LLMpoolside

Poolside: Laguna XS 2.1 (free)

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...

Anyone in the Space can @-mention Poolside: Laguna XS 2.1 (free) with the team's shared context - pooled credits, one chat, one memory.

All models

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

Verdict

Laguna XS 2.1 is Poolside's free-tier code model with a 262K context window, making it useful for reading large codebases without cost. Performance benchmarks aren't public, so you're flying blind on quality versus alternatives like Codestral or DeepSeek Coder. The zero-cost pricing makes it worth testing for non-critical code tasks, but expect to graduate to a paid model once you need reliability or stronger reasoning. Best as a sandbox model or cost-cap fallback.

Best for

  • Exploring large codebases without API costs
  • Prototyping code generation workflows
  • Teaching or learning environments
  • Cost-capped automation experiments

Strengths

The 262K context window handles entire repositories in a single prompt, and zero pricing removes friction for experimentation. Poolside built this specifically for code, so it understands syntax and structure better than general-purpose models. The free tier has no usage caps listed, making it viable for high-volume prototyping or educational use cases where budget is the primary constraint.

Trade-offs

No public benchmarks means you can't compare it to Codestral, Claude, or DeepSeek Coder on HumanEval or MBPP. Proprietary license limits transparency into training data or model architecture. Free models often deprioritize latency and uptime, so expect slower responses or occasional availability issues. Code quality likely trails paid alternatives—fine for drafts, risky for production.

Specifications

Provider
poolside
Category
llm
Context length
262,144 tokens
Max output
32,768 tokens
Modalities
text
License
proprietary
Released
2026-07-02

Pricing

Input
$0.00/Mtok
Output
$0.00/Mtok
Model ID
poolside/laguna-xs-2.1:free

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

Estimated monthly spend
Freeno token cost
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

ProviderContextInputOutputP50 latencyThroughput30d uptime
poolside262k$0.00/Mtok$0.00/Mtok

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 Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Explain Codebase Architecture

Here's the contents of my project's src/ directory. Explain the overall architecture, how the modules connect, and where the main entry points are.
Open in a Space →

Generate Boilerplate Code

Generate a FastAPI router with CRUD endpoints for a 'users' resource. Include Pydantic models, path operations, and basic error handling.
Open in a Space →

Refactor Legacy Function

Here's a 200-line function that does too much. Refactor it into smaller, testable functions with clear responsibilities.
Open in a Space →

Debug Stack Trace

I'm getting this stack trace when running my Node.js app. Explain what's failing and suggest a fix.
Open in a Space →

Write Unit Tests

Here's a function that parses CSV files. Write Jest unit tests covering normal cases, edge cases, and error conditions.
Open in a Space →
Data last verified 2 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.