RunPod · Pricing Plans
Runpod Plans Pricing
Runpod Plans Pricing is the pricing profile for RunPod on the APIs.io network — every figure transcribed verbatim from the provider’s own pricing page on 2026-10-07.
It defines 18 plans, including Pods - B300 — $ 7.89 /hr; Pods - H200 — $ 4.59 /hr; Pods - B200 — $ 6.79 /hr, and 15 more.
The page prices API or platform usage directly, priced by usage; the service is delivered as managed.
Tagged areas include Artificial Intelligence, Cloud, Compute, GPU, and Inference.
18 Plans
Prices the API
Basis: usage other
Delivered: managed
Transcribed from the provider's pricing page on 2026-10-07 — www.runpod.io/pricing.
View Source
Artificial IntelligenceCloudComputeGPUInferenceMachine LearningServerless
Compare tiers
| Plan | Price | Includes | Overage |
|---|---|---|---|
| Pods - B300 | $ 7.89 /hr per GPU hour | 288 GB HBM3e 251 GB RAM 32 vCPUs | — |
| Pods - H200 | $ 4.59 /hr per GPU hour | 141 GB VRAM 276 GB RAM 24 vCPUs | — |
| Pods - B200 | $ 6.79 /hr per GPU hour | 180 GB VRAM 283 GB RAM 28 vCPUs | — |
| Pods - H100 SXM | $ 3.49 /hr per GPU hour | 80 GB VRAM 125 GB RAM 20 vCPUs | — |
| Pods - A100 PCIe | $ 1.59 /hr per GPU hour | 80 GB VRAM 117 GB RAM 8 vCPUs | — |
| Pods - RTX A5000 | $ 0.27 /hr per GPU hour | 24 GB VRAM 25 GB RAM 9 vCPUs | — |
| Serverless - 80 GB H100 | $ 4.79 /hr per worker hour | — | — |
| Serverless - 16 GB A4000/A4500/RTX 4000/RTX 2000 | $ 0.58 /hr per worker hour | — | — |
| Clusters - H200 SXM | $ 4.31 /hr per GPU hour | — | — |
| Clusters - A100 SXM | $ 1.79 /hr per GPU hour | — | — |
| Clusters - L40S / H100 SXM / B200 | Contact sales | — | — |
| Reserved Clusters | Contact sales | — | — |
| Storage - Container Disk | $0.10/GB/mo per GB | — | — |
| Storage - Network Storage (Standard) | Under 1TB - $0.07/GB/mo per GB | — | Over 1TB - $0.05/GB/mo |
| Storage - Network Storage (High-Performance) | $0.14/GB/mo per GB | — | — |
| Public Endpoint - FLUX.1 [dev] | $0.02 per megapixel per megapixel | — | — |
| Public Endpoint - Qwen3 32B AWQ | $10.00 per 1m tokens per 1m tokens | — | — |
| Public Endpoint - Nano Banana Pro Edit | $0.14 per request per request | — | — |
Compare with the market: Artificial Intelligence pricing · Developer Tools & DevOps pricing
Plans
Pods - B300
per-use
$ 7.89 /hr per GPU hour
Includes: 288 GB HBM3e 251 GB RAM 32 vCPUs
Pods - H200
per-use
$ 4.59 /hr per GPU hour
Includes: 141 GB VRAM 276 GB RAM 24 vCPUs
Pods - B200
per-use
$ 6.79 /hr per GPU hour
Includes: 180 GB VRAM 283 GB RAM 28 vCPUs
Pods - H100 SXM
per-use
$ 3.49 /hr per GPU hour
Includes: 80 GB VRAM 125 GB RAM 20 vCPUs
Pods - A100 PCIe
per-use
$ 1.59 /hr per GPU hour
Includes: 80 GB VRAM 117 GB RAM 8 vCPUs
Pods - RTX A5000
per-use
$ 0.27 /hr per GPU hour
Includes: 24 GB VRAM 25 GB RAM 9 vCPUs
Serverless - 80 GB H100
per-use
$ 4.79 /hr per worker hour
Serverless - 16 GB A4000/A4500/RTX 4000/RTX 2000
per-use
$ 0.58 /hr per worker hour
Clusters - H200 SXM
per-use
$ 4.31 /hr per GPU hour
Clusters - A100 SXM
per-use
$ 1.79 /hr per GPU hour
Clusters - L40S / H100 SXM / B200
none
Contact sales
Reserved Clusters
none
Contact sales
Storage - Container Disk
month
$0.10/GB/mo per GB
Storage - Network Storage (Standard)
month
Under 1TB - $0.07/GB/mo per GB
Overage: Over 1TB - $0.05/GB/mo
Storage - Network Storage (High-Performance)
month
$0.14/GB/mo per GB
Public Endpoint - FLUX.1 [dev]
per-use
$0.02 per megapixel per megapixel
Public Endpoint - Qwen3 32B AWQ
per-use
$10.00 per 1m tokens per 1m tokens
Public Endpoint - Nano Banana Pro Edit
per-use
$0.14 per request per request
Sources
Work with this as data
Every plan here is available over the APIs.io API and to AI agents over MCP.