Laguna S 2.1

Laguna S 2.1 Thinking

Poolside's open-weights agentic coding model with 118B total parameters and 8B activated per token, with thinking enabled for harder long-horizon software engineering, tool use, and extended reasoning. It supports a context window of up to 1M tokens.

Laguna M.1

Poolside's most capable agentic coding model. A 225B total parameter Mixture-of-Experts model with 23B activated parameters, trained from scratch on 30T tokens for software engineering workflows. Paid model; a free preview route may be available temporarily. During Poolside's preview, prompts and completions are logged by Poolside and may be used to improve services, including model training unless opted out; avoid sensitive data if that is a concern.

Ornith 1.5 35B

Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.

Ornith 1.5 35B Thinking

Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.

Qwen3.5 0.8B

Qwen3.5 0.8B is a lightweight open-weight multimodal model from Alibaba for fast reasoning, visual understanding, tool use, and JSON output.

Qwen3.5 2B

Qwen3.5 2B is a small open-weight multimodal model from Alibaba for efficient reasoning, coding, visual understanding, tool use, and JSON output.