Poolside
AI lab building foundation models for software development (Laguna family). Retains API data and trains on it by default. Requesty routes to 2 Poolside models with context windows up to 33K tokens. One API key, OpenAI-compatible SDK, no markup.
All Poolside models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
laguna-m.1 | 33K | — | Free | Free | 🧠 | — |
laguna-xs.2 | 33K | — | Free | Free | 🧠 | — |
About Poolside on Requesty
How many Poolside models are available through Requesty?
Requesty routes to 2 Poolside models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Poolside model?
Poolside has free tiers available — look for the models marked "Free" in the pricing column.
Does Requesty add markup on Poolside pricing?
No. Requesty passes through exactly what Poolside charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Poolside models?
Poolside's default terms may include data use for training. Check their privacy policy and Requesty's enterprise options for opt-out controls.
Where are Poolside models hosted?
Poolside models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Poolside rows in the models explorer.