Poolside: Laguna S 2.1 (free)
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 (free) with the team's shared context - pooled credits, one chat, one memory.
Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.
Verdict
Best for
- Zero-cost code prototyping and exploration
- Multi-file codebase context experiments
- Documentation generation for side projects
- Learning prompt engineering without spend
- Testing code workflows before paid deployment
Strengths
The 262K context window handles entire repositories or long documentation sets in a single request, useful for cross-file refactoring or generating README files from source. Zero pricing removes friction for high-volume experimentation — you can iterate on prompts, test edge cases, and explore code generation patterns without watching a meter. Free tier access lowers the barrier for teams evaluating whether code-focused models fit their workflow before committing budget to commercial alternatives.
Trade-offs
No public benchmarks means you're flying blind on code correctness, reasoning depth, and language coverage compared to models like Claude Sonnet or GPT-4. Poolside hasn't published HumanEval, MBPP, or MultiPL-E scores, so you can't gauge whether it matches free alternatives like DeepSeek Coder or Qwen2.5-Coder. Free-tier models often throttle throughput or deprioritize requests under load, which may introduce latency spikes. Proprietary license blocks self-hosting or fine-tuning if you need model customization down the road.
Specifications
- Provider
- poolside
- Category
- llm
- Context length
- 262,144 tokens
- Max output
- 32,768 tokens
- Modalities
- text
- License
- proprietary
- Released
- 2026-07-21
Pricing
- Input
- $0.00/Mtok
- Output
- $0.00/Mtok
- Model ID
poolside/laguna-s-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
5 seats · 80 msgs/day
Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.
Providers
Performance
Benchmarks
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
Starter prompts
Multi-File Refactor Plan
Review these five Python modules and propose a refactoring plan to eliminate circular imports and consolidate duplicate logic. List specific functions to move and new module boundaries.Open in a Project →
Generate README from Source
Read the attached source files and write a README.md covering project purpose, installation steps, usage examples, and API reference. Infer details from code structure and comments.Open in a Project →
Explain Legacy Codebase
Analyze this legacy Java project and write a 300-word summary explaining its architecture, main components, and data flow. Highlight any deprecated patterns or technical debt.Open in a Project →
Cross-File Bug Hunt
These four TypeScript files contain a bug where user permissions aren't checked before database writes. Identify the missing validation and show exactly where to add the check.Open in a Project →
Prototype API Endpoint
Write a FastAPI endpoint that accepts a JSON payload with user_id and preferences, validates the schema, updates a PostgreSQL table, and returns a 200 response with the updated record.Open in a Project →
Compare with
More language models
- Poolside: Laguna XS 2.1poolside
- Poolside: Laguna XS 2.1 (free)poolside
- Qwen2.5 72B Instructqwen
- Qwen2.5 Coder 32B Instructqwen
- Qwen: Qwen2.5 7B Instructqwen
- Qwen: Qwen2.5 VL 72B Instructqwen
- Qwen: Qwen3 14Bqwen
- Qwen: Qwen3 235B A22Bqwen
- Qwen: Qwen3 235B A22B Instruct 2507qwen
- Qwen: Qwen3 235B A22B Thinking 2507qwen
- Qwen: Qwen3 30B A3Bqwen
- Qwen: Qwen3 30B A3B Instruct 2507qwen