We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Poolside: Laguna S 2.1 (free)
poolside/laguna-s-2.1:freeTry Poolside: Laguna S 2.1 (free) now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Poolside: Laguna S 2.1 (free) at a glance
- Context window of 262,144 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports reasoning effort control.
About Poolside: Laguna S 2.1 (free)
Laguna S 2.1 is a coding agent model from Poolside, offered on api14 under the model id poolside/laguna-s-2.1:free. It is the latest coding agent model in the Laguna line from Poolside, and the provider release date is 2026-07-21. It is a 118B total parameter model with 8B active parameters, and it scores 70.2% on Terminal-Bench 2.1.
The model works with text input and produces text output, so it fits text based coding and reasoning workflows rather than image or audio tasks. It has a context window of 262144 tokens, which is enough to hold large source files, long diffs, or extended agent transcripts in a single request. The maximum output is 32768 tokens, so responses can be long, but they are still bounded well below the input context size. Supported request parameters are include_reasoning, max_tokens, reasoning, temperature, tool_choice, and tools.
Those capabilities point to practical uses around code. Because it is a coding agent model with tool calling support, it suits tasks such as working through a repository, running commands in a terminal style loop, editing files, and iterating on failing tests. The large context window helps when the model needs to keep many files or a long conversation in view, and the reasoning parameters let you control whether reasoning content is requested or returned. Tool choice and tools let you define the functions or commands the model may call, which is what makes agent style workflows possible rather than plain chat.
You call it through api14's OpenAI-compatible API using the model id poolside/laguna-s-2.1:free. Requests follow the OpenAI chat completions shape, so you send messages and set the parameters the model supports: include_reasoning, max_tokens, reasoning, temperature, tool_choice, and tools. If you use tool calling, pass your tool definitions in tools and control selection with tool_choice. Use max_tokens to cap the response length, and temperature to adjust sampling. The live price table on the page shows current pricing, so check there before you build around it.
One limit to keep in mind is modality: the model accepts text only, so if your task depends on images or audio, a different model is a better fit. The maximum output of 32768 tokens also means very large single responses will be truncated or need to be split across calls. If you need a model outside the coding agent niche, or one with non text input, look elsewhere on api14.
How to call the Poolside: Laguna S 2.1 (free) API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "poolside/laguna-s-2.1:free".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "poolside/laguna-s-2.1:free",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
include_reasoningmax_tokensreasoningtemperaturetool_choicetoolsSpecifications
- Context length
- 262,144
- Max output
- 32,768
- Input
- text
- Output
- text
Requests on api14 · last 7 days
Poolside: Laguna S 2.1 (free): frequently asked questions
- How much does the Poolside: Laguna S 2.1 (free) API cost?
- Poolside: Laguna S 2.1 (free) is free to call ($0 per token). Free variants have stricter upstream rate limits, so use them for testing and low-volume work.
- What is the context window of Poolside: Laguna S 2.1 (free)?
- Poolside: Laguna S 2.1 (free) reads up to 262,144 tokens per request: prompt, history and documents together. It writes up to 32,768 output tokens per response.
- What can Poolside: Laguna S 2.1 (free) do?
- Poolside: Laguna S 2.1 (free) accepts text and returns text. It supports tool calling, reasoning effort control.
- How do I call Poolside: Laguna S 2.1 (free) from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "poolside/laguna-s-2.1:free". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Poolside: Laguna S 2.1 (free)?
- Comparable Text models at a similar price: Recursive: Flint (free), XingChen: Xing4.0 29B A4B (free), NVIDIA: Nemotron 3.5 Super VL (free). Each runs through the same API key, so switching is one string.
Poolside: Laguna S 2.1 (free) community
New topicThis community has no topics yet. Open the first one about Poolside: Laguna S 2.1 (free).