Laguna XS.2
Proprietary LLM with 262k-token context for long-form text tasks.
PoolsideLanguage ModelsClosed
Model page Updated 2026-06-18
About Laguna XS.2
Laguna XS.2 was built as a text-only LLM by Poolside. Its design centers on a 262144-token context window that supports extended input sequences. The model remains fully proprietary with no public parameter count.
This architecture excels at preserving coherence across lengthy documents and multi-turn conversations. It handles complex textual relationships without requiring external retrieval steps. Users benefit from its ability to track details over very large contexts.
Teams typically deploy Laguna XS.2 for document analysis, code review sessions, and narrative generation. It fits enterprise workflows that demand reliable performance on long inputs. Integration occurs through Poolside's managed API endpoints.
Capabilities
Long-context reasoning
Extended document analysis
Coherent text generation
Multi-turn conversation handling
Instruction following
How Laguna XS.2 compares
Laguna XS.2 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Laguna XS.2 ranks #24 of 147
$0.15
Trinity Mini$0.15
$0.15
Rnj 1 Instruct$0.18
$0.18
$0.19
$0.20
Laguna XS.2$0.20
$0.20
$0.20
Reka Flash 3$0.24
$0.26
$0.27
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Legal Contract Analysis
Laguna XS.2 processes full-length contracts and regulatory documents within its 262144-token context for detailed clause extraction and risk identification.
Long-Form Content Creation
The model maintains coherent text generation across extended multi-chapter outputs while following precise stylistic and structural instructions.
Iterative Research Workflows
It supports multi-turn conversation handling and long-context reasoning to refine hypotheses over successive interactions with large source materials.
Strengths & limitations
Strengths
- +Very large context window
- +Text-only specialization
- +Strong handling of long inputs
- +Focused language modeling
Limitations
- –No vision or multimodal support
- –Text modality only
- –General-purpose rather than domain-specific
Cost calculator
Estimate what Laguna XS.2 would cost for your usage.
$0.00020
per request
$2
estimated / month
Based on Laguna XS.2's $0.10/1M input · $0.20/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
JavaScript · openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "poolside/laguna-xs.2",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: poolside/laguna-xs.2
Editor's verdict
Our take on Laguna XS.2
Laguna XS.2 is Poolside's proprietary language models with a 262K-token context window.
At $0.20 per 1M output tokens, it is very cost-efficient for its class.
It is available through Poolside's API and aggregators like OpenRouter.
Best suited to very large context window and text-only specialization.
Did you find this helpful?
Frequently asked questions
Laguna XS.2 provides a context window of 262144 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Laguna models
Sibling versions in the Laguna family from Poolside.
Similar models
Other language models worth comparing.