Compare Laguna S 2.1 from Poolside and Laguna Xs 2.1 from Poolside on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Laguna S 2.1Laguna Xs 2.1laguna-s-2.1 is Poolside's coding agent model, designed for programming and developer agent workflows. It offers a massive 1,048,576-token context window, a 118B total parameter architecture with 8B active parameters, and cost-effective text processing with prompt caching.
laguna-xs-2.1 is Poolside's coding agent model, designed for coding and text generation tasks. It features a 262,144-token context window with cost-effective pricing across input, output, and prompt caching. Compared with Laguna XS.2, it represents Poolside's latest step forward in the 33B-A3B category.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
Laguna Xs 2.1: $0.2/M output tokens; Laguna S 2.1: $0.2/M. Use the cost calculator above to estimate your own workload.
Laguna S 2.1 accepts 1,048,576 and Laguna Xs 2.1 accepts 262,144 input tokens.
Laguna S 2.1 accepts text input; Laguna Xs 2.1 accepts text input.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.