infrastructure channel · GPU cloud

RunPod serverless and GPU pricing

A GPU cloud with pods, serverless workers, endpoint controls, and community templates for custom AI workloads.

Where this provider fits

A GPU cloud with pods, serverless workers, endpoint controls, and community templates for custom AI workloads.

Reasons to evaluate it

  • Serverless and persistent GPU options
  • Control over model packaging
  • Broad GPU selection

Questions to resolve before purchase

  • Total cost depends on startup, idle, and execution time
  • It is not directly comparable with per-output hosted APIs

Recorded price evidence

RunPod recorded offers · checked-source scope
ProviderConfigurationRecorded priceEvidence
RunPodinfrastructurecustom-serverless-worker · A100 serverless · not-applicable · no audio · source unit: hour$0.0008 / compute secondfreshProvider sourceChecked Aug 21, 2026

Checked evidence, not a ranking: fresh rows were checked against the linked first-party source on the shown date. APIDir does not name a cheapest provider unless exact configurations and units match. Recheck before purchasing.

Questions developers ask

What does APIDir verify about RunPod?

APIDir separates the service channel from the underlying model owner, records exact offer configuration, links the source, and exposes the check date.

Does an entry mean APIDir recommends this provider?

No. A directory record is a research starting point. Review current sources, legal terms, limits, and a workload-specific test.

Why can a displayed observation be stale?

Historical observations remain visible for audit, but stale records do not support current cheapest or savings claims.

APIDir Delta

Get checked price changes, not noise.

One concise issue with source links, comparable configurations, and corrections.