RunPod GPU and Serverless pricing
checked 21 November 2026
RunPod rents 46 GPU models, from $0.12 an hour (RTX A2000, community cloud). Its cheapest on-demand H100 is $3.19 (H100 NVL, secure cloud), 7% below the $3.43 market median. Storage, data transfer and billing rules are under the prices.
- Cheapest GPU $0.12 RTX A2000, community cloud
- H100 market median $3.43 RunPod's H100 is 7% below it
- 74 offers
- 46 GPU models
- Source runpod.io
In our latest check: RunPod has the cheapest on-demand rate in our index for A40, MI350X and RTX PRO 4500. None of its 74 matching prices changed since 14 November 2026.
RunPod is a GPU cloud for Pods, Serverless endpoints and multi-node clusters. The live table on this page covers Pod GPU compute, with Secure Cloud and Community Cloud labeled separately; Serverless has a different worker/runtime billing model. Pod billing is usage-based, with on-demand, prepaid savings plans and separate storage rules.
Compare the full daily GPU market
The table labels Pod and Flex serverless rates separately. Worker startup, idle time and storage can change the bill; compare those rules on the serverless GPU page. This is also not a full-bill calculator: storage configuration is separate, even though RunPod documents free Pod ingress and egress.
What else you pay at RunPod
Besides the GPU rate: Storage costs $0.10/GB/month for container or volume disk on a running Pod; $0.20/GB/month for volume disk on a stopped Pod; network volumes $0.07/GB/month under 1TB, $0.05/GB/month over 1TB. Data in and out is free. Billing is per second. A stopped instance still bills for its storage. Deposit or first charge: no fixed deposit; balance must cover at least one hour of the chosen Pod to deploy. Each of these was checked on RunPod's own documentation on 16 October 2026. Add the charges that apply to you in the job cost calculator.
RunPod prices, checked 21 November 2026
More filters: provider, memory, node size, stock, place, CPU and RAM, sort, price unit
“Machines in” filters the 16 of 74 offers whose provider says where the machine is; the others are under “Place not stated”.
“vCPUs per GPU” and “RAM per GPU” use the 18 of 74 offers whose provider publishes the machine's vCPUs or RAM for a stated number of GPUs (RunPod); an offer that does not publish them never matches a minimum. A GiB counts as 1.07 GB.
| GPU / provider | Billing | $/GPU-hour | Node · total per hour | Rent |
|---|---|---|---|---|
| RTX 2000 Ada · RunPod16 GB | secure cloud | $0.24 | – | In stock: lowRent → |
| RTX PRO 4000 Blackwell · RunPod24 GB | secure cloud | $0.57 | – | In stock: lowRent → |
| A40 · RunPod48 GB | secure cloud | $0.59 | – | In stock: mediumRent →checked 21 NovDetails
|
| RTX A6000 · RunPod48 GB | secure cloud | $0.69+16.9% in 30 days | – | In stock: lowRent →checked 21 NovDetails
|
| RTX PRO 4500 Blackwell · RunPod32 GB | secure cloud | $0.72 | – | In stock: mediumRent → |
| RTX 4090 · RunPod24 GB | secure cloud | $0.89 | – | In stock: mediumRent →checked 21 NovDetails
|
| RTX 6000 Ada · RunPod48 GB | secure cloud | $1.09+10.1% in 30 days | – | In stock: lowRent →checked 21 NovDetails
|
| A100 PCIe 80GB · RunPod80 GB | secure cloud | $2.09+16.8% in 30 days | – | In stock: lowRent →checked 21 NovDetails
|
| A100 SXM 80GB · RunPod80 GB | secure cloud | $2.19+22.3% in 30 days | – | In stock: highRent →checked 21 NovDetails
|
| RTX PRO 6000 Server · RunPod96 GB | secure cloud | $2.69+8.0% in 30 days | – | In stock: highRent →checked 21 NovDetails
|
| RTX PRO 6000 Workstation · RunPod96 GB | secure cloud | $2.79+7.7% in 30 days | – | In stock: lowRent → |
| H100 NVL · RunPod94 GB | secure cloud | $3.19 | – | In stock: lowRent →checked 21 NovDetails
|
| H100 SXM · RunPod80 GB | secure cloud | $4.39+10.0% in 30 days | – | In stock: highRent →checked 21 NovDetails
|
| H200 (SXM) · RunPod141 GB | secure cloud | $5.29 | – | In stock: mediumRent →checked 21 NovDetails
|
| MI350X · RunPod294 GB | secure cloud | $5.49 | – | In stock: lowRent → |
| B200 · RunPod180 GB | secure cloud | $7.99 | – | In stock: lowRent →checked 21 NovDetails
|
| B300 · RunPod288 GB | secure cloud | $8.99 | – | In stock: lowRent →checked 21 NovDetails
|
| RTX A4000 · RunPod16 GB | secure cloud | $0.25 | – | Out of stock |
| RTX A4500 · RunPod20 GB | secure cloud | $0.25 | – | Out of stock |
| RTX A5000 · RunPod24 GB | secure cloud | $0.27 | – | Out of stock |
| RTX 4000 Ada · RunPod20 GB | secure cloud | $0.28 | – | Out of stock |
| RTX 3090 · RunPod24 GB | secure cloud | $0.50 | – | Out of stockchecked 21 NovDetails
|
| L4 · RunPod24 GB | secure cloud | $0.69+16.9% in 30 days | – | Out of stockchecked 21 NovDetails
|
| L40 · RunPod48 GB | secure cloud | $0.82 | – | Out of stock |
| RTX PRO 5000 Blackwell · RunPod48 GB | secure cloud | $0.96 | – | Out of stock |
| L40S · RunPod48 GB | secure cloud | $1.09 | – | Out of stockchecked 21 NovDetails
|
| RTX 5090 · RunPod32 GB | secure cloud | $1.39+16.8% in 30 days | – | Out of stock |
| MI300X · RunPod192 GB | secure cloud | $2.39 | – | Out of stock |
| H100 PCIe · RunPod80 GB | secure cloud | $2.89 | – | Out of stockchecked 21 NovDetails
|
| H200 NVL · RunPod143 GB | secure cloud | $3.79 | – | Out of stock |
| RTX A2000 · RunPod6 GB | community cloud | $0.12 | – | In stock: lowRent → |
| Tesla V100 PCIe · RunPod16 GB | community cloud | $0.19 | – | In stock: lowRent → |
| RTX 3090 · RunPod24 GB | community cloud | $0.22 | – | In stock: lowRent → |
| Tesla V100 SXM2 · RunPod16 GB | community cloud | $0.23 | – | In stock: lowRent → |
| RTX 4090 · RunPod24 GB | community cloud | $0.34 | – | Rent → |
| RTX 5080 · RunPod16 GB | community cloud | $0.39 | – | In stock: lowRent → |
| RTX 6000 Ada · RunPod48 GB | community cloud | $0.74 | – | Rent → |
| RTX PRO 4500 Blackwell · RunPod32 GB · Flex worker | serverless | $1.15$0.000319/sec | – | Rent → |
| A100 PCIe 80GB · RunPod80 GB | community cloud | $1.19 | – | Rent → |
| RTX 4090 · RunPod24 GB · Flex worker | serverless | $1.34$0.000372/sec+21.8% in 30 days | – | Rent → |
| A100 SXM 80GB · RunPod80 GB | community cloud | $1.39 | – | Rent → |
| RTX PRO 6000 Server · RunPod96 GB | community cloud | $1.69 | – | Rent → |
| RTX PRO 6000 Workstation · RunPod96 GB | community cloud | $1.69 | – | Rent → |
| RTX 5090 · RunPod32 GB · Flex worker | serverless | $1.89$0.000525/sec+19.6% in 30 days | – | Rent → |
| H100 NVL · RunPod94 GB | community cloud | $2.59 | – | Rent → |
| H100 SXM · RunPod80 GB | community cloud | $2.69 | – | Rent → |
| A100 · RunPod80 GB · Flex worker | serverless | $2.99$0.000831/sec+9.9% in 30 days | – | Rent → |
| H200 (SXM) · RunPod141 GB | community cloud | $3.59 | – | In stock: lowRent → |
| RTX PRO 6000 · RunPod96 GB · Flex worker | serverless | $3.69$0.001025/sec+5.7% in 30 days | – | Rent → |
| H100 · RunPod80 GB · Flex worker | serverless | $5.89$0.001636/sec+23.0% in 30 days | – | Rent → |
| B200 · RunPod180 GB | community cloud | $5.98 | – | Rent → |
| B300 · RunPod288 GB | community cloud | $6.94 | – | Rent → |
| H200 (SXM) · RunPod141 GB · Flex worker | serverless | $6.99$0.001942/sec+17.9% in 30 days | – | Rent → |
| B200 · RunPod180 GB · Flex worker | serverless | $10.79$0.002997/sec+24.9% in 30 days | – | Rent → |
| B300 · RunPod288 GB · Flex worker | serverless | $11.99$0.003331/sec | – | Rent → |
| RTX 3070 · RunPod8 GB | community cloud | $0.13 | – | Out of stock |
| RTX A5000 · RunPod24 GB | community cloud | $0.16 | – | Out of stock |
| RTX 3080 · RunPod10 GB | community cloud | $0.17 | – | Out of stock |
| RTX A4000 · RunPod16 GB | community cloud | $0.17 | – | Out of stock |
| RTX 3080 Ti · RunPod12 GB | community cloud | $0.18 | – | Out of stock |
| RTX 4070 Ti · RunPod12 GB | community cloud | $0.19 | – | Out of stock |
| RTX A4500 · RunPod20 GB | community cloud | $0.19 | – | Out of stock |
| RTX 4000 Ada · RunPod20 GB | community cloud | $0.20 | – | Out of stock |
| RTX 3090 Ti · RunPod24 GB | community cloud | $0.27 | – | Out of stock |
| RTX 4080 SUPER · RunPod16 GB | community cloud | $0.28 | – | Out of stock |
| RTX A6000 · RunPod48 GB | community cloud | $0.33 | – | Out of stock |
| RTX 5000 Ada · RunPod32 GB | community cloud | $0.49 | – | Out of stock |
| RTX 5090 · RunPod32 GB | community cloud | $0.69 | – | Out of stock |
| L40 · RunPod48 GB | community cloud | $0.69 | – | Out of stock |
| L40S · RunPod48 GB | community cloud | $0.79 | – | Out of stock |
| RTX PRO 5000 Blackwell · RunPod48 GB | community cloud | $0.82 | – | Out of stock |
| A100 SXM 40GB · RunPod40 GB | community cloud | $1.00 | – | Out of stock |
| RTX PRO 6000 Max-Q · RunPod96 GB | community cloud | $1.64 | – | Out of stock |
| H100 PCIe · RunPod80 GB | community cloud | $1.99 | – | Out of stock |
Try another provider or reduce the minimum memory.
Fresh prices come first. Within each billing type, prices run lowest first, with unavailable offers last. Commercial relationships never affect ordering. How we collect and rank prices.
Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
Cite this data
GPU Rental Prices, "RunPod Pricing: GPU Pods & Serverless (November 2026)", prices checked 21 November 2026, https://gpurentalprices.com/providers/runpod
Quote it with a link to this page. Downloads of the whole dataset are on Data & API.
Cheapest listed per-GPU-hour rates verified at the source. Before storage, egress and networking.
RunPod access and company facts
| Check | Published information | Checked |
|---|---|---|
| Minimum account funding | no fixed deposit; balance must cover at least one hour of the chosen Pod to deploy | 16 October 2026 |
| Published compliance | ISO/IEC 27001:2022 management-system certification; SOC 2 Type II and SOC 3 examinations. Scope and current documents need checking for the intended deployment. | 27 September 2026 |
| Named customer example | Faceless.video, in a provider-published case study | 27 September 2026 |
| Data centres | Secure Cloud data centres that RunPod groups as the United States, Europe and Oceania | 18 October 2026 |
| Data centre in Japan | AP-JP-1, in Fukushima | 18 October 2026 |
| SOC 2 | Type II | 17 October 2026 |
| ISO 27001 | certified (27001:2022) | 17 October 2026 |
| Data location terms | 31 regions | 17 October 2026 |
A company fact or certification is not a guarantee for every product or region. Unrecorded fields are left unknown. The smallest recorded node does not establish immediate stock or account approval.
Strengths and trade-offs
Strengths
Computed from the verified fees and platform matrix (cells checked between 7 July 2026 and 17 October 2026 at RunPod's own documentation; verified items link to their source). Full matrices: fees · enterprise.
Pricing model
RunPod prices by workload type: Pods for dedicated GPU instances, Serverless for inference workers and Clusters for multi-node jobs. The Pods documentation says compute and storage are billed by the second, and on-demand Pods have no commitment. Savings plans are prepaid commitments for a fixed term and apply to GPU compute only, while storage continues at standard rates. RunPod also requires enough account credit for the selected configuration before an on-demand Pod can be deployed.
Capacity tiers
RunPod exposes several capacity paths. Pods are the main self-serve instance product, with Community Cloud and Secure Cloud shown as separate pricing columns on the public pricing page. The homepage describes Serverless for production inference, Pods for development and agent hosting, and Instant Clusters for training runs. Secure Cloud is described as network-isolated infrastructure for workloads with stricter compliance needs, while Community Cloud is the lower-friction marketplace-style tier surfaced in pricing.
GPU lineup
RunPod publishes a broad GPU type table in its documentation. Current listed families include NVIDIA Blackwell GPUs such as B200 and B300, Hopper GPUs such as H100 and H200, Ampere GPUs such as A100, A40 and A30, Ada and RTX workstation cards, L4 and L40 variants, older V100 cards, and AMD MI300X. The pricing page highlights high-memory datacenter GPUs alongside RTX 4090, RTX 5090 and RTX A-series options.
Storage, egress and hidden costs
RunPod says Pods have no fees for data ingress or egress. Storage is separate from GPU compute: container disk, volume disk and network volumes each have their own billing treatment, and network volumes are portable between Pods. The docs warn that storage can continue accruing on stopped Pods, savings plans do not cover storage, and RunPod is not designed for long-term cloud storage. Backups to another storage location are recommended for critical data.
Reliability and support posture
RunPod publishes several reliability and compliance statements, but buyers should separate marketing claims from the contract they sign. Its homepage states an uptime commitment and points readers to the compliance page and Trust Center for current SLA and certification details. Its documentation says Secure Cloud uses T3 and T4 data centers with enterprise-grade security, reliability, redundancy and faster response times. Compliance coverage can vary by workload, region, provider and deployment model.
Free credits and referral programs
RunPod documents referral, affiliate, creator and startup programs. The referral program pays RunPod Credits as a percentage of referred Serverless and Pod spend during the documented reward window, with bonus credits after the referred account reaches the required funding threshold. The affiliate program is for qualifying high-performing referrers and pays cash through Partnerstack. The startup page lists Starter and Growth tiers, including a credit match tier and a starter-credit tier. See RunPod referrals and RunPod Startup Program.
Who should pick RunPod
Pick RunPod if you want a practical GPU platform with both self-serve instances and serverless inference in one account. It is especially relevant when you want per-second Pod billing, no RunPod egress fee, and a choice between lower-cost Community Cloud and more controlled Secure Cloud capacity. For long-running production, check savings-plan terms, stopped-Pod storage charges and region-specific compliance before committing. For sensitive or regulated work, verify the exact Trust Center documents for your deployment model.
Similar providers
Lium
GPU marketplace. Rates, rental minimums and availability come from its public node feed. The listing link lets Lium count referrals; no commission is arranged.
from $0.09/hr marketplace host
21 GPU families in common
Runcrate
GPU instances that may run on partners' machines, billed per second on most GPUs from a prepaid balance. Publishes one starting rate per GPU, with no node size, region or stock.
from $0.36/hr on-demand
15 GPU families in common
Spheron
Decentralized GPU network with fixed pricing.
from $0.48/hr on-demand
11 GPU families in common
Ranked by overlap in the GPU models both providers list today; not an endorsement and never affected by commercial relationships.
FAQ
Yes. RunPod's Pod pricing docs state that Pods are billed by the second for compute and storage.
RunPod says Pods have no data ingress or egress fees. Storage still has separate billing rules.
Secure Cloud is positioned for stricter compliance and network isolation. Community Cloud appears as a separate capacity tier in RunPod pricing.
Yes. RunPod documents referral rewards, an affiliate path, creator credits for templates and a startup program with eligibility conditions.
Profile checked 6 July 2026. Sources: www.runpod.io · www.runpod.io · docs.runpod.io · docs.runpod.io · docs.runpod.io · docs.runpod.io · www.runpod.io · docs.runpod.io · www.runpod.io
RunPod comparisons and cost checks
Compare serverless GPU pricing · RunPod alternatives by live GPU rate · RunPod vs Lambda · Storage, egress and billing matrix · GPU servers and GPU-as-a-service