Skip to content
All systems operational0 AI providers monitored, polled every 2 minutes
Live status

Laguna S 2.1

Mid-tier

by poolside

Laguna S 2.1 is poolside's first major public model release, shipped July 21, 2026 with open weights on Hugging Face the same day under the OpenMDW-1.1 license. It is a 118 billion parameter mixture-of-experts with roughly 8 billion active per token, a 1,048,576 token context window, and up to 131,072 output tokens. Hosted pricing on OpenRouter is $0.10 per million input tokens and $0.20 per million output, with cache reads at $0.01, which puts it among the cheapest frontier-adjacent coding options available. poolside reports 70.2 percent on Terminal-Bench 2.1 in thinking mode, 78.5 percent on SWE-Bench Multilingual, and 40.4 percent on DeepSWE, claiming it leads open models of disclosed size and outranks systems roughly ten times larger. The part worth noting is the eval hygiene: poolside disclosed that Terminal-Bench results come from its own harness and published the full unedited trajectory of every benchmark trial, which is a materially higher standard than the vendor-claimed tables that shipped with most of the same week's launches. At 8 billion active parameters the model is genuinely runnable on modest hardware, which separates it from the 1T-plus open-weight releases where downloadable does not mean deployable.

Input Price

$0.10

per 1M tokens

Output Price

$0.20

per 1M tokens

Context Window

1.0M

tokens

Released

2026-07

Open source

Capabilities

textcodetool-usereasoning

Key Strengths

  • $0.10/$0.20 per 1M tokens hosted, among the cheapest coding models
  • Open weights on Hugging Face day one under OpenMDW-1.1
  • 118B total parameters with only ~8B active per token
  • 1M token context, 131K max output
  • 70.2 percent on Terminal-Bench 2.1 in thinking mode
  • Full benchmark trajectories published, harness disclosed

Best For

  • Cost-sensitive agentic coding at volume
  • Self-hosted coding assistants on modest hardware
  • Terminal and shell-driven automation
  • Worker models under a more expensive planner

Pricing Details

Input tokens

$0.10

per 1M tokens

Output tokens

$0.20

per 1M tokens

Estimated cost per 1K requests

$0.20

~1K input + ~500 output tokens avg

Prices are subject to change. Check the official documentation for current pricing. See the cost calculator for detailed estimates.

Open Source Model

Laguna S 2.1 is free to download and self-host under the OpenMDW-1.1. Hosted API pricing varies by provider (e.g., Together, Fireworks, Groq). See our open source LLM guide for deployment options.

Related Models

View DocumentationCompare ModelsCost CalculatorFull Pricing Guide