## Poolside Models Overview

Poolside models are foundation models for software engineering. Use this page to choose a model, compare reasoning support and context windows, and find the right setup guidance for API access or deployment planning. Supported models are models that Poolside validates, ships, upgrades, patches, and helps operate in a Poolside deployment. Model availability, provider-specific variants, and model IDs can vary by access method.

## Compare Models

| Detail | Laguna S 2.1 | Laguna XS 2.1 | Laguna M.1 |
| --- | --- | --- | --- |
| Best for | Long-horizon agentic coding and extended tool-use workflows | Fast agentic coding and rapid iteration | Complex, multi-step coding tasks where agent quality matters more than raw throughput |
| Parameters | 118B total, 8B active per token | 33B total, 3B active per token | 225B total, 23B active per token |
| Context window | 1M tokens | 256K tokens | 256K tokens |
| Model type | Mixture of Experts | Mixture of Experts | Mixture of Experts |
| Modality | Text-to-text | Text-to-text | Text-to-text |
| Reasoning | Native reasoning with thinking on or off per request | Native reasoning with thinking on or off per request | Native reasoning with thinking on or off per request |
| Model weights | [Hugging Face](https://huggingface.co/poolside/Laguna-S-2.1) | [Hugging Face](https://huggingface.co/poolside/Laguna-XS-2.1) | [Hugging Face](https://huggingface.co/poolside/Laguna-M.1) |
| License | OpenMDW-1.1 | OpenMDW-1.1 | Apache 2.0 |

## Reasoning Terminology

Poolside and compatible providers use related terms for model reasoning behavior:

- **Reasoning**: The general model capability or behavior. In API contexts, this can also refer to fields such as OpenRouter’s `reasoning` object or assistant `reasoning_content`.
- **Thinking**: The Poolside term for turning reasoning behavior on or off per request.
- **Effort**: A generic scale used to express how much reasoning to request. ACP clients support `default`, `max`, `xhigh`, `high`, `medium`, `low`, `minimal`, and `none`; OpenRouter `reasoning.effort` values depend on provider model metadata.
- **Thought level**: The ACP session config option that maps to effort values.

## Access Models

How you access Poolside models determines which API base URL, reasoning controls, and model IDs are available. To find model IDs for your access method, see [List available models](https://docs.poolside.ai/api/openai-api-examples#list-available-models).

| Access method | API base URL | Reasoning controls |
| --- | --- | --- |
| Poolside Platform | `https://inference.poolside.ai/v1` | Poolside Platform enables thinking by default. To turn it off for an API request, set `chat_template_kwargs.enable_thinking` to `false`. In Poolside ACP sessions, thought level maps `max` to thinking on and `none` to thinking off. |
| Poolside deployment | `https://<api-domain>/openai/v1` | Depends on the deployed models and serving configuration. |
| OpenRouter | `https://openrouter.ai/api/v1` | OpenRouter `reasoning.effort`. Supported values depend on provider model metadata. |
| OpenAI-compatible provider or local server | The base URL your provider or model server exposes | Provider-specific. |

Want to try a model before choosing an access method? Use [chat.poolside.ai](https://chat.poolside.ai/) to send prompts from your browser. No sign-up required.

For authentication and request examples, see [Poolside API](https://docs.poolside.ai/api/overview). To choose a login method for `pool`, see [Log in to Poolside](https://docs.poolside.ai/get-started/log-in).