Laguna XS 2.1 is the compact member of Poolside's open-weight Laguna family, a mixture-of-experts design with 33B total and 3B active parameters released in July 2026. Like its larger sibling Laguna S, it is trained from scratch for software engineering and post-trained with reinforcement learning from code execution feedback, with native reasoning togglable per request. The small active-parameter count keeps latency low, and the model is deliberately sized to run locally on a single GPU, part of Poolside's design brief for it. It suits high-volume coding agent workloads, fast edit-and-verify loops, and cost-sensitive automation where a frontier-scale model is more than the task needs.
Poolside Laguna XS 2.1 runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Multi | Not by default | No | — | — |
Each route hosting Poolside Laguna XS 2.1 has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring. No training on customer data. GLOBAL; wallets; deposit available.
Call Poolside Laguna XS 2.1 through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "poolside/laguna-xs-2.1",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
