Poolside
Maker of the open-weight 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, from the flagship Laguna S to the compact Laguna XS that runs on a single GPU.
poolside.aiCall Poolside models through Opper with one API key. Sign up without a credit card.
Models from Poolside
| Model | Context | Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|---|---|
| 262K | Multi | No | — | — | Input price | |||
| 262K | Multi | No | — | — | Input price |
