# Pixverse v5.5 | Image to Video

PixVerse v5.5 generates high-quality video clips from both text and image prompts, offering smooth motion, sharp details.

## API Information

- **Model Slug:** pixverse-v5-5-image-to-video
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-v5-5/pixverse-v5-5-image-to-video
- **Provider:** PixVerse
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Pricing depends on resolution, duration, audio, and multi-clip options. A 5-second 720p single-clip video without audio costs 60 credits ($0.38). Enabling audio adds ~10 credits, multi-clip adds ~30 credits. Duration of 8s roughly doubles the cost, 10s adds ~10%% more. 1080p is 2x the cost of 720p.
- **Estimated Processing Time:** 45 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-v5-5-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Pricing depends on resolution, duration, audio, and multi-clip options. A 5-second 720p single-clip video without audio costs 60 credits ($0.38). Enabling audio adds ~10 credits, multi-clip adds ~30 credits. Duration of 8s roughly doubles the cost, 10s adds ~10%% more. 1080p is 2x the cost of 720p.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Pricing depends on resolution, duration, audio, and multi-clip options. A 5-second 720p single-clip video without audio costs 60 credits ($0.38). Enabling audio adds ~10 credits, multi-clip adds ~30 credits. Duration of 8s roughly doubles the cost, 10s adds ~10%% more. 1080p is 2x the cost of 720p. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | - |
| image_url | string | Yes | - | - | URL of the image to use as the first frame |
| resolution | string | No | 720p | 360p,540p,720p,1080p | The resolution of the generated video |
| generate_audio_switch | boolean | No | false | - | Enable audio generation (BGM, SFX, dialogue) |
| generate_multi_clip_switch | boolean | No | false | - | Enable multi-clip generation with dynamic camera changes |
| duration | string | No | 5 | 5,8,10 | The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds |
| aspect_ratio | string | No | 16:9 | 16:9,4:3,1:1,3:4,9:16 | The aspect ratio of the generated video |
| thinking_type | string | No | - | enabled,disabled | Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision |
| negative_prompt | string | No | - | - | Negative prompt to be used for the generation |
| style | string | No | - | anime,3d_animation,clay,comic,cyberpunk | The style of the generated video |
| seed | integer | No | - | - | The same seed and the same prompt given to the same version of the model will output the same video every time. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pixverse-v5-5-image-to-video",
  "input": {
    "prompt": "The superhero dog runs",
    "image_url": "https://storage.googleapis.com/magicpoint/inputs/pixverse-v5-5-image-to-video-input.png"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**pixverse-v5.5-image-to-video — Image-to-Video AI Model**

Developed by Pixverse as part of the **pixverse-v5.5** family, **pixverse-v5.5-image-to-video** transforms static images into dynamic 1080p video clips up to 8 seconds long, enabling creators to animate photos with smooth motion and realistic physics in under 30 seconds. This **image-to-video AI model** stands out by supporting image inputs alongside text prompts for precise control over camera movements and scene transitions, solving the challenge of bringing still visuals to life without complex editing software. Ideal for users seeking fast **Pixverse image-to-video** generation, it delivers high-quality outputs in versatile aspect ratios like 16:9 and 9:16, perfect for social media and marketing.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.