Cumulus LabsBack to Leaderboard
Vision
Qwen 3 VL 8B
+17.3%~$QW3VL
Qwen 3 vision-language model with native image understanding. Excels at OCR, chart analysis, document QA, and visual reasoning. Runs on every universal and video node.
Deploy Now
#3 overall · 6 deploys
1.3s
Cold Start
avg on Ion
480ms
Avg Inference
per request
6
Active Replicas
right now
6
Total Deployments
all time
7-Day Trend
+17.3% this weekCold Start vs Competitors
Lower is better●~$QW3VL1.3s
~$IVNL1.4s
~$Q25VL1.3s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.55
Est. Daily (1K req/day)
$0.55
Est. Monthly (30K req)
$16.50
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 3 VL 8B on Ion const client = await cumulus.deploy("qwen3-vl-8b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })