# Kling | o3 | Pro | Referance to Video

Transforms images, elements, and text into cohesive, high-quality video scenes while preserving character identity, object detail, and environmental consistency.

## API Information

- **Model Slug:** kling-o3-pro-reference-to-video
- **Branded URL:** https://www.eachlabs.ai/kling/kling-o3/kling-o3-pro-reference-to-video
- **Provider:** Kling
- **Category:** Reference to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Pricing is calculated per second of generated video: $0.112/sec (audio off) or $0.14/sec (audio on).
- **Estimated Processing Time:** 360 seconds
- **Last Updated:** 2026-07-13
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/kling-o3-pro-reference-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Pricing is calculated per second of generated video: $0.112/sec (audio off) or $0.14/sec (audio on).

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Pricing is calculated per second of generated video: $0.112/sec (audio off) or $0.14/sec (audio on). |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | No | - | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| multi_prompt | array | No | - | 0–5 | List of prompts for multi-shot video generation. |
| start_image_url | string | No | - | - | Image to use as the first frame of the video. |
| end_image_url | string | No | - | - | Image to use as the last frame of the video. |
| image_urls | array | No | - | 0–4 | Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video. |
| elements | array | No | - | 0–3 | Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2. |
| generate_audio | boolean | No | false | - | Whether to generate native audio for the video. |
| duration | string | No | 5 | 3,4,5,6,7,8,9,10,11,12,13,14,15 | Video duration in seconds (3-15s). Default value: "5" |
| shot_type | string | No | customize | customize | The type of multi-shot video generation. |
| aspect_ratio | string | No | 16:9 | 16:9,9:16,1:1 | The aspect ratio of the generated video frame. |

## 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": "kling-o3-pro-reference-to-video",
  "input": {}
}'
```

## 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

**kling-o3-pro-reference-to-video — Image-to-Video AI Model**

Developed by Kling as part of the **kling-o3** family, **kling-o3-pro-reference-to-video** transforms static images, multiple reference elements, and text prompts into cohesive, cinema-grade video scenes with exceptional character identity preservation and environmental consistency. This **image-to-video AI model** stands out through its multi-reference processing, supporting up to 10+ images simultaneously to maintain precise subject consistency across dynamic motions—ideal for creators seeking **Kling image-to-video** tools that deliver professional results without stitching multiple clips. Powered by the Omni architecture and Multimodal Visual Language framework, it generates up to 15-second videos at 1080p or 4K resolution, complete with native audio sync, solving the challenge of inconsistent AI animations in complex scenes.

## 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.