Model Reference

plugsky-lite — speed without the tradeoff

plugsky-lite is a 3B-class compact model (Llama 3.2 3B family) built for speed: ~0.24s median latency, 128K context, full tool support.

plugsky-lite is Plugsky's speed king: 3B-class model at ~0.24s latency, 128K context, tool calling. Perfect for high-volume production traffic.

Key points

  • OpenAI-compatible API: change the base URL and API key to switch.
  • Flat-rate plans with unlimited fair-use — see the pricing section.
  • Private deployment options: VPC, on-prem and air-gapped.

Explore more: all articles · free tools · docs · what is Plugsky.

Get started in minutes

OpenAI-compatible API with 30+ models, free trial, and a 99.9% uptime SLA. No code changes required.

Start Free → Read the docs