Laguna S 2.1 (Reasoning)
by Poolside
Laguna S 2.1 (Reasoning) is a reasoning model from Poolside, released on July 21, 2026. It has a 1M-token context window. API pricing is $0.1 per 1M input tokens and $0.2 per 1M output tokens. It ranks #46 of 220 models by Intelligence Score with a score of 39.8.
Laguna S 2.1 is Poolside's most capable Laguna 2.1 model: an open-weight Mixture-of-Experts coding model with 118B total parameters and 8B activated per token (256 routed experts + 1 shared; 48 layers). It targets long-horizon and agentic coding with interleaved thinking, a 1,048,576-token context window in thinking and no-thinking modes, and text-to-text only modalities. Available as open weights on Hugging Face and via Poolside's API, OpenRouter, and other hosts (poolside/laguna-s-2.1).
Key specs
| Provider | Poolside |
|---|---|
| Release date | 2026-07-21 |
| License | open weights |
| Context window | 1M tokens |
| Input price | $0.1 / 1M tokens |
| Output price | $0.2 / 1M tokens |
| Intelligence Score | 39.8 |
| Coding index | 29.3 |
Quick answers
What is the context window of Laguna S 2.1 (Reasoning)?
Laguna S 2.1 (Reasoning) has a context window of 1M tokens.
How much does Laguna S 2.1 (Reasoning) cost?
Laguna S 2.1 (Reasoning) costs $0.1 per 1M input tokens and $0.2 per 1M output tokens through the API.
Is Laguna S 2.1 (Reasoning) open source?
Yes. Laguna S 2.1 (Reasoning) is an open model released under the open weights license.
When was Laguna S 2.1 (Reasoning) released?
Poolside released Laguna S 2.1 (Reasoning) on July 21, 2026.
How does Laguna S 2.1 (Reasoning) compare to Claude Opus 5.5 (Reasoning)?
Laguna S 2.1 (Reasoning) scores 39.8 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.1 vs $4 per 1M tokens.
Compare on the AI leaderboard · All AI models
More models from Poolside
- Laguna XS 2.1 (Reasoning) — Poolside