# Luma Ray 3.2

> Luma's flagship Ray video model. Text-to-video and keyframe (start/end image) generation with optional HDR-encoded output and professional EXR export.

- **Provider**: replicate
- **Model ID**: luma/ray-3.2
- **Category**: video_generation
- **Credits**: 1740 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

- `duration` (integer, optional): Video duration in seconds. 10s is not supported with hdr, start_image, end_image, or loop. (Default: `5`; Options: `5`, `10`)
- `end_image` (string, optional): Optional last frame of the video. Only valid with 5s duration; not supported with loop.
- `aspect_ratio` (string, optional): Aspect ratio of the generated video. Ignored when start_image or end_image is set — the model derives the ratio from the anchor frame(s). (Default: `16:9`; Options: `9:16`, `3:4`, `1:1`, `4:3`, `16:9`, `21:9`)
- `loop` (boolean, optional): Generate a seamlessly looping video. Not supported with 10s duration, hdr, or end_image. (Default: `False`)
- `hdr` (boolean, optional): Generate HDR-encoded MP4. Requires 720p or 1080p, 5s duration, and no loop. (Default: `False`)
- `exr_export` (boolean, optional): Export an EXR file alongside the MP4 for professional colour-grading workflows. Requires hdr=true. (Default: `False`)
- `prompt` (string, **required**): Text prompt describing the video. Be specific about subject, motion, camera movement, lighting, and pacing.
- `resolution` (string, optional): Output resolution. 540p is not available when hdr is true. (Default: `720p`; Options: `540p`, `720p`, `1080p`)
- `start_image` (string, optional): Optional first frame of the video. Only valid with 5s duration.

## Example Request

```json
{
  "model": "luma/ray-3.2",
  "input": {
    "prompt": "your prompt here"
  }
}
```

## 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

luma, ray, video-generation, text-to-video, keyframes, hdr

## Documentation

https://replicate.com/luma/ray-3.2