---
title: LTX-2.5 Fast | Runware Docs
url: https://runware.ai/docs/models/lightricks-ltx-2-5-fast
description: Fast high-resolution video generation with longer clip support, native audio, and first-to-last-frame control
---
# LTX-2.5 Fast

![LTX-2.5 Fast](https://assets.runware.ai/covers/lightricks-ltx-2-5-fast.jpg)

LTX-2.5 Fast is the speed-focused variant in the LTX 2.5 video family, built for high-throughput text-to-video and image-to-video generation. It supports output from 720p through 4K, longer durations at HD resolutions, optional native audio generation, and first-to-last-frame image guidance for more directed motion and shot planning. It is well suited to rapid creative iteration, storyboard development, social and advertising content, and other video workflows that need faster turnaround without dropping to low-end resolutions.

- **Status**: live
- **ID**: `lightricks:ltx@2.5-fast`
- Try in Playground
- **Creator**: Lightricks
- **Release Date**: August 11, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.09 from, per second · ~44s per request

**Rates** (per second)

- 720p: `$0.09`
- 1080p: `$0.13`
- 2K: `$0.19`
- 4K: `$0.30`

**4 example generations**

- [audio-driven](https://runware.ai/docs/models/lightricks-ltx-2-5-fast/examples#example-volcanology-museum-sonic-logo-loop) · 1080p: `$0.78` (~34s)
- [first-last-frame](https://runware.ai/docs/models/lightricks-ltx-2-5-fast/examples#example-pneumatic-flood-barrier-deployment-demo) · 1080p · 8s: `$1.04` (~53s)
- [text-to-video](https://runware.ai/docs/models/lightricks-ltx-2-5-fast/examples#example-rooftop-apiary-honey-harvest-ad) · 720p · 12s · audio: `$1.08` (~29s)
- [first-frame](https://runware.ai/docs/models/lightricks-ltx-2-5-fast/examples#example-hydrographic-survey-studio-logo-loop) · 1440p · 10s: `$1.90` (~1m 4s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `fps` is `48, or 50`, `duration` must be at most `10`.

---

Inside `inputs`, `frameImages` cannot be used with `audio`.

---

When `inputs.audio` is provided, `duration` and `settings.cameraMovement` cannot be used.

---

When `inputs.audio` is provided, `inputs.referenceImages` is required.

---

When `inputs.audio` is provided, dimensions are limited to `1920×1080` or `1080×1920`.

---

When `inputs.referenceImages` is provided, `inputs.audio` is required.

---

`width` and `height` must be used together.

---

When `width` or `height` is provided, `duration` must be at most `10`.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (9:16)` | `1080x1920` |
| `2K (16:9)` | `2560x1440` |
| `2K (9:16)` | `1440x2560` |
| `4K (16:9)` | `3840x2160` |
| `4K (9:16)` | `2160x3840` |

## Notes

LTX-2.5 Fast decides what to generate from the input you attach:

- **Text-to-Video:** Provide a prompt on its own.
- **Image-to-Video:** Provide `inputs.frameImages`. The first entry opens the clip and an optional second one closes it.
- **Audio-to-Video:** Provide `inputs.audio` together with a single `inputs.referenceImages` entry that establishes the subject. Frame images cannot be combined with audio.

**Duration:** Set `duration` to a whole number of seconds, or `auto` to let the model read the length from the prompt. A one-line action stays short and a multi-shot sequence runs longer, but the result never exceeds the ceiling for the resolution and frame rate you asked for.

Audio-driven output runs as long as the audio, so `duration` is not accepted on that path.

**Camera movement:** `settings.cameraMovement` applies a fixed camera move to the shot. It is available for text-to-video and image-to-video.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `items: 1`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [audio](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`
- **Duration**: `2s to 20s`

Audio input (UUID or URL). Drives the generated video, whose length follows the audio.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `lightricks:ltx@2.5-fast`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `5000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-width)

- **Type**: `integer`
- **Default**: `1920`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-height)

- **Type**: `integer`
- **Default**: `1080`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [duration](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-duration)

- **Type**: `integer | string`
- **Default**: `6`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Allowed values**: `6` `8` `10` `12` `14` `16` `18` `20` `auto`

### [fps](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-fps)

- **Type**: `integer`

Frames per second for video generation. Higher values create smoother motion but require more processing time.

**Allowed values**: `24` `25` `48` `50`

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [audio](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-settings-audio)

- **Path**: `settings.audio`
- **Type**: `boolean`

Generate synchronized audio.

### [cameraMovement](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#request-settings-cameramovement)

- **Path**: `settings.cameraMovement`
- **Type**: `string`

Cinematic camera movement.

**Allowed values**:

- `dolly_in` Camera moves toward the subject.
- `dolly_out` Camera moves away from the subject.
- `dolly_left` Camera tracks to the left.
- `dolly_right` Camera tracks to the right.
- `jib_up` Camera rises on a jib.
- `jib_down` Camera lowers on a jib.
- `static` Fixed camera with no movement.
- `focus_shift` Focus racks between subjects.

## Response Parameters

### [taskType](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/lightricks-ltx-2-5-fast#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-5-fast/fd6620b0-9fea-46fd-b8e0-73359b149a11.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "655d7ac1-4038-41bd-aff3-ebe3634af62c",
  "model": "lightricks:ltx@2.5-fast",
  "positivePrompt": "Cinematic landscape social media ad for an urban rooftop apiary at early sunrise. In one fluid commercial shot, begin inches above a weathered wooden hive entrance as honeybees land, crawl, and lift into the air. Reveal a beekeeper in a clean cream canvas suit gently drawing a heavy honeycomb frame from the open hive. Hundreds of bees move naturally across the amber wax while warm honey glows through the cells. A light breeze stirs the beekeeper’s veil, rooftop herbs, and flowering planters; loose bees drift through shafts of golden light against a cool blue-gray city skyline. End with the beekeeper tilting the frame toward the sun, creating a luminous amber hero image with rich tactile detail. Premium modern documentary art direction, restrained honey-gold and slate-blue palette, realistic anatomy and handling, crisp morning backlight, shallow depth of field, subtle film grain. Synchronized natural sound: layered bee hum moving with the swarm, soft wooden frame scrape, canvas rustle, rooftop wind, leaves brushing, and distant muted city traffic. No dialogue, music, lettering, labels, logos, or watermarks.",
  "width": 1280,
  "height": 720,
  "duration": 12,
  "fps": 24,
  "settings": {
    "audio": true,
    "cameraMovement": "dolly_right"
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-5-fast/a6d2d3ab-fa0a-4cd0-8bf1-03ee83d90546.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "d1e20b84-fbb8-4dbe-87f2-96194a4d0cb8",
  "model": "lightricks:ltx@2.5-fast",
  "positivePrompt": "Begin on the supplied opening frame with the PELAGIC GRID hydrographic survey identity centered and perfectly legible. Continue as a refined ten-second logo motion graphic: a narrow sea-glass cyan sonar pulse emerges from the center of the circular emblem and travels outward. As it crosses the emblem, the copper bathymetric contour lines lift into shallow dimensional relief and flow in smooth concentric waves, like a seafloor map being surveyed in real time. Fine coordinate ticks and tiny depth-point particles briefly illuminate around the circle, remaining abstract and nonverbal. The pulse expands across the surrounding ink-blue field, revealing faint chart-grid geometry and delicate topographic traces in the negative space. Copper lines move with measured precision rather than liquid chaos; the wordmark stays sharp, stable, correctly spelled, and unobstructed throughout. Near the end, the chart traces recede, particles settle back into the emblem, and the sonar ring contracts cleanly to restore the exact calm opening composition for a seamless loop. Static front-facing camera, premium broadcast motion design, crisp vector-like edges, subtle tactile print grain, deep navy, oxidized copper, and restrained cyan palette. No extra words, no new symbols, no camera move, no cuts, no mockup, no interface elements.",
  "width": 2560,
  "height": 1440,
  "duration": 10,
  "fps": 25,
  "settings": {
    "cameraMovement": "dolly_in"
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/c1be51cb-fe9f-438d-9f38-1c955a69c389.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-5-fast/bd55b634-bf94-4fa3-a8bd-94d3c128a80a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "99b4738f-bd0e-48c8-8901-69a4ca97bccb",
  "model": "lightricks:ltx@2.5-fast",
  "positivePrompt": "Create a clear, photorealistic product deployment explainer in one continuous locked-off shot. Preserve the exact flood-test hall, deep-navy barrier, safety-orange end caps, hose, anchor points, perspective and lighting established by the endpoint images. Begin with the barrier lying fully flat across the concrete channel as a shallow sheet of water advances on the far side. The connected blower activates and the textile chamber inflates progressively and credibly from the hose end: wrinkles lift, reinforced seams straighten, the tube expands along its length, orange end caps rotate into position and anchor straps draw taut. As the barrier rises, the advancing water meets it, forms small realistic splashes and gathers into a contained pool behind it. End with the barrier fully pressurized, stable and evenly shaped, holding back rippling water while the foreground remains dry. Emphasize understandable product function, realistic fabric and water physics, and a reassuring municipal engineering-demo mood. No cuts, no time lapse, no camera movement, no people, no labels, no logos, no on-screen text, no interface graphics.",
  "width": 1920,
  "height": 1080,
  "duration": 8,
  "fps": 48,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/2592add1-c054-4aa2-9c04-7ba543bcc73d.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/88442226-03d8-4ba0-80b2-3d15cbae5e0b.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-5-fast/68ce23d5-3fdb-4660-bc1d-7842bb242974.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "caaf2466-a861-43b6-b15b-2e2ad4cff922",
  "model": "lightricks:ltx@2.5-fast",
  "positivePrompt": "Create a premium 9:16 animated museum logo ident using the supplied reference image as the exact visual identity. Preserve the emblem geometry, mineral-white contour lines, vermilion fissure, basalt texture, centered composition, and the exact legibility and shape of the “CALDERA ARCHIVE” wordmark. Keep the camera locked and the background still. Drive every movement precisely from the supplied audio: the opening subterranean rumble produces an almost imperceptible vibration within the concentric contour lines; on the deep seismic thump, the rings compress inward once and release like a measured seismograph pulse; each of the four dry sensor clicks sends one clean vermilion signal around a successive contour ring; the mineral shimmer causes a restrained crystalline highlight to travel across the emblem and wordmark. Fine basalt dust may lift a few millimeters on the strongest thump, then settle naturally. Motion must feel engineered, geological, and museum-grade rather than explosive or fantastical. Maintain sharp typography and abundant negative space throughout. End on the identical fully settled frame and visual state as the opening so the video loops seamlessly with the audio.",
  "width": 1080,
  "height": 1920,
  "fps": 25
}
```