Small & Fast Poolside Models

Quick answer · Updated June 2026

The small, fast Poolside model is Laguna XS.2 (free) — the efficient tier at 126 tokens/sec and Free per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work.

126 t/sSpeed

FreeInput /M

262KContext

Compact, efficient models — the small/mini/flash/haiku tier — ranked by output speed. These trade a little raw intelligence for low cost and high throughput, which is the right tradeoff for chat, classification, extraction and other high-volume work.

1P
laguna-xs.2:free
ReasoningToolsFree/M · 582ms ttft · 262K ctx
126 t/s
Speed

Frequently asked

What is the smallest, fastest Poolside model?

How many Poolside models are there?

modelgrep tracks 2 Poolside models with live benchmarks, speed, latency and per-provider pricing. 1 of them qualify for this ranking.

More Poolside rankings

Poolside: Smartest LLMs Poolside: Best LLMs for Coding Poolside: Best LLMs for Design & Frontend Poolside: Fastest LLMs Poolside: Lowest-Latency LLMs Poolside: Cheapest LLMs Poolside: Best Free LLMs Poolside: Best Reasoning LLMs Poolside: Best Vision LLMs Poolside: Best LLMs for Agents Poolside: Best Open-Source LLMs Poolside: Longest-Context LLMs

All rankings

Small & Fast LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Fastest LLMs Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs