# LTX-2.3 22B · Text to Video API

> Testun-i-fideo gyda sain, meintiau rhagosodedig, hyd at 481 o fframiau a llawer o reolaethau samplu

Yn cynhyrchu clip o `prompt`. Mae `video_size` yn cynnig rhagosodiadau sgwâr, portread a thirwedd, mae `num_frames` yn amrywio o 9 i 481, ac `fps` yn 1 i 60. Mae `generate_audio` yn ychwanegu sain. Gellir tiwnio samplu gyda `num_inference_steps` (8 i 50), graddfeydd arweiniad, `camera_lora` a graddfeydd distill LoRA ar gyfer pob rediad.

- Model id: `ltx-2.3-22b/text-to-video`
- Made by: Lightricks
- Category: Text to Video
- Output: video
- Price per megapixel of your output video: $0.00161 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-22b/text-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/text-to-video`
- Docs page: https://doitong.com/cy/developers/models/ltx-2.3-22b/text-to-video

## Pricing

Price: **$0.00161 / megapixel of output video**. Price per megapixel of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.18 = 180 API credits (112 MP output video × $0.001605).

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/ltx-2.3-22b/text-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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Anogiad a ddefnyddir fel sail ar gyfer cynhyrchu fideo. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Cyfrif fframiau'r allbwn a gynhyrchir. |
| `video_size` |  | object {width, height} \| enum (string) | no | `landscape_16_9` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensiynau'r fideo a gynhyrchwyd. |
| `generate_audio` |  | boolean | no | `true` |  | Yn rheoli a yw'r fideo'n cynnwys sain a gynhyrchwyd. |
| `use_multiscale` |  | boolean | no | `true` |  | Toglo cynhyrchu aml-raddfa ar gyfer gwell cydlyniad a manylder. Gyda True, mae fideo llai rhagarweiniol yn arwain ail gynhyrchu y mae ei faint yn cyrraedd neu'n rhagori ar y dimensiynau gofynnol. |
| `fps` |  | number | no | `24` | 1 – 60 | Cyfradd ffrâm fideo allbwn, wedi'i mesur mewn fframiau yr eiliad. |
| `num_inference_steps` |  | integer | no | `40` | 8 – 50 | Cyfrif camau casgliad a gyflawnwyd. |
| `video_cfg_scale` |  | number | no | `3` | 1 – 20 | Gosodiad arweiniad fideo: codwch ef i gael mwy o gysondeb a ffocws yn y cynnwys a gynhyrchir. Mae'n defnyddio arweiniad heb ddosbarthwr (CFG). |
| `video_stg_scale` |  | number | no | `0` | 0 – 20 | Rheoli cysondeb a ffocws fideo drwy raddfa Spatiotemporal Guidance (STG); cynyddwch y gosodiad i gryfhau'r ddau. |
| `video_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Addasiad ail-raddio fideo ar gyfer cydbwyso arweiniad heb ddosbarthwr yn erbyn arweiniad gofodol-amserol fel cymhareb. |
| `video_modality_scale` |  | number | no | `3` | 0 – 10 | Addasiad modd fideo ar gyfer cydbwyso cyfraniadau'r fideo a'r sain fel cymhareb. |
| `audio_cfg_scale` |  | number | no | `7` | 1 – 20 | Gosodiad arweiniad sain: codwch ef i gael mwy o gysondeb a ffocws yn y cynnwys a gynhyrchir. Mae'n defnyddio arweiniad heb ddosbarthwr (CFG). |
| `audio_stg_scale` |  | number | no | `0` | 0 – 20 | Rheoli cysondeb a ffocws sain drwy raddfa Spatiotemporal Guidance (STG); cynyddwch y gosodiad i gryfhau'r ddau. |
| `audio_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Addasiad ail-raddio sain ar gyfer cydbwyso arweiniad heb ddosbarthwr yn erbyn arweiniad gofodol-amserol fel cymhareb. |
| `audio_modality_scale` |  | number | no | `3` | 0 – 10 | Addasiad modd sain ar gyfer cydbwyso cyfraniadau'r fideo a'r sain fel cymhareb. |
| `gradient_estimation_gamma` |  | number | no | `2` | 0 – 10 | Gosodiad amcangyfrif graddiant dad-sŵnio: mae 0 yn diffodd yr amcangyfrif; fel arall, mae'r gwerth yn pennu gamma. |
| `use_restart_sampling` |  | boolean | no | `false` |  | Toglo samplu ailgychwyn ar gyfer ansawdd fideo o bosibl yn well: mae ei alluogi yn cyflwyno ychydig o sŵn ym mhob cam dad-sŵnio. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Dewis trefnydd. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high`, `full` | Lefel cyflymu a gymhwysir i brosesu. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Dewis LoRA camera ar gyfer rheoli symudiad yn y fideo a gynhyrchir yn fwy manwl na chan anogiadau symudiad camera yn unig. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Cryfder LoRA camera ar gyfer rheoli symudiad yn y fideo a gynhyrchir yn fwy manwl na chan anogiadau symudiad camera yn unig. |
| `negative_prompt` |  | string | no | `news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static` |  | Anogiad negyddol a ddefnyddir wrth gynhyrchu fideo. |
| `seed` |  | integer \| null | no |  |  | Gwerth hadau sy'n cychwyn cynhyrchu rhifau ar hap. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Yn rheoli a yw ehangu'r anogiad wedi'i alluogi. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Rheoli a yw gwiriad diogelwch wedi'i alluogi. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Math allbwn y fideo sy'n deillio o hynny. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Lefel ansawdd y fideo sy'n deillio o hynny. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Modd ysgrifennu'r fideo sy'n deillio o hynny. |
| `distill_lora_first_pass_scale` |  | number | no | `0.2` | 0 – 1 | Rheoli graddio LoRA distyllu'r pas cyntaf, gan ddefnyddio 0 i'w ddiffodd. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Rheoli graddio LoRA distyllu ar gyfer pob pas ar ôl y cyntaf. |

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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/ltx-2.3-22b/text-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"
  }'

# 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/ltx-2.3-22b/text-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"
  }),
});
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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-22b/text-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": "ltx-2.3-22b/text-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "ltx-2.3-22b/text-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": 180,
    "usd": "0.18",
    "charged": 180,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "prompt": "A cowboy walking through a dusty town at high noon, camera following from behind, cinematic depth, realistic lighting, western mood, 4K film grain."
  },
  "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, width, height, fps, duration, num_frames} | Fideo a gynhyrchwyd gan y model. |
| `seed` | integer | Gwerth had a ddefnyddir i gychwyn cynhyrchu rhifau ar hap. |
| `prompt` | string | Anogiad a ddefnyddir i arwain cynhyrchu. |

## Related models

- [LTX-2.3 22B · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video/lora.md) (`ltx-2.3-22b/text-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video.md) (`ltx-2.3-22b/image-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video/lora.md) (`ltx-2.3-22b/image-to-video/lora`): $0.00181 / megapixel of output video
- [LTX 2.3 22B](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video/lora.md) (`ltx-2.3-22b/reference-video-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Extend Video](https://doitong.com/developers/models/ltx-2.3-22b/extend-video.md) (`ltx-2.3-22b/extend-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Extend Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/extend-video/lora.md) (`ltx-2.3-22b/extend-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video.md) (`ltx-2.3-22b/reference-video-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/video-to-video.md) (`ltx-2.3-22b/video-to-video`): $0.00161 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-22b/text-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=ltx-2.3-22b/text-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-22b/text-to-video