Cumulus LabsBack to Leaderboard
Vision
InternVL 3.5 8B
+13.2%~$IVNL
State-of-the-art open vision-language model at 8B scale. Top scores on MMBench, DocVQA, and OCRBench. Runs on all 5 universal-b nodes.
Deploy Now
#5 overall · 5 deploys
1.4s
Cold Start
avg on Ion
520ms
Avg Inference
per request
5
Active Replicas
right now
5
Total Deployments
all time
7-Day Trend
+13.2% this weekCold Start vs Competitors
Lower is better●~$IVNL1.4s
~$QW3VL1.3s
~$Q25VL1.3s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.60
Est. Daily (1K req/day)
$0.60
Est. Monthly (30K req)
$18.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy InternVL 3.5 8B on Ion const client = await cumulus.deploy("internvl3-5-8b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })