LTX 2.3 - Oxen.ai

Try LTX 2.3 in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: ltx-2-3 LTX 2.3 generates video from a text prompt, a first-frame image, or an audio track, served directly by Lightricks’ LTX API. One form covers all three: add an input image for image-to-video, add an audio file for a synchronized audio-to-video generation, or generate from the prompt alone, at up to 4K and 50 FPS. Pick the Fast tier for speed and cost or the Pro tier for higher fidelity; both reach 4K, and audio-to-video always runs on Pro, the only tier LTX serves it on. Editing an existing clip lives on the companion LTX 2.3 Extend, Retake, and Reframe models.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Sync
Async
Async with SSE

This blocks until the video is ready (typically 5-15 minutes). Prefer Async or Async with SSE for anything beyond quick experimentation.See the video generation reference for more details.

Minimal
Basic parameters
All parameters

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>"
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>"
    },
)
response.raise_for_status()
print(response.json())

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast"
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast"
    },
)
response.raise_for_status()
print(response.json())

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 6,
  "fps": 24,
  "generate_audio": true,
  "camera_motion": "none"
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast",
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "duration": 6,
        "fps": 24,
        "generate_audio": true,
        "camera_motion": "none"
    },
)
response.raise_for_status()
print(response.json())

See the async queue reference for more details.

Minimal
Basic parameters
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>"
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast"
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 6,
  "fps": 24,
  "generate_audio": true,
  "camera_motion": "none"
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast",
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "duration": 6,
        "fps": 24,
        "generate_audio": true,
        "camera_motion": "none"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

See the async queue reference for more details.

Minimal
Basic parameters
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "ltx-2-3",
  "prompt": "<prompt>",
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_audio": "https://example.com/audio.mp3",
  "video_mode": "fast",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 6,
  "fps": 24,
  "generate_audio": true,
  "camera_motion": "none"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "ltx-2-3",
        "prompt": "<prompt>",
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_audio": "https://example.com/audio.mp3",
        "video_mode": "fast",
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "duration": 6,
        "fps": 24,
        "generate_audio": true,
        "camera_motion": "none"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/ltx-2-3

Request parameters

Required parameters

Field	Type	Default	Description
`prompt`	`string`	—	Text description of the video to generate, or how to animate the input image.

Optional parameters

Field	Type	Default	Description
`input_image`	`string`	—	Optional first-frame image to animate (image-to-video). Leave empty to generate from the prompt alone. Format: uri.
`input_audio`	`string`	—	Optional audio track (2-20 seconds) to drive an audio-to-video generation. Output length and lip sync follow the audio; 1080p only. Always runs on Pro. Format: uri.
`video_mode`	`string`	`"fast"`	Fast is quicker and cheaper; Pro is higher fidelity. Audio-to-video always runs on Pro. One of: fast, pro.
`tail_image_url`	`string`	—	Optional last frame for image-to-video; the model interpolates between the input image and this frame. Format: uri.
`resolution`	`string`	`"1080p"`	Output resolution tier. Audio-to-video is 1080p only. One of: 720p, 1080p, 1440p, 4k.
`aspect_ratio`	`string`	`"16:9"`	Output aspect ratio. One of: 16:9, 9:16.
`duration`	`integer`	`6`	Video duration in seconds. Up to 20 seconds on Fast at 720p/1080p and 24/25 FPS, otherwise up to 10. Range: 6 – 20.
`fps`	`integer`	`24`	Frame rate. 48 and 50 FPS shorten the maximum duration. One of: 24, 25, 48, 50.
`generate_audio`	`boolean`	`true`	Generate synchronized audio for the video.
`camera_motion`	`string`	`"none"`	Camera motion effect to apply to the generated video. One of: none, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift.
`guidance_scale`	`number`	—	Audio-to-video only: how strictly the video follows the prompt. Defaults to 5 with a prompt, 9 with an input image. Range: 1 – 15.

Try LTX 2.3 in the Workbench

​Example request

​Fetch model details

​Request parameters

​Required parameters

​Optional parameters

Example request

Fetch model details

Request parameters

Required parameters

Optional parameters