Provider pricing
RunPod AI API pricing
RunPod has a directory profile; no complete positive input/output price pair is recorded in the public snapshot. Missing rates must not be interpreted as free access.
Best for
Cost-sensitive teams serving custom models or running large batch GPU jobs.
Strengths
- Among the cheapest H100/H200 hourly rates on the market
- Serverless vLLM endpoints for any HuggingFace model in one click
- Per-second billing with sub-200ms cold starts on warm workers
- Spot instances for batch jobs at deep discounts
Last updated: · Source: No official pricing URL recorded · Methodology
Frequently asked questions
How much does the RunPod API cost?
RunPod has a directory profile; no complete positive input/output price pair is recorded in the public snapshot. Missing rates must not be interpreted as free access.
Which RunPod model is cheapest?
A cheapest model cannot be established without a complete recorded rate pair.
Does RunPod have cached or batch prices?
No model-specific cached or batch rates are recorded. Consult the provider for eligibility and additional charges.
How often are provider prices verified?
The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-10-31; only explicit per-model dates are verification records.