> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Ray 3.2 with Comfy Router

> Call luma_2/ray-3.2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `luma_2/ray-3.2`, served by Comfy Router from Luma 2.

**Input:** Text, Image, Video · **Output:** Video

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys?onboarding=router) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk` and `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

**Model ID:** `luma_2/ray-3.2`

**Endpoint:** `POST https://api.comfy.org/v2/models/luma_2/ray-3.2`

**Wait for the result**

```python Python theme={null}
from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment.
# The SDK automatically creates an idempotency key and reuses it for automatic retries.
with Comfy() as client:
    result = client.models.run(
        "luma_2/ray-3.2",
        {
            "prompt": "a paper boat drifting across a plain white background",
            "type": "video",
            "video": {
                "duration": "5s",
                "resolution": "360p",
            },
        },
    )

print(result)
```

```typescript TypeScript theme={null}
import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment.
// The SDK automatically creates an idempotency key and reuses it for automatic retries.
const { data } = await comfy.models.run("luma_2/ray-3.2", {
  prompt: "a paper boat drifting across a plain white background",
  type: "video",
  video: {
    duration: "5s",
    resolution: "360p",
  },
});

console.log(data);
```

```bash cURL theme={null}
curl https://api.comfy.org/v2/models/luma_2/ray-3.2 \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d "{\"prompt\": \"a paper boat drifting across a plain white background\", \"type\": \"video\", \"video\": {\"duration\":\"5s\",\"resolution\":\"360p\"}}"
```

**Queue and collect later**

The same body, sent to `POST https://api.comfy.org/v2/models/luma_2/ray-3.2/requests`. Router answers `201` with a `request_id` as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. [Queued delivery](/development/comfy-router/queue.md) walks through status, cancellation and collection.

```python Python theme={null}
import asyncio
from comfy_sdk import AsyncComfy

# Reads COMFY_API_KEY from the environment.
# Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
async def main():
    async with AsyncComfy() as client:
        handle = await client.models.submit(
            "luma_2/ray-3.2",
            {
                "prompt": "a paper boat drifting across a plain white background",
                "type": "video",
                "video": {
                    "duration": "5s",
                    "resolution": "360p",
                },
            },
        )
        print("request_id:", handle.request_id)  # with the model ID, all another process needs

        # Poll until the request completes, waiting the Retry-After the server names.
        async for update in handle.iter_events():
            print(update.status, update.queue_position)

        # The provider's own payload, the same value models.run() returns.
        # A request that failed or was cancelled raises the typed Router error here.
        result = await handle.get()

    print(result)

asyncio.run(main())
```

```typescript TypeScript theme={null}
import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment.
// Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
const handle = await comfy.models.submit("luma_2/ray-3.2", {
  prompt: "a paper boat drifting across a plain white background",
  type: "video",
  video: {
    duration: "5s",
    resolution: "360p",
  },
});
console.log("requestId:", handle.requestId); // with the model ID, all another process needs

// Poll until the request completes, waiting the Retry-After the server names.
for await (const update of handle.events()) {
  console.log(update.status, update.queuePosition);
}

// The same result models.run() returns. A request that failed or was cancelled rejects here.
const result = await handle.get();

console.log(result.data);
```

```bash cURL theme={null}
# 1. Submit. Router answers 201 with request_id, status_url, response_url and cancel_url.
curl https://api.comfy.org/v2/models/luma_2/ray-3.2/requests \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d "{\"prompt\": \"a paper boat drifting across a plain white background\", \"type\": \"video\", \"video\": {\"duration\":\"5s\",\"resolution\":\"360p\"}}"

# 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
REQUEST_ID="<request_id from the 201 body>"
curl -i https://api.comfy.org/v2/models/luma_2/ray-3.2/requests/$REQUEST_ID/status \
  -H "X-API-Key: $COMFY_API_KEY"

# 3. Collect. 200 with the model's native output, 202 with the status body while it is still running.
curl https://api.comfy.org/v2/models/luma_2/ray-3.2/requests/$REQUEST_ID \
  -H "X-API-Key: $COMFY_API_KEY"
```

## Schema

### Input

**aspect\_ratio** `string`

Output aspect ratio. The ray-3.2 video models support the subset 9:16, 3:4, 1:1, 4:3, 16:9, 21:9.

Possible values: `3:1`, `2:1`, `21:9`, `16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`, `1:2`, `1:3`

**image\_ref** `object[]`

Reference images for style/content guidance. Up to 9 for type 'image', up to 8 for type 'image\_edit'.

**image\_ref\[].data** `string`

Base64-encoded image or video data

**image\_ref\[].generation\_id** `string`

UUID of a prior completed generation to reuse as the source. Used by ray-3.2 video\_edit / video\_reframe.

**image\_ref\[].media\_type** `string`

MIME type. Required with data (and with url for video sources, e.g. video/mp4 on video\_edit / video\_reframe).

**image\_ref\[].url** `string`

Publicly accessible image or video URL

**model** `string`

Model to use. uni-1 / uni-1-max for image generation, ray-3.2 for video generation, editing, and reframing.

**output\_format** `string`

Output image format

Possible values: `png`, `jpeg`

**prompt** `string` *required*

Text prompt

**source** `object`

Reference to an image or video. Used for style/content guidance, guided generation, video-edit/video-reframe sources, and guide keyframes. Provide exactly one of generation\_id, url, or data.

**source.data** `string`

Base64-encoded image or video data

**source.generation\_id** `string`

UUID of a prior completed generation to reuse as the source. Used by ray-3.2 video\_edit / video\_reframe.

**source.media\_type** `string`

MIME type. Required with data (and with url for video sources, e.g. video/mp4 on video\_edit / video\_reframe).

**source.url** `string`

Publicly accessible image or video URL

**style** `string`

Style preset

Possible values: `auto`, `manga`

**type** `string`

The kind of generation to perform. image/image\_edit are produced by the uni-1 / uni-1-max models; video/video\_edit/video\_reframe are produced by the ray-3.2 model.

Possible values: `image`, `image_edit`, `video`, `video_edit`, `video_reframe`

**video** `object`

Video output settings for ray-3.2. Only the fields that affect validation and billing are modelled here; additional fields (edit controls, source\_position) are forwarded to Luma untouched.

**video.duration** `string`

Clip duration for ray-3.2 video / video\_edit. Defaults to 5s. HDR generation (type video) is restricted to 5s.

Possible values: `5s`, `10s`

**video.end\_frame** `object`

Reference to an image or video. Used for style/content guidance, guided generation, video-edit/video-reframe sources, and guide keyframes. Provide exactly one of generation\_id, url, or data.

**video.end\_frame.data** `string`

Base64-encoded image or video data

**video.end\_frame.generation\_id** `string`

UUID of a prior completed generation to reuse as the source. Used by ray-3.2 video\_edit / video\_reframe.

**video.end\_frame.media\_type** `string`

MIME type. Required with data (and with url for video sources, e.g. video/mp4 on video\_edit / video\_reframe).

**video.end\_frame.url** `string`

Publicly accessible image or video URL

**video.exr\_export** `boolean`

Export an EXR file alongside the MP4. Requires hdr true. Rejected for video\_reframe.

**video.hdr** `boolean`

Render in HDR. Requires 720p/1080p. Rejected for video\_reframe.

**video.keyframe\_indexes** `integer[]`

Output-frame positions for `keyframes`, same length; 0–120 for 5s, 0–240 for 10s. Forwarded untouched.

**video.keyframes** `object[]`

Guide-frame images (1–64), mutually exclusive with start\_frame/end\_frame. Billed at the requested duration; a keyframes request is never a single-keyframe extend.

**video.keyframes\[].data** `string`

Base64-encoded image or video data

**video.keyframes\[].generation\_id** `string`

UUID of a prior completed generation to reuse as the source. Used by ray-3.2 video\_edit / video\_reframe.

**video.keyframes\[].media\_type** `string`

MIME type. Required with data (and with url for video sources, e.g. video/mp4 on video\_edit / video\_reframe).

**video.keyframes\[].url** `string`

Publicly accessible image or video URL

**video.loop** `boolean`

Loop the generated clip. Create-only (type video).

**video.resolution** `string`

Output resolution for ray-3.2 video. Defaults to 720p. 360p is the draft tier. HDR requires 720p or 1080p.

Possible values: `360p`, `540p`, `720p`, `1080p`

**video.start\_frame** `object`

Reference to an image or video. Used for style/content guidance, guided generation, video-edit/video-reframe sources, and guide keyframes. Provide exactly one of generation\_id, url, or data.

**video.start\_frame.data** `string`

Base64-encoded image or video data

**video.start\_frame.generation\_id** `string`

UUID of a prior completed generation to reuse as the source. Used by ray-3.2 video\_edit / video\_reframe.

**video.start\_frame.media\_type** `string`

MIME type. Required with data (and with url for video sources, e.g. video/mp4 on video\_edit / video\_reframe).

**video.start\_frame.url** `string`

Publicly accessible image or video URL

**web\_search** `boolean`

Enable web search grounding

Generated from the schema Router serves at `GET /v2/models/luma_2/ray-3.2/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

**created\_at** `string`

Creation timestamp

**failure\_code** `string`

Machine-readable failure code for programmatic handling

Possible values: `content_moderated`, `generation_failed`, `budget_exhausted`, `output_not_found`

**failure\_reason** `string`

Human-readable failure description, populated only on a FAILED generation. `null` on a successful one.

**id** `string`

Generation identifier

**model** `string`

Model used

**output** `object[]`

A generated output entry

**output\[].type** `string`

Media type (e.g. image)

**output\[].url** `string`

Presigned URL (1hr expiry)

**state** `string`

Current state of the generation

Possible values: `queued`, `processing`, `completed`, `failed`

**type** `string`

The kind of generation to perform. image/image\_edit are produced by the uni-1 / uni-1-max models; video/video\_edit/video\_reframe are produced by the ray-3.2 model.

Possible values: `image`, `image_edit`, `video`, `video_edit`, `video_reframe`

## Examples

### Input

```json theme={null}
{
  "prompt": "a paper boat drifting across a plain white background",
  "type": "video",
  "video": {
    "duration": "5s",
    "resolution": "360p"
  }
}
```

### Output

```json theme={null}
{
  "created_at": "2027-01-01T00:00:00Z",
  "failure_code": null,
  "failure_reason": null,
  "id": "gen-luma-agents-ray32-9c1f3a0e7d52",
  "model": "ray-3.2",
  "output": [
    {
      "type": "video",
      "url": "https://example.invalid/luma_2/ray-3.2/generated.mp4"
    }
  ],
  "state": "completed",
  "type": "video"
}
```

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider, and a `413` means the request body was larger than Router accepts. Download generated assets promptly because [result URLs can expire](/development/comfy-router/reference.md#result-assets).

Any size limit named in a field description above is the provider's own bound on that field, quoted from the provider's specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see [request body size](/development/comfy-router/limitations.md#request-bodies-are-capped).

This page documents one partner model called through Comfy Router. The same `comfy-sdk` / `@comfyorg/sdk` package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: `Comfy(api_key=...)` / `new Comfy({ apiKey })`, with `client.workflows`, `client.assets` and `client.jobs`. See [Comfy SDKs](/development/api-development/sdks.md).

> **[Headers](/development/comfy-router/headers.md)**
>
> Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

> **[Using the Router API](/development/comfy-router/api.md)**
>
> Model discovery, validation errors, retries, and billing.

> **[Limitations](/development/comfy-router/limitations.md)**
>
> What Router does not do today, and what to use instead.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.