Laguna M.1
Poolside's closed LLM with 262k-token context for long text tasks.
PoolsideLanguage ModelsClosed
Model page Updated 2026-06-18
About Laguna M.1
Laguna M.1 is built as a proprietary LLM focused on text modality. Its design centers on a 262144-token context window that accommodates very long inputs without chunking. Poolside keeps the model closed to maintain control over deployment and updates.
The primary strength is its ability to retain coherence across hundreds of thousands of tokens. This capability suits workloads where sustained context matters more than open-source flexibility. No public benchmarks or parameter sizes are provided.
Typical usage involves enterprise text processing such as analyzing lengthy documents or code repositories. It fits into secure pipelines where users require managed access rather than local weights. Integration occurs through Poolside's platform for controlled, scalable inference.
Capabilities
Long-context reasoning
Extended document analysis
Text generation and completion
Multi-turn conversation handling
Information synthesis from large inputs
How Laguna M.1 compares
Laguna M.1 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Laguna M.1 ranks #40 of 147
$0.30
$0.30
$0.32
$0.34
$0.34
$0.35
$0.40
Laguna M.1$0.40
$0.40
$0.40
$0.40
$0.40
$0.40
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Legal Contract Review
Processes contracts spanning hundreds of pages in a single pass, identifying clauses, risks, and inconsistencies through extended document analysis.
Research Paper Synthesis
Combines findings across multiple lengthy academic papers or technical reports, producing integrated summaries and cross-references using information synthesis from large inputs.
Iterative Software Architecture Planning
Maintains coherent multi-turn discussions over evolving codebases and design decisions while tracking prior context across thousands of tokens.
Strengths & limitations
Strengths
- +Very large 262k token context window
- +Focused text-only processing
- +Suitable for long-form reasoning tasks
Limitations
- –Text modality only with no vision support
- –High compute cost at maximum context lengths
- –No native multimodal capabilities
Cost calculator
Estimate what Laguna M.1 would cost for your usage.
$0.00040
per request
$4
estimated / month
Based on Laguna M.1's $0.20/1M input · $0.40/1M 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-m.1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: poolside/laguna-m.1
Editor's verdict
Our take on Laguna M.1
Laguna M.1 is Poolside's proprietary language models with a 262K-token context window.
At $0.40 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 262k token context window and focused text-only processing.
Did you find this helpful?
Frequently asked questions
Laguna M.1 supports 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.