Local LLMs
Poolside Releases Open-Weight Laguna S 2.1 Coding Agent Model
Poolside launched Laguna S 2.1, an open-weight model specialized for coding agents. Available for free local hosting via vLLM and Ollama, hosted API prices start at $0.09 per 1M input tokens and $0.18 per 1M output tokens.
August 13, 2026 3 min read
Curated by Oleksandr Kuzmenko, AI Product EngineerUpdated August 13, 2026Sources cited on every story
AI-assisted · editor-reviewedHow we use AI
Impact: Medium
Why it matters
You can deploy a specialized coding model locally for zero per-token cost or integrate a cloud API priced cheaper than 78% of tracked open-weight providers.
TL;DR
- 01Laguna S 2.1 offers open weights for zero token-cost local execution.
- 02Hosted API pricing is set at $0.09/1M input and $0.18/1M output tokens.
- 03Supported across Ollama, vLLM, and llama.cpp runtimes.
Key facts
- Input Token Price
- $0.09 / 1M tokens
- Output Token Price
- $0.18 / 1M tokens
- Effective Price (3:1 ratio)
- $0.11 / 1M tokens
- License / Hosting
- Open-weight / Self-hostable
Self-Hosting & Deployment Options
Laguna S 2.1 features fully open weights available for download. It runs out of the box on standard inference stacks:
Ollamafor local desktop developmentvLLMfor high-throughput batch servingllama.cppfor GGUF quantized CPU/GPU deployment
Pricing Structure
For developers preferring managed endpoints over self-hosting:
- Input Cost: $0.09 per 1M tokens
- Output Cost: $0.18 per 1M tokens
- Effective Cost (3:1 ratio): $0.11 per 1M tokens
Try it in 2 minutes
ollama run poolside/laguna-s-2.1bash
✓ When to use
- Use when setting up self-hosted coding agents to eliminate per-token API API costs.
- Deploy in local Cursor or VS Code completions backends via Ollama.
✕ When NOT to use
- Do not use if your workflow requires multimodal vision inputs.
- Avoid for non-technical general conversational text writing.
What to do today
- Run `ollama run poolside/laguna-s-2.1` to benchmark the model locally on your codebase.
- Compare cost vs accuracy against existing OpenAI/Anthropic coding tool proxies.
#Laguna S 2.1#Ollama#vLLM#llama.cpp
Sources