# Luma Ray 3.2 Video to Video API

> Редактирование видео Ray 3.2: изменение стиля исходного видео с пресетами, параметрами силы редактирования и ключевыми кадрами

Редактирует `video_url` согласно `prompt`, с опциональным `start_image_url` для управления первым кадром. `edit_strength` предлагает уровни adhere, flex и reimagine от 1 до 3, а `auto_controls` или объект `controls` задают альтернативное условие. До 64 `keyframes` можно закрепить с помощью `keyframe_indexes`. Результат имеет разрешение от 540p до 1080p и длительность 5s или 10s, с опциональными `hdr` и `exr_export`.

- Model id: `luma/agent/ray/v3.2/video-to-video`
- Made by: Luma AI
- Category: Video to Video
- Output: video
- Price: from $0.144 / second (5 s ≈ $0.72) (cheapest run $0.72 (720 API credits))
- Run: `POST https://api.doitong.ru/v1/run/luma/agent/ray/v3.2/video-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/luma/agent/ray/v3.2/video-to-video`
- Docs page: https://doitong.com/developers/models/luma/agent/ray/v3.2/video-to-video

## Pricing

Price: **from $0.144 / second (5 s ≈ $0.72)** (the lowest tier; the quote prices your exact input). Billed per second of output (`duration`, default 10).

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `exr_export` = true and `hdr` = true and `resolution` = 1080p: $1.296 (1296 API credits) / second
- When `exr_export` = true and `hdr` = true: $0.648 (648 API credits) / second
- When `hdr` = true and `resolution` = 1080p: $0.864 (864 API credits) / second
- When `hdr` = true: $0.432 (432 API credits) / second
- When `resolution` = 1080p: $0.432 (432 API credits) / second
- When `resolution` = 720p: $0.216 (216 API credits) / second

The full example input below costs $0.72 = 720 API credits (5 s × 144 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/luma/agent/ray/v3.2/video-to-video` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 6000 characters | Text instructions for editing the source video. |
| `video_url` | `video` | string (video URL) | yes |  | ≥ 1 characters | URL for the video being edited. |
| `user` |  | string \| null | no |  |  | Optional opaque ID identifying the end user who submits the request. |
| `start_image_url` | `image` | string (image URL) \| null | no |  |  | First-frame override for the edited video, supplied as an optional image URL; when omitted, the model derives that frame from the source video. For example, supplying a restyled opening image from the source can guide the edit's appearance. |
| `resolution` |  | enum (string) | no | `540p` | `540p`, `720p`, `1080p` | Output resolution after editing. |
| `duration` |  | enum (string) | no | `5s` | `5s`, `10s` | Length of the video after editing. |
| `edit_strength` |  | enum (string) \| null | no |  | `adhere_1`, `adhere_2`, `adhere_3`, `flex_1`, `flex_2`, `flex_3`, `reimagine_1`, `reimagine_2`, `reimagine_3` | Source-preservation setting for edits, available only when auto_controls is not used; omission selects the model's default. From greatest departure to closest adherence, the options are 'reimagine_*', 'flex_*' for a balanced result, and 'adhere_*'. |
| `auto_controls` |  | boolean | no | `false` |  | Automatic edit conditioning: the model uses the source video to determine the schedule rather than accepting edit_strength alongside this option. |
| `hdr` |  | boolean | no | `false` |  | HDR encoding for MP4 output at either 720p or 1080p, available only to accounts with HDR access. |
| `exr_export` |  | boolean | no | `false` |  | Additional EXR export accompanying the MP4, available only with both HDR access and hdr=true. |
| `controls` |  | object {pose, depth, normals, trajectory, face} \| null | no |  |  | Fine-grained alternative to edit_strength that configures conditioning separately for pose, depth, normals, trajectory, and face. Using these controls rules out auto_controls. |
| `controls.pose` |  | object {enabled, strength} \| null | no |  |  | Conditioning based on pose or skeleton. |
| `controls.pose.enabled` |  | boolean | no | `true` |  | Toggle for pose or skeleton conditioning during editing. |
| `controls.pose.strength` |  | enum (string) \| null | no |  | `precise`, `coarse` | Pose-conditioning precision selection: retain the default by omitting it, choose 'coarse' for greater freedom, or use 'precise' to track the source pose tightly. |
| `controls.depth` |  | object {enabled, blur} \| null | no |  |  | Conditioning based on depth or scene geometry. |
| `controls.depth.enabled` |  | boolean | no | `true` |  | Toggle for depth or scene-geometry conditioning during editing. |
| `controls.depth.blur` |  | number \| null | no |  | 0 – 1 | Depth blur setting, left unspecified to retain the default or increased to give geometry greater freedom. |
| `controls.normals` |  | object {enabled, augmentation} \| null | no |  |  | Conditioning based on surface normals. |
| `controls.normals.enabled` |  | boolean | no | `true` |  | Toggle for surface-normal conditioning during editing. |
| `controls.normals.augmentation` |  | number \| null | no |  | 0 – 1 | Surface-normal augmentation setting; retain the default by omitting it, or increase it to permit greater reinterpretation of surface geometry. |
| `controls.trajectory` |  | object {enabled, sparsity} \| null | no |  |  | Conditioning based on motion trajectories. |
| `controls.trajectory.enabled` |  | boolean | no | `true` |  | Toggle for motion-trajectory conditioning during editing. |
| `controls.trajectory.sparsity` |  | number \| null | no |  | 0 – 1 | Motion-trajectory sparsity setting; omit it to retain the default, or increase it to reduce how many motion anchors are used. |
| `controls.face` |  | object {enabled} \| null | no |  |  | Conditioning based on facial identity. |
| `controls.face.enabled` |  | boolean | no | `true` |  | Toggle for face-identity conditioning during editing. |
| `keyframes` |  | array of string \| null | no |  | 1 – 64 items | Multi-keyframe editing guides supplied as image URLs instead of start_image_url. Supply keyframes together with an equally long keyframe_indexes array to pin each image to its source-video frame position; at most 64 URLs are allowed. |
| `keyframe_indexes` |  | array of integer \| null | no |  | 1 – 64 items | Source-frame mapping paired one-to-one with keyframes: entry [i] specifies the anchor position for keyframes[i]. Both arrays must have equal lengths, and positions must be distinct and non-negative. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Screening can be relaxed by setting false, provided the caller is authorized. |

File parameters (`video`, `image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/luma/agent/ray/v3.2/video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/luma/agent/ray/v3.2/video-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/luma/agent/ray/v3.2/video-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "luma/agent/ray/v3.2/video-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "luma/agent/ray/v3.2/video-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 720,
    "usd": "0.72",
    "charged": 720,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "exr_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Video produced by the model. |
| `exr_file` | object {url, content_type, file_name, file_size} \| null | EXR sidecar in the form Luma exports: either one EXR file or a ZIP archive. It is generated when exr_export is true. |

## Related models

- [Luma Ray 3.2 Text to Video](https://doitong.com/developers/models/luma/agent/ray/v3.2/text-to-video.md) (`luma/agent/ray/v3.2/text-to-video`): from $0.10 / second
- [Luma Ray 3.2 Image to Video](https://doitong.com/developers/models/luma/agent/ray/v3.2/image-to-video.md) (`luma/agent/ray/v3.2/image-to-video`): from $0.03 / second
- [Luma Ray 3.2 Reframe](https://doitong.com/developers/models/luma/agent/ray/v3.2/reframe.md) (`luma/agent/ray/v3.2/reframe`): from $0.06 / second of input video
- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time
- [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md) (`fast-animatediff/turbo/video-to-video`): $0.00125 / second of processing time
- [AnimateDiff · Video to Video](https://doitong.com/developers/models/fast-animatediff/video-to-video.md) (`fast-animatediff/video-to-video`): $0.00125 / second of processing time
- [Auto-Captioner](https://doitong.com/developers/models/auto-caption.md) (`auto-caption`): $0.10 / video
- [Bernini-R Edit Video](https://doitong.com/developers/models/bernini-r/edit-video.md) (`bernini-r/edit-video`): from $0.04 / second of output video

## Links

- HTML page: https://doitong.com/developers/models/luma/agent/ray/v3.2/video-to-video
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=luma/agent/ray/v3.2/video-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/luma/agent/ray/v3.2/video-to-video