GPU cloud

Lepton AI

/lepton-ai · Cupertino, USA · est. 2023

Data: mediumVisit provider ↗

Key facts

  • Lepton AI is a gpu cloud headquartered in Cupertino, USA, founded 2023.
  • Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
  • Blended reference price is $0.50 per 1M tokens (in $0.50 / out $0.50).
  • Reference latency 330 ms TTFT at 125 tok/s throughput, with 99.4% reference uptime.
  • Editorial reputation index 78/100 from 145 weighted signals; 90-day trend stable.

Specification

Category
GPU cloud
Headquarters
Cupertino, USA
Founded
2023
Model access
Open weights
Flagship / served
Fast open-model endpoints
Reference open model
Llama 3.3 70B
OpenAI-compatible API
Yes
Blended $/1M
$0.50 seed

Strengths & trade-offs

Strength

Developer-friendly platform with tuned serving.

Trade-off

Smaller brand footprint post-acquisition.


Profile reviewed 2026-07-10. Confidence for this listing:medium — Figure based on public sources but not re-confirmed on the exact review date; may drift.Not affiliated with Lepton AI. ← Back to directory