Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 262K tokens
- Added
- Apr 28, 2026
- Max output
- 33K tokens
- Tokenizer
- Other
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
No provider breakdown is published for Laguna XS.2 (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- temperature
- tool_choice
- tools
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model poolside/laguna-xs.2:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "poolside/laguna-xs.2:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="poolside/laguna-xs.2:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "poolside/laguna-xs.2:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Laguna XS.2 (free)
Laguna XS.2 (free) is Poolside's compact coding-agent model, paired with tool calling and optional reasoning in a small-footprint package. It handles a 262,144-token context window and caps completion at 32,768 tokens, so it's built for long-context code tasks rather than short chat turns. Text in, text out only — no vision. Reasoning is available per request but not forced on, which keeps it flexible for both quick tool-calling steps and slower, more deliberate coding tasks. It's the free tier of the XS.2 line, sitting alongside a paid version with identical specs.
This is the free version of Laguna XS.2 — same 262,144-token context window as its paid sibling (which costs $0.10/$0.20 per 1M input/output tokens), but at zero cost. That context window beats 56% of catalog models. Poolside also runs a larger Laguna M.1 line at $0.20/$0.40 per 1M tokens, plus a free M.1 tier, so the lab offers four price/size combinations. Reasoning is optional here, not mandatory — you can toggle it per request depending on whether you need speed or depth.
Questions
- How much does Laguna XS.2 (free) cost via API?
- It's free — $0 per 1M input tokens and $0 per 1M output tokens from the provider, and OpenKey's 3% fee on a $0 base is still $0. There's also a paid Laguna XS.2 with identical specs at $0.10/$0.20 per 1M input/output tokens if you need a non-free SLA or rate limits.
- What is Laguna XS.2 (free)'s context window?
- It's 262,144 tokens, roughly enough to hold several large codebases' worth of source files or a few hundred pages of text in a single request. That's a larger window than 56% of models in the OpenKey catalog, and it applies equally to the free and paid versions of XS.2.
- Is Laguna XS.2 (free) free to use?
- Yes, both prompt and completion tokens are priced at $0.00 per 1M from the provider. It's one of the free models on OpenKey, sitting next to a paid Laguna XS.2 variant priced at $0.10/$0.20 per 1M tokens for input/output.
- Does Laguna XS.2 (free) support tool calling and reasoning?
- Yes to both. It supports tool_choice and tools parameters for function calling, plus a reasoning parameter that's enabled by default but not mandatory — you can turn it off per request. It does not support image or other non-text input; modality is text-to-text only.
- How does Laguna XS.2 (free) compare to Laguna M.1?
- Laguna M.1 is Poolside's larger model, priced at $0.20/$0.40 per 1M input/output tokens versus $0.10/$0.20 for the paid XS.2 — roughly double the cost. Both have a free tier: Laguna M.1 (free) and Laguna XS.2 (free) are both $0.00/$0.00, giving you a choice of two free coding models from the same lab at different size classes.
More from poolside
All poolside models →Laguna M.1
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
ctx 262K in $0.206 out $0.412
Laguna M.1 (free)
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
ctx 262K in Free out Free
Laguna XS.2
Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
ctx 262K in $0.103 out $0.206