LLMpoolside

Poolside: Laguna S 2.1

Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...

Anyone in the Project can @-mention Poolside: Laguna S 2.1 with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Laguna S 2.1 is Poolside's specialized code model with a massive 1M-token context window and aggressive pricing at $0.09/$0.18 per Mtok. It's built for ingesting entire codebases or multi-file refactors where you need the model to hold sprawling context without hallucinating references. The trade-off: no public benchmarks yet, so you're evaluating on your own tasks. Reach for this when you need cheap, long-context code work and can afford to validate outputs yourself.

Best for

Whole-codebase analysis and refactoring
Multi-file code generation tasks
Cost-sensitive development workflows
Long-context code review automation
Repository-wide documentation generation

Strengths

The 1M-token window lets you drop entire repositories into a single prompt without chunking or retrieval hacks. At $0.09 input, it's cheaper than most general-purpose models for code-heavy workloads. Poolside's focus on code means the architecture is tuned for syntax, not prose, so it should handle language-hopping and API patterns more naturally than a general LLM repurposed for coding.

Trade-offs

No public benchmark data means you can't compare it to GPT-4o, Claude Sonnet, or Gemini on HumanEval or MBPP before committing. Poolside is a newer vendor, so ecosystem tooling and community knowledge are thin. If you need vision (screenshots of UIs) or non-code reasoning, you'll need a second model. The output price doubles the input cost, so verbose generation runs can add up quickly.

Specifications

Provider: poolside
Category: llm
Context length: 1,048,576 tokens
Max output: 131,072 tokens
Modalities: text
License: proprietary
Released: 2026-07-21

Pricing

Input: $0.09/Mtok
Output: $0.18/Mtok
Model ID: poolside/laguna-s-2.1

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$2.06

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Refactor Across Files

I'm renaming `processOrder` to `fulfillOrder` in this repository. Update the function definition in `orders.py` and all call sites in the files I've provided. Preserve existing logic and comments.

Open in a Project →

Generate API Client

Here's the complete OpenAPI 3.0 spec for our internal API. Generate a Python client with typed request/response models, error handling, and docstrings for each endpoint.

Open in a Project →

Explain Legacy Codebase

I've pasted the entire `services/` directory. Write a 300-word summary of the architecture: what each service does, how they communicate, and where the main data models live.

Open in a Project →

Migrate Deprecated APIs

We're migrating from `requests` to `httpx`. Find every `requests.get()` and `requests.post()` call in these files and rewrite them as `httpx` equivalents, preserving timeouts and headers.

Open in a Project →

Write Integration Tests

Based on the `auth/`, `billing/`, and `notifications/` modules I've provided, write pytest integration tests that cover the full user signup flow, including email verification and trial activation.

Open in a Project →

Compare with

Compare Poolside: Laguna S 2.1 with…

More language models

See all language models →