models

Ltx 095

Markdown · JSON

Ltx 095

Ltx 095 generates videos from text or a supplied image. Describe the subject and action, then use an optional negative prompt to identify unwanted visual details when that control is available.

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Ltx 095 is a Lightricks video-generation entry with documented text-to-video and image-to-video capability. Keep this exact model selection with the shot when comparing or revising results. A text brief establishes the scene, while an optional image can supply the starting composition and subject appearance.

Build the brief around a visible change. A curtain lifting in a breeze, a ceramic cup rotating into a new view or a character turning toward a sound each gives the sequence an identifiable event. Describe the initial situation, the movement and the view that should remain at the end.

For a scene developed from text, identify the main subject and the details needed to recognize it. Add the location, lighting and camera viewpoint that shape the shot. Keep the description internally consistent so the same subject, place and action can be followed across the generated sequence.

For an image-led sequence, prepare a reference that fits the intended motion. Leave the subject enough room to move within the composition and keep important features visible. Describe how the scene should develop from the reference. Save that image with the result so changes in appearance can be checked against the source.

The documented controls include an optional negative prompt. Where this is exposed, use it to identify specific unwanted visual traits relevant to the scene. Keep the desired action and composition in the main brief. Preserve the exact text of both fields when recording the shot and comparing revisions.

Use an explicit camera direction when the viewpoint is part of the idea. State whether the camera stays fixed, moves alongside a subject or approaches a detail. Relate the camera’s movement to what the audience should notice. Review the resulting motion as a complete sequence, including its final framing.

For a series of visual studies, retain the exact model selection and use a consistent brief for comparison. Inspect the subject’s outline, material appearance, body proportions where relevant and relationship to the background. Record the observed differences that affect the shot’s purpose so the choice can be made from actual output.

Keep the finished video, prompt, image and selected settings together. When revising a candidate, identify a concrete issue such as a movement that ends too far from its target or a detail that changes during the shot. Preserve the successful scene elements and revise the instruction connected to that issue.

Ailoot Ultra · Video POST /v1/videos ltx-095

ltx-095

Lightricks /ltx-095

Overview

Ltx 095 generates videos from text or a supplied image. Describe the subject and action, then use an optional negative prompt to identify unwanted visual details when that control is available.

Accepted inputs
Text · Images
Results
Video

Available in Ailoot · inputs & methods

Ailoot Ultra · Video POST /v1/videos
Input types
text, image
Output types
video
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
ltx-095
Conditions: Use this exact Ailoot routing selector.
Default—
FieldpromptTypestringRequirementRequiredValues & limits
Conditions: Describe the scene and its motion.
Default—
FieldimageTypestring or array<string>RequirementOptionalValues & limits
Conditions: Use your actual publicly reachable image URL or base64 image; the selected model supports image input.
Default—
Fieldnegative_promptTypestringRequirementOptionalValues & limits
Conditions: Describe content to avoid.
Default—
Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, prompt
ParameteroptionalContractimage, negative_prompt
Parametermaterial_typesContracttext, image
ParameterconditionsContractUse this exact Ailoot routing selector., Describe the scene and its motion., Use your actual publicly reachable image URL or base64 image; the selected model supports image input., Describe content to avoid.

Method aliases: /v1/videos/generations

Lifecycle: submit_once_poll_original

GET /v1/videos/{request_id}

GET /v1/videos/generations/{request_id}

GET /v1/videos/{request_id}/content

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Pricing

How the final charge is calculated

The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Not specified When fast mode is selected
Flex mode
Not specified When flex mode is selected
Maximum reasoning effort
Not specified When maximum reasoning effort uses the default adjustment

Estimated rates for comparison

Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

ConfigurationRate scheduleForecast quantityBilling quantityCharge
ConfigurationBase token ratesRate scheduleBase rateForecast quantity—Billing quantity—Charge
Input · Input tokens · Estimate for comparison only — / 1K tokens
Output · Output tokens · Estimate for comparison only — / 1K tokens
Input · Cache read · Estimate for comparison only — / 1K tokens
Input · Cache write · Estimate for comparison only — / 1K tokens
Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens
ConfigurationPer requestRate schedule—Forecast quantity—Billing quantityone requestCharge
Input · Estimate for comparison only $0.2 per request
ConfigurationEstimated generation costRate schedule—Forecast quantityone generation estimateBilling quantity—Charge
Output · Estimated generation cost · Estimate for comparison only $0.2 estimate before generation

This estimate is not an additional charge or a fixed rate for the completed generation.

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →

Example requests

Ailoot Ultra · Video

curl · create once and retain receiptRead the original taskSave every completed owned asset
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
cat > request.json <<'JSON'
{
  "model": "ltx-095",
  "prompt": "A cat is walking on grass."
}
JSON
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
# Create once; retain id, polling_url, original task identifiers and every header.
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_STATUS'
import json,os,subprocess
from pathlib import Path
from urllib.parse import urljoin,urlsplit
r=json.loads(Path("result.json").read_text())
u=urljoin("https://api.ailoot.ai",r["polling_url"])
p=urlsplit(u)
if p.scheme!="https" or p.netloc!="api.ailoot.ai" or p.username or p.password:
    raise SystemExit("Unexpected returned polling URL; preserve the response")
subprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-D","status-headers.txt","-o","status.json"],check=True)
# Read this same original polling_url again while pending.
# Preserve unknown/result_pending_check; do not repeat creation.
PY_STATUS
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_ASSETS'
import json,os,subprocess
from pathlib import Path
from urllib.parse import urljoin,urlsplit
r=json.loads(Path("status.json").read_text())
roles={}
def visit(v,path=""):
    if isinstance(v,dict):
        for k,x in v.items(): visit(x,path+"/"+k)
    elif isinstance(v,list):
        for i,x in enumerate(v): visit(x,path+"/"+str(i))
    elif isinstance(v,str):
        u=urljoin("https://api.ailoot.ai",v); p=urlsplit(u)
        if p.scheme=="https" and p.netloc=="api.ailoot.ai" and not p.username and not p.password and p.path.startswith("/v1/media/assets/") and p.path.endswith("/content"):
            roles.setdefault(u,[]).append(path)
visit(r)
if not roles: raise SystemExit("No completed owned assets; retain the original status")
manifest=[]
for i,(u,paths) in enumerate(roles.items()):
    target=Path(f"asset-{i}.bin")
    subprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-o",str(target)],check=True)
    raw=target.read_bytes()
    if not raw: raise SystemExit("Empty asset; retain original status and metadata")
    ext="glb" if raw[:4]==b"glTF" else "png" if raw[:8]==b"\x89PNG\r\n\x1a\n" else "jpg" if raw[:3]==b"\xff\xd8\xff" else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "mp4" if raw[4:8]==b"ftyp" else "bin"
    name=f"asset-{i}.{ext}"
    if target.name!=name: target.rename(name)
    manifest.append({"file":name,"response_paths":paths,"bytes":len(raw)})
Path("asset-manifest.json").write_text(json.dumps(manifest,indent=2))
print("Saved",len(manifest),"unique owned assets; every response role retained")
PY_ASSETS

Receive and save results

Ailoot Ultra · Video

  • GET /v1/videos/{request_id}
  • GET /v1/videos/generations/{request_id}
  • GET /v1/videos/{request_id}/content
  • GET /v1/media/assets
  • GET /v1/media/assets/{asset_id}
Keep all completed results

Save every completed video or returned file; retrieve every actual returned asset URL.

Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.

If the original response needs checking

Keep the returned public task or operation id and all headers. Read only the original task; unknown or result_pending_check does not authorize another creation.

Response fields
FieldType
FieldidTypestring
Fieldpolling_urlTypestring
Fieldprovider_task_idTypestring
Fieldtask_idTypestring
FieldstatusTypestring
Fieldvideo_urlTypestring

Aliases

Model aliases

Ailoot Ultra ltx-095

Method path aliases

/v1/videos/generations

Related caller IDs

ltx-095

FAQ · Ltx 095
What inputs and results are available?

POST /v1/videos · ltx-095: text, image → video

Which fields does the request use?

POST /v1/videos · ltx-095: model, prompt, image, negative_prompt

More details

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription
Choose a discounted plan for your regular requests.
Promo code: up to 50% off
Enter your code at checkout. The price updates to reflect the current promotion.
Spending in your history
The model, tokens and amount are recorded for each request.

Choose a subscription · View model prices

Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application
Add text, image, video and audio generation to paid features in your service.
Reseller licence
Send a description of your project and how you provide access. Request written terms for use and resale.
Documents on the website
The service offer, licence agreement and data processing policy are available before you connect.

Request a reseller licence · Service offer and licence agreement