# RunPod pricing

Extracted automatically from [https://runpod.io/pricing](https://runpod.io/pricing), captured 2026-10-17 (extracted 2026-10-18). Only prices whose exact wording was found on the page under the right plan are listed; always confirm on the vendor’s site.

- Pricing model: Usage-based
- Starts at: not listed
- Badges: Usage-based, Contact sales
- Confidence: High: every check passed
- Company profile: [RunPod](https://rewindex.com/company/runpod.md) · Pricing page changes: [history](https://rewindex.com/company/runpod/changes.md?kind=pricing)

## Plans

| Plan | Product | Price | Source quote |
| --- | --- | --- | --- |
| Clusters |  | $6.35 per hour (H200 SXM) | “H200 SXM $ 6.35 /hr” |
|  |  | $2.15 per hour (A100 SXM) | “A100 SXM $ 2.15 /hr” |
| Pods |  | $8.99 per hour (B300) | “B300 288 GB HBM3e 251 GB RAM 32 vCPUs $ 8.99 /hr” |
|  |  | $5.29 per hour (H200) | “H200 141 GB VRAM 276 GB RAM 24 vCPUs $ 5.29 /hr” |
|  |  | $7.99 per hour (B200) | “B200 180 GB VRAM 283 GB RAM 28 vCPUs $ 7.99 /hr” |
|  |  | $2.49 per hour (RTX Pro 6000) | “RTX Pro 6000 96 GB VRAM 188 GB RAM 16 vCPUs $ 2.49 /hr” |
|  |  | $3.19 per hour (H100 NVL) | “H100 NVL 94 GB VRAM 94 GB RAM 16 vCPUs $ 3.19 /hr” |
|  |  | $2.89 per hour (H100 PCIe) | “H100 PCIe 80 GB VRAM 188 GB RAM 16 vCPUs $ 2.89 /hr” |
|  |  | $3.99 per hour (H100 SXM) | “H100 SXM 80 GB VRAM 125 GB RAM 20 vCPUs $ 3.99 /hr” |
|  |  | $1.79 per hour (A100 PCIe) | “A100 PCIe 80 GB VRAM 117 GB RAM 8 vCPUs $ 1.79 /hr” |
|  |  | $1.79 per hour (A100 SXM) | “A100 SXM 80 GB VRAM 125 GB RAM 16 vCPUs $ 1.79 /hr” |
|  |  | $1.29 per hour (Pro 6000 MIG 48GB) | “Pro 6000 MIG 48GB 48 GB VRAM 62 GB RAM 8 vCPUs $ 1.29 /hr” |
| Public Endpoints |  | $0.05 per 1,000 1000 characters (Pruna / Whisper V3 Large) | “Pruna / Whisper V3 Large $0.05 per 1000 characters” |
|  |  | $0 per 1,000 1000 characters. (resembleai / Chatterbox Turbo) | “resembleai / Chatterbox Turbo $0.00 per 1000 characters.” |
|  |  | $0.05 per 1,000 1000 characters (minimax / Minimax Speech 02 HD) | “minimax / Minimax Speech 02 HD $0.05 per 1000 characters” |
|  |  | $0.027 per request (bytedance / Seedream 4.0 Edit) | “bytedance / Seedream 4.0 Edit $0.0270 per request” |
|  |  | $0.027 per request (bytedance / Seedream 4.0 T2I) | “bytedance / Seedream 4.0 T2I $0.0270 per request” |
|  |  | $0 per 1,000,000 1M tokens (deep-cogito / Deep Cogito v2 Llama 70B) | “deep-cogito / Deep Cogito v2 Llama 70B $0.00001 per 1m tokens” |
|  |  | $10 per 1,000,000 1M tokens (qwen / Qwen3 32B AWQ) | “qwen / Qwen3 32B AWQ $10.00 per 1m tokens” |
|  |  | $1 per 1,000,000 1M tokens (ibm / IBM Granite 4.0 H Small) | “ibm / IBM Granite 4.0 H Small $1.00 per 1m tokens” |
|  |  | $0.12 per request (Bytedance / Seedance 1.0 pro — 5s, 480p) | “Bytedance / Seedance 1.0 pro 5s: $0.12(480p) per request” |
|  |  | $0.3 per request (Alibaba / Wan 2.2 I2V 720p — 5s) | “Alibaba / Wan 2.2 I2V 720p 5s: $0.30 per request” |
| Serverless |  | $10.65 per hour (B300) | “280 GB B300 Maximum throughput for big models. $ 10.65 /hr” |
|  |  | $8.64 per hour (B200) | “180 GB B200 Maximum throughput for big models. $ 8.64 /hr” |
|  |  | $5.93 per hour (H200) | “141 GB H200 Extreme throughput for big models. $ 5.93 /hr” |
|  |  | $3.49 per hour (RTX 6000 Pro) | “96 GB RTX 6000 Pro PRO High throughput for large model inference workloads. $ 3.49 /hr” |
|  |  | $4.79 per hour (H100) | “80 GB H100 PRO Extreme throughput for big models. $ 4.79 /hr” |
|  |  | $2.72 per hour (A100) | “80 GB A100 High throughput GPU, yet still very cost-effective. $ 2.72 /hr” |
|  |  | $1.75 per hour (L40, L40S, 6000 Ada, MIG 48GB) | “48 GB L40, L40S, 6000 Ada, MIG 48GB PRO Extreme inference throughput on LLMs like Llama 3 7B. $ 1.75 /hr” |
|  |  | $1.22 per hour (A6000, A40) | “48 GB A6000, A40 A cost-effective option for running big models. $ 1.22 /hr” |
|  |  | $1.58 per hour (5090) | “32 GB 5090 PRO Extreme throughput for small-to-medium models. $ 1.58 /hr” |
|  |  | $1.15 per hour (RTX PRO 4500 Blackwell) | “32 GB RTX PRO 4500 Blackwell Cost-effective Blackwell inference for 32GB workloads. $ 1.15 /hr” |
| Reserved Clusters |  | Contact sales |  |

## Add-ons

| Add-on | Price | Source quote |
| --- | --- | --- |
| Container Disk | $0.1 per gb month / month | “Storage Type Container Disk $0.10/GB/mo” |
| Volume Disk — Running | $0.1 per gb month / month | “Volume Disk Running - $0.10/GB/mo” |
| Volume Disk — Idle | $0.2 per gb month / month | “Idle - $0.20/GB/mo Volume Disk” |
| Network Storage (Standard) — Under 1TB | $0.07 per gb month / month | “Network Storage (Standard) Under 1TB - $0.07/GB/mo” |
| Network Storage (Standard) — Over 1TB | $0.05 per gb month / month | “Over 1TB - $0.05/GB/mo Network Storage (Standard)” |
| Network Storage (High-Performance) | $0.14 per gb month / month | “Network Storage (High-Performance) $0.14/GB/mo Network Storage (High-Performance)” |


---
Canonical: https://rewindex.com/company/runpod/pricing · Markdown: https://rewindex.com/company/runpod/pricing.md · JSON: https://rewindex.com/api/v1/companies/runpod/pricing · Generated 2026-10-18T06:01:34.644Z