RunPod increased seven Serverless GPU hourly rates, including B300 from $10.65/hr to $11.99/hr and B200 from $8.64/hr to $10.79/hr, raising inference costs. Listed B300 memory changed from 280 GB to 288 GB, and the page now announces Batch Inference as generally available on Runpod Serverless.
Machine-written from the diff below (Sol; type: price change). Check the diff before relying on it.
What changed
Struck in red is what RunPod removed; blue is what they added. Muted text is unchanged context.
BeforeAfter
Changed#1
Before: …Pricing | Per-Second H100, A100, RTX | Runpod Kimi K3 is now available on Runpod Skip to main content Product Pods On-demand GPUs,…
After: …Pricing | Per-Second H100, A100, RTX | Runpod Batch Inference is now generally available on Runpod Serverless Skip to main content Product Pods On-demand GPUs,…
Changed#2
Before: …Pricing Enterprise Contact Sales Sign in Get Started Prefer to call? Call +1 ‹tok› GPU Pricing GPU Cloud Pricing Updated ‹date› Runpod…
After: …Pricing Enterprise Contact Sales Sign in Get Started Questions? Call, text, or connect on WhatsApp. GPU Pricing GPU Cloud Pricing Updated ‹date› Runpod…
Removed#3
Before: …form. Serverless Cost effective for every inference workload. Save 25% over other Serverless cloud providers on flex workers alone. Get started GPU Per hour Per second Workers…
After: …form. Serverless Cost effective for every inference workload. removed Get started GPU Per hour Per second Workers…
Changed#4
Before: …Get started GPU Per hour Per second Workers 280 GB B300 Maximum throughput for big models. $…
After: …Get started GPU Per hour Per second Workers 288 GB B300 Maximum throughput for big models. $…
Changed#5
Before: …GB B300 Maximum throughput for big models. $ 10.65 /hr 180 GB B200 Maximum throughput for big…
After: …GB B300 Maximum throughput for big models. $ 11.99 /hr 180 GB B200 Maximum throughput for big…
Changed#6
Before: …GB B200 Maximum throughput for big models. $ 8.64 /hr 141 GB H200 Extreme throughput for big…
After: …GB B200 Maximum throughput for big models. $ 10.79 /hr 141 GB H200 Extreme throughput for big…
Changed#7
Before: …GB H200 Extreme throughput for big models. $ 5.93 /hr 96 GB RTX 6000 Pro PRO High…
After: …GB H200 Extreme throughput for big models. $ 6.99 /hr 96 GB RTX 6000 Pro PRO High…
Changed#8
Before: …H100 PRO Extreme throughput for big models. $ 4.79 /hr 80 GB A100 High throughput GPU, yet…
After: …H100 PRO Extreme throughput for big models. $ 5.39 /hr 80 GB A100 High throughput GPU, yet…
Changed#9
Before: …5090 PRO Extreme throughput for small-to-medium models. $ 1.58 /hr 32 GB RTX PRO 4500 Blackwell Cost-effective…
After: …5090 PRO Extreme throughput for small-to-medium models. $ 1.79 /hr 32 GB RTX PRO 4500 Blackwell Cost-effective…
Changed#10
Before: …4090 PRO Extreme throughput for small-to-medium models. $ 1.10 /hr 24 GB L4, A5000, 3090, MIG 24GB…
After: …4090 PRO Extreme throughput for small-to-medium models. $ 1.34 /hr 24 GB L4, A5000, 3090, MIG 24GB…
Changed#11
Before: …24GB Great for small-to-medium sized inference workloads. $ 0.69 /hr 16 GB A4000, A4500, RTX 4000, RTX…
After: …24GB Great for small-to-medium sized inference workloads. $ 0.75 /hr 16 GB A4000, A4500, RTX 4000, RTX…
Changed#12
Before: …submitting the form. Gain additional savings with reservations. Save more with long-term commitments. Speak with our team to reserve discounted active and flex workers. Get started How Runpod pricing works Runpod pricing…
After: …submitting the form. Gain additional savings with reservations. Speak with our team about Serverless reservations and contract pricing. Get started How Runpod pricing works Runpod pricing…
Added#13
Before: …Docs Company About Partners Contact Call +1 ‹tok›nothing here Careers Make infrastructure our job, so it doesn't…
After: …Docs Company About Partners Contact Call +1 ‹tok›Text us Message or call on WhatsApp Careers Make infrastructure our job, so it doesn't…
Compared with the previous archived version (#4376 to #11136). Text is normalized before comparing: dates, counters and tokens show as ‹date›, ‹count›, ‹tok›, and noise-only edits are hidden. Rewindex shows changed passages with a few words of context, not a copy of the page. View the live page (opens in new tab).
Archive proof
Rewindex commits each page capture it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert. That proves these records existed by then and have not been changed since, by anyone, Rewindex included.
RunPod increased seven Serverless GPU hourly rates, including B300 from $10.65/hr to $11.99/hr and B200 from $8.64/hr to $10.79/hr, raising inference costs. Listed B300 memory changed from 280 GB to 288 GB, and the page now announces Batch Inference as generally available on Runpod Serverless.
RunPod’s pricing page added “Using an AI agent? Point it to agents.runpod.io.” This is a promotional link addition; no pricing, plan or feature changes are shown.
Cite this
Pricing page changed: price increase on RunPod’s Pricing page, changed 2026-10-30 08:45 UTC (change 2 of 2).