Cumulus LabsBack to Leaderboard
Video
FastWan T2V 14B
+42.1%~$FW14
Distilled Wan 2.2 text-to-video at 14B scale. 3-step generation completes in under 60 seconds — 4× faster than the full model. Maximum video throughput on Ion.
Deploy Now
#15 overall · 1 deploys
16.8s
Cold Start
avg on Ion
55.0s
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+42.1% this weekCold Start vs Competitors
Lower is better●~$FW1416.8s
~$FWTI512.4s
~$FW1-38.2s
~$WAN1418.5s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$18.00
Est. Daily (1K req/day)
$18.00
Est. Monthly (30K req)
$540.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy FastWan T2V 14B on Ion const client = await cumulus.deploy("fastwan-t2v-14b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })