Cumulus LabsBack to Leaderboard
Video
LTX-Video
+16.4%~$LTX
LTX-Video real-time video generation. Flow-matching architecture enables low-latency video synthesis. Strong temporal consistency with flexible resolution support.
Deploy Now
#23 overall · 1 deploys
15.6s
Cold Start
avg on Ion
78.0s
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+16.4% this weekCold Start vs Competitors
Lower is better●~$LTX15.6s
~$FW1416.8s
~$FWTI512.4s
~$FW1-38.2s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$22.00
Est. Daily (1K req/day)
$22.00
Est. Monthly (30K req)
$660.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy LTX-Video on Ion const client = await cumulus.deploy("ltx-video") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })