Directory › GPU & inference hosting › RunPod
RunPod
Cheap GPUs for running Ollama or vLLM for your agent.
GPU & inference hosting Price verified 2026-10-16
Visit provider ↗ Direct link, no affiliate relationship. Disclosure
| Starting price | from $0.27/hr (RTX A5000 24 GB) |
|---|---|
| Pricing model | Usage-based |
| Key specs | Per-second GPU Pods, Serverless endpoints, and Clusters. Examples listed: RTX A5000 24 GB $0.27/hr, RTX A6000 48 GB $0.59/hr, L40 48 GB $0.82/hr, RTX 5090 32 GB $1.19/hr. |
| Date checked | 2026-10-16 |
| Sources | www.runpod.io/pricing |
Agent-friendly features
- Serverless GPU endpoints
- Per-second billing
Security notes
- Security details not captured.
Security notes are what the provider states on the pages we read, or gaps we noticed. Treat vendor claims as claims, not audits.
Not verified or not checked
- Prices are a snapshot; GPU stock and community vs secure tiers not distinguished.
Tags
Similar providers
Lambda
from $0.69/GPU-hr (RTX 6000 24 GB)
Vast.ai
Live 'from' rates, e.g. RTX 5090 from $0.39/hr; H100 SXM from $1.73/hr
Spot something out of date? Send a correction with a link to the provider page. Providers can fix factual errors for free.