Laguna S 2.1 is now available on AI Gateway
By Steven Van ·
Poolside's open-weight model ships free with a 256K context window or paid with 1M, and runs in thinking and no-thinking modes.
Vercel's AI Gateway now supports Laguna S 2.1, an open-weight Mixture-of-Experts model from Poolside built for agentic coding and long-running tasks such as writing and debugging code, running tests, building browser-based tooling, and working on MLOps pipelines and AI research.
The model comes in two versions: a free poolside/laguna-s-2.1-free with a 256K context window, and a paid poolside/laguna-s-2.1 with a 1M context window. Both run in thinking and no-thinking modes. In thinking mode, Laguna S 2.1 reports 70.2% on Terminal-Bench 2.1, 78.5% on SWE-bench Multilingual, and 59.4% on SWE-Bench Pro.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →