Laguna S 2.1 is now available on AI Gateway
- Source
- vercel.com
- Author
- Rohan Taneja
- Date

Context
Poolside's Laguna S 2.1 arrived on Vercel's AI Gateway with two different limits. The July 21 announcement lists a free version with 256,000 tokens of context and a paid version with one million. That limit determines how much text the model can consider within a request.
The distinction matters for a model aimed at coding and extended tasks: the larger advertised context belongs to the paid option. The model also supports thinking and no-thinking modes. Those are separate choices from the access tier's context capacity.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
- mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
- SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
“Laguna S 2.1 is an open-weight Mixture-of-Experts model that supports a context window of up to 1M tokens and runs 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.”
“AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.”
Checking sign-in…
Loading comments…






