Poolside models

Poolside has 4 models in the directory. The newest is Laguna S 2.1, released Jul 21, 2026.

The cheapest to run is Laguna S 2.1 at $0.10 per million input tokens.

Laguna S 2.1 has the longest context window, 1.05M tokens.

Models
4
Newest
Jul 21, 2026
From
$0.10/M input
Longest context
1.05M

All Poolside models

Filter in the directory
  • Reads text. Tool calling, reasoning. Served by 6 providers.

    by poolsideJul 21, 2026$0.10/M input tokens$0.20/M output tokens6 providers

  • Reads text. Tool calling, reasoning. Served by 4 providers.

    by poolsideJul 2, 2026$0.10/M input tokens$0.20/M output tokens4 providers

  • Reads text. Tool calling, reasoning. Served by 2 providers.

    by poolsideApr 28, 2026$0/M input tokens$0/M output tokens2 providers

  • Reads text. Reasoning.

    by poolsideApr 28, 2026$0/M input tokens$0/M output tokens

Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.

Not sure which Poolside model fits?

I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.

Book Meeting