Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Specs
poolside/laguna-s-2.1How to use Laguna S 2.1 in your app
The quickest way is through an API gateway such as OpenRouter, which uses the same format as the OpenAI API. Create a key, then send a request with the model ID poolside/laguna-s-2.1:
Prefer no code? Many tools in our AI tools directory run on models like this one.
More models from Poolside
Questions about Laguna S 2.1
What is Laguna S 2.1?
Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
How big is the context window of Laguna S 2.1?
Laguna S 2.1 can read up to 1,048,576 tokens in one request, roughly 786,432 words.
How much does Laguna S 2.1 cost?
Through OpenRouter, Laguna S 2.1 costs about $0.09 / 1M tokens for input and $0.18 / 1M tokens for output. Prices change, so check before large jobs.
Is Laguna S 2.1 open source?
Laguna S 2.1 has open weights, so you can download and run it yourself, subject to its licence.
What can Laguna S 2.1 take as input?
Laguna S 2.1 accepts text and produces text.
Latest AI models
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
Specs and prices come from OpenRouter and the provider, and are refreshed daily. Last checked 21 Jul 2026.