# LTX 2.3 Fast Text-to-Video — Atlas Cloud API

> LTX-2.3 Fast text-to-video (Lightricks LTX-2 native API): generate a cinematic clip from a text prompt, up to 4K at 24/48 fps (up to 20s at 720p/1080p, silent-only).

This is the machine-readable API reference for **LTX 2.3 Fast Text-to-Video** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `ltx/ltx-2.3-fast/text-to-video`
- **Built by**: LTX
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/ltx/ltx-2.3-fast/text-to-video
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.03 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "ltx/ltx-2.3-fast/text-to-video"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video ltx/ltx-2.3-fast/text-to-video -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `ltx/ltx-2.3-fast/text-to-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"ltx/ltx-2.3-fast/text-to-video"`

- **`prompt`** (`string`, _required_):
  Scene description including desired content, camera movement and atmosphere.
  - Default: `"A majestic eagle soaring through golden clouds at sunset, slow cinematic dolly-in, warm light."`

- **`duration`** (`integer`, _optional_):
  Video length in seconds. Durations above 10s (12–20) require 720p or 1080p at 24/25 fps; 1440p, 4k and 48 fps are limited to 6–10s.
  - Default: `6`
  - Options: 6, 8, 10, 12, 14, 16, 18, 20

- **`resolution`** (`string`, _optional_):
  Output resolution tier. Combined with aspect_ratio to select the exact frame size (720p→1280x720, 1080p→1920x1080, 1440p→2560x1440, 4k→3840x2160; portrait 9:16 swaps width/height). 1440p and 4k support 6–10s durations only.
  - Default: `"720p"`
  - Options: "720p", "1080p", "1440p", "4k"

- **`aspect_ratio`** (`string`, _optional_):
  Frame orientation: 16:9 landscape or 9:16 portrait.
  - Default: `"16:9"`
  - Options: "16:9", "9:16"

- **`fps`** (`integer`, _optional_):
  Frames per second. 48 fps is available only for durations ≤10s; at 1440p and 4k all durations are ≤10s regardless of fps.
  - Default: `24`
  - Options: 24, 25, 48, 50

- **`generate_audio`** (`boolean`, _optional_):
  Audio generation is not supported on ltx-2-3-fast; keep this false (silent video).
  - Default: `false`

- **`camera_motion`** (`string`, _optional_):
  Optional camera movement directive applied to the shot.
  - Options: "dolly_in", "dolly_out", "dolly_left", "dolly_right", "jib_up", "jib_down", "static", "focus_shift"



**Required Parameters Example**:

```json
{
  "model": "ltx/ltx-2.3-fast/text-to-video",
  "prompt": "A majestic eagle soaring through golden clouds at sunset, slow cinematic dolly-in, warm light."
}
```


**Full Example**:

```json
{
  "model": "ltx/ltx-2.3-fast/text-to-video",
  "prompt": "A majestic eagle soaring through golden clouds at sunset, slow cinematic dolly-in, warm light.",
  "duration": 6,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "fps": 24,
  "generate_audio": false,
  "camera_motion": "dolly_in"
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):

- **`message`** (`string`, _optional_):

- **`data`** (`string`, _optional_):



**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": null
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx/ltx-2.3-fast/text-to-video",
  "prompt": "A majestic eagle soaring through golden clouds at sunset, slow cinematic dolly-in, warm light.",
  "duration": 6,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "fps": 24,
  "generate_audio": false,
  "camera_motion": "dolly_in"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/ltx/ltx-2.3-fast/text-to-video)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

#### 1. Introduction

**LTX-2.3 Fast Text-to-Video** is served through the native Lightricks LTX-2 API (`api.ltx.io`). This README covers a single API model identifier:

- `ltx/ltx-2.3-fast/text-to-video`

LTX-2 is Lightricks' second-generation diffusion-transformer video model, generating video up to 4K at cinematic frame rates (24 and 48 fps). This is the **LTX-2.3 Fast** tier: it generates up to 20 seconds in a single pass at 720p/1080p and is silent-only (no audio generation). Requests are processed asynchronously (submit + poll) and every generation is delivered as a finished MP4 hosted on AtlasCloud storage.

#### 2. Key Features

- **Text-to-Video**: Generate a cinematic clip from a text prompt describing content, camera movement and atmosphere.
- **Silent Output**: This tier does not generate audio — keep `generate_audio: false`. For sound, use `ltx-2.3-pro` or the LTX-2.5 tiers.
- **Up to 4K, 24/48 fps**: Renders at 720p / 1080p / 1440p / 4K in landscape (16:9) or portrait (9:16).
- **Longer Single-Pass Clips**: Up to 20 seconds at 720p/1080p and 24/25 fps (6–20s); higher resolutions and 48 fps cap at 6–10s.
- **Camera Control**: Optional `camera_motion` directive (dolly, jib, focus shift, static).

#### 3. Support Matrix

| Resolution | Landscape | Portrait | FPS | Duration (s) |
|---|---|---|---|---|
| 720p  | 1280x720  | 720x1280  | 24 | 6, 8, 10, 12, 14, 16, 18, 20 |
| 720p  | 1280x720  | 720x1280  | 48 | 6, 8, 10 |
| 1080p | 1920x1080 | 1080x1920 | 24 | 6, 8, 10, 12, 14, 16, 18, 20 |
| 1080p | 1920x1080 | 1080x1920 | 48 | 6, 8, 10 |
| 1440p | 2560x1440 | 1440x2560 | 24, 48 | 6, 8, 10 |
| 4K    | 3840x2160 | 2160x3840 | 24, 48 | 6, 8, 10 |

`duration: -1` (automatic) is available on LTX-2.5 tiers only. Audio generation is not supported on this tier.

#### 4. Parameters

The request body matches this model's schema exactly:

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/ltx/ltx-2.3-fast/text-to-video · Docs: https://www.atlascloud.ai/docs