Poolside's first-party API — direct route to the Laguna agentic coding models.
Poolside is a San Francisco-based foundation AI lab founded by former GitHub CTO Jason Warner and Eiso Kant, training models for software engineering from scratch with reinforcement learning from code execution feedback. Its open-weight Laguna family of mixture-of-experts models is built for agentic coding, pairing native reasoning with long-horizon tool use. This route is Poolside's own inference API, serving Laguna S 2.1 and the compact Laguna XS 2.1 on global infrastructure with no fixed residency guarantee. The natural pick when you want purpose-built coding agent models straight from the lab that trains them.
Every model we route through Poolside. Compare residency, zero data retention, training posture and price at a glance, with full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| Multi | No | 262K | — | — | ||
| Multi | No | 262K | — | — |
Poolside hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.
