10x more capacity for Laguna S 2.1 on AI Gateway

Poolside Laguna S 2.1 now has 10x more capacity on Vercel AI Gateway. The increase covers both the paid model id poolside/laguna-s-2.1 and the free model id poolside/laguna-s-2.1-free, so callers can send far more requests through the gateway than before.

Capacity here is the practical limit on how much traffic AI Gateway will accept for those model ids. Both poolside/laguna-s-2.1 and poolside/laguna-s-2.1-free receive the same 10x lift. Integration stays a model-string swap: set the model to poolside/laguna-s-2.1 for the paid path or poolside/laguna-s-2.1-free for the free path.

That matters for engineers running high-volume agentic coding and long-running tasks. Those workloads issue many sequential or parallel model calls; a 10x capacity increase on both tiers reduces the chance that request volume alone is what stops a job mid-run on AI Gateway.

Poolside supplies Laguna S 2.1; Vercel surfaces it on AI Gateway under those two model ids. Keeping free and paid on the same 10x increase means teams can load-test or prototype on poolside/laguna-s-2.1-free and move the same traffic pattern to poolside/laguna-s-2.1 without reworking capacity assumptions at the gateway layer.

If you already route through AI Gateway, point high-throughput agent or coding jobs at poolside/laguna-s-2.1-free or poolside/laguna-s-2.1 and re-check request volume against the new limit. Watch whether free-tier throughput holds under sustained agent loops, and whether paid poolside/laguna-s-2.1 remains the right default once request volume is no longer the main constraint.