Cumulus LabsBack to Leaderboard
LLMs
DeepSeek R1 14B
+18.9%~$DSR1
DeepSeek's R1 reasoning model at 14B scale. Visible chain-of-thought with step-by-step reasoning traces. Outperforms GPT-4o on math, science, and logic benchmarks.
Deploy Now
#9 overall · 4 deploys
1.4s
Cold Start
avg on Ion
285ms
Avg Inference
per request
4
Active Replicas
right now
4
Total Deployments
all time
7-Day Trend
+18.9% this weekCold Start vs Competitors
Lower is better●~$DSR11.4s
~$QW3-81.2s
~$QW301.7s
~$QW321.8s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.80
Est. Daily (1K req/day)
$0.80
Est. Monthly (30K req)
$24.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy DeepSeek R1 14B on Ion const client = await cumulus.deploy("deepseek-r1-14b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })