Skip to main content

LTX 2 v2.3 Fast Text-to-Video

Live
LightricksVideo generationBenchmark price · $0.4 per job
Use this model
Best discount now20.0%offYou pay 80.0% of reference.
Median discount20.0%offAcross 3 live offers.
Realized · 7 daysNot enough dataFrom 0 requests this week.
Requests · 24h03 offers from 1 seller.
Current offers
3 of 21 offers
Availability
Providers
ProviderDiscountPriceUptimeSold
Venice AI
20%
$0.32/job
0.0%
-
Venice AI
20%
$0.32/job
0.0%
-
Mordiem
10%
$0.36/job
-
-
Total
Cumulative offers
Sold
$0

Discount trend

Realized · 7 days
No trend yet.It fills in after the nightly update.

Recent fills

17:436 seconds50.0%
06:506 seconds25.0%
21:191 job52.0%
21:181 job52.0%
21:181 job52.0%
17:291 jobVenice AI50.0%
17:291 jobVenice AI50.0%
17:281 jobVenice AI50.0%
17:271 jobVenice AI50.0%
17:261 jobVenice AI50.0%
17:251 jobVenice AI50.0%
11:531 job60.0%
11:521 job60.0%
11:521 job60.0%
11:511 job60.0%
11:501 job60.0%
11:491 job60.0%
11:491 job60.0%
20:191 jobVenice AI50.0%
20:191 jobVenice AI50.0%
Times in UTCSettled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct0% of traffic
0.0% success
p50 - · p95 -
Use this model

Change your base URL.
Keep your code.

Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.

Read the quickstart ↗
Parameters this model acceptsPOST /v1/video/generations
  • modelstringThis model’s id
  • promptstringWhat to generate
  • duration_secondsnumberHow long the result runs6 · 8 · 10 · 12 · 14 · 16 · 18 · 20
Others are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
import os
import requests

response = requests.post(
    "$SURPLUS_BASE_URL/video/generations",
    headers={"Authorization": f"Bearer {os.environ['SURPLUS_API_KEY']}"},
    json={"model": "ltx-2-v2-3-fast-text-to-video", "prompt": "A lighthouse at dusk"},
)

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

Related models