Serverless Inference
Per-second billed endpoints that scale to zero, where cold-start latency matters more than raw hourly rate.
0 GPU instances · Updated Aug 22, 2026
No items in this list yet
Related classes
Frequently asked questions
- How are serverless inference ranked?
- Each GPU instance is scored on weighted, normalized specs (pricing, capability, and benchmark data), then adjusted for data confidence and freshness. Sources are listed on every GPU instance page.
- How fresh is this data?
- Data is verified against named sources and flagged when older than 2 days. The last verification date is shown on each page.