-plus/pixel-image-1.0/text-to-image/llms.txt): Pixel Image 1.0 text-to-image via PixelByte
- [Seedance 2.0](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0/image-to-video/llms.txt): Seedance 2.0 image-to-video via PixelByte - animate images with cinematic motion
- [Seedance 2.0](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0/omni-reference/llms.txt): Seedance 2.0 omni reference to video via PixelByte - use @image1, @video1, @audio1 placeholders in prompt
- [Seedance 2.0](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0/start-end-frame-to-video/llms.txt): Seedance 2.0 start-end frame to video via PixelByte - transition between two frames
- [Seedance 2.0](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0/text-to-video/llms.txt): Seedance 2.0 text-to-video via PixelByte - cinematic video from text prompts
- [Wan 2.7](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7/image-to-video/llms.txt): Wan 2.7 image-to-video via PixelByte
- [Wan 2.7](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7/reference-to-video/llms.txt): Wan 2.7 reference-to-video via PixelByte
- [Wan 2.7](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7/text-to-video/llms.txt): Wan 2.7 text-to-video via PixelByte
- [Wan 2.7 Pro](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7-pro/image-to-image/llms.txt): Wan 2.7 Pro image editing via PixelByte - professional-tier quality
- [Wan 2.7 Pro](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7-pro/text-to-image/llms.txt): Wan 2.7 Pro text-to-image via PixelByte - professional-tier quality
- [Seedance 2.0 Fast](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0-fast/image-to-video/llms.txt): Seedance 2.0 Fast image-to-video via PixelByte
- [Seedance 2.0 Fast](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0-fast/omni-reference/llms.txt): Seedance 2.0 Fast omni reference to video via PixelByte
- [Seedance 2.0 Fast](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0-fast/start-end-frame-to-video/llms.txt): Seedance 2.0 Fast start-end frame to video via PixelByte
- [Seedance 2.0 Fast](https://developer.muvi.video/files/llms/models/bytedance/seedance-2.0-fast/text-to-video/llms.txt): Seedance 2.0 Fast text-to-video via PixelByte - faster generation
- [Wan 2.7](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7/image-to-image/llms.txt): Wan 2.7 image editing via PixelByte
- [Wan 2.7](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.7/text-to-image/llms.txt): Wan 2.7 text-to-image via PixelByte
- [Gen 4.5](https://developer.muvi.video/files/llms/models/runway/gen-4.5/text-to-video/llms.txt): Runway Gen 4.5 video generation model
- [Gen 4.5](https://developer.muvi.video/files/llms/models/runway/gen-4.5/image-to-video/llms.txt): Runway Gen 4.5 image-to-video model
- [Seedream V5 Lite](https://developer.muvi.video/files/llms/models/bytedance-plus/seedream-v5-lite/image-to-image/llms.txt): Seedream V5 Lite image editing via PixelByte - preserves facial features, lighting, color tones
- [Seedream V5 Lite](https://developer.muvi.video/files/llms/models/bytedance-plus/seedream-v5-lite/text-to-image/llms.txt): Seedream V5 Lite text-to-image via PixelByte - 4K images with Chain of Thought reasoning
- [Kling O3 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-pro/image-to-video/llms.txt): Kling Omni Video O3 Pro image-to-video via PixelByte
- [Kling O3 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-pro/reference-to-video/llms.txt): Kling Omni Video O3 Pro reference-to-video via PixelByte
- [Kling O3 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-pro/start-end-frame-to-video/llms.txt): Kling Omni Video O3 Pro start-end-frame via PixelByte
- [Kling O3 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-pro/text-to-video/llms.txt): Kling Omni Video O3 Pro text-to-video via PixelByte
- [Gen 4](https://developer.muvi.video/files/llms/models/runway/gen-4/image-to-video/llms.txt): Runway Gen 4 image-to-video model
- [Gen 4 Turbo](https://developer.muvi.video/files/llms/models/runway/gen-4-turbo/image-to-video/llms.txt): Runway Gen 4 Turbo fast image-to-video model
- [Kling O3 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-standard/image-to-video/llms.txt): Kling Omni Video O3 Standard image-to-video via PixelByte
- [Kling O3 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-standard/reference-to-video/llms.txt): Kling Omni Video O3 Standard reference-to-video via PixelByte
- [Kling O3 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-standard/start-end-frame-to-video/llms.txt): Kling Omni Video O3 Standard start-end-frame via PixelByte
- [Kling O3 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o3-standard/text-to-video/llms.txt): Kling Omni Video O3 Standard text-to-video via PixelByte
- [Seedream V4.5](https://developer.muvi.video/files/llms/models/bytedance-plus/seedream-v4.5/image-to-image/llms.txt): Seedream V4.5 image editing via PixelByte - facial feature preservation up to 4K
- [Seedream V4.5](https://developer.muvi.video/files/llms/models/bytedance-plus/seedream-v4.5/text-to-image/llms.txt): Seedream V4.5 image editing via PixelByte - facial feature preservation up to 4K
- [Kling 3.0 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-pro/image-to-video/llms.txt): Kling 3.0 Pro image-to-video generation via PixelByte
- [Kling 3.0 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-pro/start-end-frame-to-video/llms.txt): Kling 3.0 Pro start-end-frame-to-video generation via PixelByte
- [Kling 3.0 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-pro/text-to-video/llms.txt): Kling 3.0 Pro text-to-video generation via PixelByte
- [Wan 2.6 Pro](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6-pro/image-to-video/llms.txt): Wan 2.6 Pro image-to-video via PixelByte - premium quality up to 4K
- [Kling O1](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-pro/image-to-video/llms.txt): Kling Omni Video O1 image-to-video via PixelByte
- [Kling O1](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-pro/reference-to-video/llms.txt): Kling Omni Video O1 reference-to-video via PixelByte
- [Kling O1](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-pro/start-end-frame-to-video/llms.txt): Kling Omni Video O1 start-end-frame via PixelByte
- [Kling O1](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-pro/text-to-video/llms.txt): Kling Omni Video O1 text-to-video via PixelByte
- [Wan 2.6](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6/image-to-video/llms.txt): Wan 2.6 image-to-video via PixelByte
- [Wan 2.6](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6/reference-to-video/llms.txt): Wan 2.6 reference-to-video via PixelByte
- [Wan 2.6](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6/text-to-video/llms.txt): Wan 2.6 text-to-video via PixelByte
- [Wan 2.6](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6/video-extend/llms.txt): Wan 2.6 video-extend via PixelByte - extend short clips into longer videos
- [Kling 3.0 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-standard/image-to-video/llms.txt): Kling 3.0 Standard image-to-video generation via PixelByte
- [Kling 3.0 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-standard/start-end-frame-to-video/llms.txt): Kling 3.0 Standard start-end-frame-to-video generation via PixelByte
- [Kling 3.0 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-3.0-standard/text-to-video/llms.txt): Kling 3.0 Standard text-to-video generation via PixelByte
- [Kling O1 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-standard/image-to-video/llms.txt): Kling Omni Video O1 Standard image-to-video via PixelByte
- [Kling O1 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-standard/reference-to-video/llms.txt): Kling Omni Video O1 Standard reference-to-video via PixelByte
- [Kling O1 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-standard/start-end-frame-to-video/llms.txt): Kling Omni Video O1 Standard start-end-frame via PixelByte
- [Kling O1 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-o1-standard/text-to-video/llms.txt): Kling Omni Video O1 Standard text-to-video via PixelByte
- [Wan 2.6 Flash](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6-flash/image-to-video/llms.txt): Wan 2.6 Flash image-to-video via PixelByte - speed optimized
- [Wan 2.6 Flash](https://developer.muvi.video/files/llms/models/alibaba-plus/wan-2.6-flash/reference-to-video/llms.txt): Wan 2.6 Flash reference-to-video via PixelByte
- [Kling 2.6 Pro](https://developer.muvi.video/files/llms/models/kling/kling-2.6-pro/image-to-video/llms.txt): Kling 2.6 Pro image-to-video generation
- [Kling 2.6 Pro](https://developer.muvi.video/files/llms/models/kling/kling-2.6-pro/text-to-video/llms.txt): Kling 2.6 Pro text-to-video generation
- [Kling 2.6 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.6-pro/image-to-video/llms.txt): Kling 2.6 Pro image-to-video generation via PixelByte
- [Kling 2.6 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.6-pro/text-to-video/llms.txt): Kling 2.6 Pro text-to-video generation via PixelByte
- [Hailuo 2.3 Pro](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-pro/image-to-video/llms.txt): Hailuo 2.3 Pro image-to-video via PixelByte - 1080p ultra-clear output
- [Hailuo 2.3 Pro](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-pro/text-to-video/llms.txt): Hailuo 2.3 Pro text-to-video via PixelByte - 1080p, 85% complex-instruction accuracy
- [Hailuo 2.3 Fast Pro](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-fast-pro/image-to-video/llms.txt): Hailuo 2.3 Fast Pro image-to-video via PixelByte - 1080p fast generation
- [Kling 2.6 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.6-standard/image-to-video/llms.txt): Kling 2.6 Standard image-to-video generation via PixelByte
- [Kling 2.6 Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.6-standard/text-to-video/llms.txt): Kling 2.6 Standard text-to-video generation via PixelByte
- [Hailuo 2.3 Standard](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-standard/image-to-video/llms.txt): Hailuo 2.3 Standard image-to-video via PixelByte - 768p with duration control
- [Hailuo 2.3 Standard](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-standard/text-to-video/llms.txt): Hailuo 2.3 Standard text-to-video via PixelByte - 768p with duration control
- [Kling 2.5 Turbo Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.5-turbo-pro/image-to-video/llms.txt): Kling 2.5 Turbo Pro image-to-video generation via PixelByte
- [Kling 2.5 Turbo Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.5-turbo-pro/text-to-video/llms.txt): Kling 2.5 Turbo Pro text-to-video generation via PixelByte
- [Hailuo 2.3 Fast](https://developer.muvi.video/files/llms/models/minimax-plus/hailuo-2.3-fast/image-to-video/llms.txt): Hailuo 2.3 Fast image-to-video via PixelByte - 768p optimized for speed
- [Kling O1](https://developer.muvi.video/files/llms/models/kling/kling-omni-o1/image-to-video/llms.txt): Kling O1 image-to-video generation
- [Kling O1](https://developer.muvi.video/files/llms/models/kling/kling-omni-o1/text-to-video/llms.txt): Kling O1 text-to-video generation
- [Kling 3.0](https://developer.muvi.video/files/llms/models/kling/kling-text2video-v3/text-to-video/llms.txt): Kling 3.0 text-to-video generation
- [Kling 2.6](https://developer.muvi.video/files/llms/models/kling/kling-text2video-v26/text-to-video/llms.txt): Kling 2.6 text-to-video generation
- [Kling Text2Video V2.5](https://developer.muvi.video/files/llms/models/kling/kling-text2video-v25/text-to-video/llms.txt): Kling Text2Video V2.5 text-to-video generation
- [Kling 3.0](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v3/image-to-video/llms.txt): Kling 3.0 image-to-video generation
- [Kling 3.0](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v3/start-end-frame-to-video/llms.txt): Kling 3.0 start-end-frame-to-video generation
- [Kling O1](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-o1/start-end-frame-to-video/llms.txt): Kling O1 start-end-frame-to-video generation
- [Kling 2.6](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v26/image-to-video/llms.txt): Kling 2.6 image-to-video generation
- [Kling 2.6](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v26/start-end-frame-to-video/llms.txt): Kling 2.6 start-end-frame-to-video generation
- [Kling 2.5 Turbo Standard](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.5-turbo-standard/image-to-video/llms.txt): Kling 2.5 Turbo Standard image-to-video generation via PixelByte
- [Kling I2V Frames V2.5](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v25/image-to-video/llms.txt): Kling I2V Frames V2.5 image-to-video generation
- [Kling I2V Frames V2.5](https://developer.muvi.video/files/llms/models/kling/kling-i2v-frames-v25/start-end-frame-to-video/llms.txt): Kling I2V Frames V2.5 start-end-frame-to-video generation
- [Kling 3.0](https://developer.muvi.video/files/llms/models/kling/kling-elements-i2v-v3/image-to-video-elements/llms.txt): Kling 3.0 image-to-video generation with elements
- [Kling Extend 3.0](https://developer.muvi.video/files/llms/models/kling/kling-extend-v3/extend-video/llms.txt): Kling Extend V3 video extension
- [Kling 2.1 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.1-pro/image-to-video/llms.txt): Kling 2.1 Pro image-to-video generation via PixelByte
- [Kling 2.1 Pro](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.1-pro/start-end-frame-to-video/llms.txt): Kling 2.1 Pro start-end-frame-to-video generation via PixelByte
- [Kling 2.1 Master](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.1-master/image-to-video/llms.txt): Kling 2.1 Master image-to-video generation via PixelByte
- [Kling 2.1 Master](https://developer.muvi.video/files/llms/models/kling-plus/kling-2.1-master/text-to-video/llms.txt): Kling 2.1 Master text-to-video generation via PixelByte
- [GPT Images 2](https://developer.muvi.video/files/llms/models/openai/gpt-image-2/edit-image/llms.txt): GPT Images 2 reference-to-image generation. Generates images from text prompts and reference images.
- [GPT Image 1.5](https://developer.muvi.video/files/llms/models/openai/gpt-image-1.5/edit-image/llms.txt): GPT Image 1.5 image generation
- [GPT Image 1.5](https://developer.muvi.video/files/llms/models/openai/gpt-image-1.5/text-to-image/llms.txt): GPT Image 1.5 image generation
- [GPT Image 1 Mini](https://developer.muvi.video/files/llms/models/openai/gpt-image-1-mini/edit-image/llms.txt): GPT Image 1 Mini image generation
- [GPT Image 1 Mini](https://developer.muvi.video/files/llms/models/openai/gpt-image-1-mini/text-to-image/llms.txt): GPT Image 1 Mini image generation
- [Seedream 5](https://developer.muvi.video/files/llms/models/seedance/seedream-5/edit-image/llms.txt): Seedream 5 image generation
- [Seedream 5](https://developer.muvi.video/files/llms/models/seedance/seedream-5/text-to-image/llms.txt): Seedream 5 image generation
- [Gen 4 Image](https://developer.muvi.video/files/llms/models/runway/gen-4-image/edit-image/llms.txt): Gen 4 Image image generation
- [Gen 4 Image](https://developer.muvi.video/files/llms/models/runway/gen-4-image/text-to-image/llms.txt): Gen 4 Image image generation
- [Gen 4 Turbo Image](https://developer.muvi.video/files/llms/models/runway/gen-4-turbo-image/edit-image/llms.txt): Gen 4 Turbo Image image generation
- [PixVerse V6](https://developer.muvi.video/files/llms/models/pixverse/pixverse-v6/text-to-video/llms.txt): PixVerse V6 text-to-video generates seamless 1-15 second videos up to 1080p with optional native synchronized audio and multi-clip mode.
- [PixVerse V6](https://developer.muvi.video/files/llms/models/pixverse/pixverse-v6/image-to-video/llms.txt): PixVerse V6 image-to-video animates a still image into a 1-15 second video up to 1080p with optional native audio.
- [PixVerse V6](https://developer.muvi.video/files/llms/models/pixverse/pixverse-v6/start-end-frame/llms.txt): PixVerse V6 transition generates a 1-15 second video that smoothly morphs from a start frame to an end frame, up to 1080p with optional audio.
- [Seedance 1.5 Pro](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro/image-to-video/llms.txt): ByteDance Seedance 1.5 Pro image-to-video animates a still image into a 4-12 second video at up to 1080p with optional native audio and camera control.
- [Seedance 1.5 Pro](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro/text-to-video/llms.txt): ByteDance Seedance 1.5 Pro text-to-video generates a 4-12 second video at up to 1080p from a text prompt with optional native audio and camera control.
- [Seedance 1.5 Pro](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro/start-end-frame/llms.txt): ByteDance Seedance 1.5 Pro start-end-frame generates a 4-12 second video that smoothly transitions from a start frame to an end frame, up to 1080p with optional native audio.
- [Seedance 1.5 Pro Fast](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro-fast/image-to-video/llms.txt): ByteDance Seedance 1.5 Pro Fast image-to-video — production-tuned variant with no cold starts. Animates a still image into a 4-12 second video at 720p or 1080p with optional native audio.
- [Seedance 1.5 Pro Fast](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro-fast/text-to-video/llms.txt): ByteDance Seedance 1.5 Pro Fast text-to-video — production-tuned variant with no cold starts. Generates a 4-12 second video at 720p or 1080p from a text prompt with optional native audio.
- [Seedance 1.5 Pro Fast](https://developer.muvi.video/files/llms/models/bytedance-plus/seedance-v1.5-pro-fast/start-end-frame/llms.txt): ByteDance Seedance 1.5 Pro Fast start-end-frame — production-tuned variant. Generates a 4-12 second transition video from start frame to end frame at 720p or 1080p with optional native audio.

## Categories

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