Cumulus LabsBack to Leaderboard
Vision
Qwen 2.5 VL 7B
+7.6%~$Q25VL
Efficient vision-language model at 7B scale. Handles images, documents, and video frames with strong multimodal reasoning. Runs on all 4 universal-a nodes.
Deploy Now
#12 overall · 4 deploys
1.3s
Cold Start
avg on Ion
445ms
Avg Inference
per request
4
Active Replicas
right now
4
Total Deployments
all time
7-Day Trend
+7.6% this weekCold Start vs Competitors
Lower is better●~$Q25VL1.3s
~$QW3VL1.3s
~$IVNL1.4s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.50
Est. Daily (1K req/day)
$0.50
Est. Monthly (30K req)
$15.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 2.5 VL 7B on Ion const client = await cumulus.deploy("qwen2-5-vl-7b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })