Cumulus LabsBack to Leaderboard
Video
FastWan T2V 1.3B
+35.2%~$FW1-3
Lightweight 1.3B text-to-video model with sub-20 second generation. Ideal for high-volume video applications where speed and cost are the priority.
Deploy Now
#17 overall · 1 deploys
8.2s
Cold Start
avg on Ion
18.0s
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+35.2% this weekCold Start vs Competitors
Lower is better●~$FW1-38.2s
~$FW1416.8s
~$FWTI512.4s
~$WAN1418.5s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$8.00
Est. Daily (1K req/day)
$8.00
Est. Monthly (30K req)
$240.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy FastWan T2V 1.3B on Ion const client = await cumulus.deploy("fastwan-t2v-1-3b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })