Laguna XS.2 APIOPEN WEIGHTS262K context
Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series.
Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go).
What is 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...
Laguna XS.2 pricing
Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):
| Model | Input / 1M | Output / 1M | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Laguna XS.2 | $0.10 | $0.20 | $0.05 | — | 262K |
On output price, Laguna XS.2 is cheaper than 89% of the 309 models in the catalog.
What Laguna XS.2 costs per month
| Workload | Tokens in / out (monthly) | Est. cost |
|---|---|---|
| Support chatbot | 40M / 12M | $6.40 |
| RAG / knowledge base | 200M / 20M | $24.00 |
| Coding agent | 80M / 25M | $13.00 |
| Batch extraction | 150M / 8M | $16.60 |
| Content generation | 20M / 40M | $10.00 |
Estimate your own monthly cost
Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.
Laguna XS.2 vs alternatives
| Model | Input / 1M | Output / 1M | Context | Our test |
|---|---|---|---|---|
| Laguna XS.2 | $0.10 | $0.20 | 262K | — |
| Laguna M.1 | $0.20 | $0.40 | 262K | — |
| UI-TARS 7B | $0.10 | $0.20 | 128K | — |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262K | — |
| Mistral Small 3.2 24B | $0.07 | $0.20 | 128K | — |
When not to use Laguna XS.2
- It is served by a single provider, so there is less failover headroom during an outage.
Specs
| Model ID | poolside/laguna-xs.2 |
| Modality | text->text (input: text) |
| Context window | 262,144 tokens |
| Max output | 32,768 tokens |
| Tool / function calling | ✅ Yes |
| Structured output (JSON) | — |
| Released | 2026-04-28 |
| Open weights | ✅ poolside/Laguna-XS.2 · 88.6K downloads / 316 likes (30d) |
How to call Laguna XS.2
from openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
model="poolside/laguna-xs.2",
messages=[{"role": "user", "content": "Hello"}],
# supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)curl https://api.datallmlab.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"poolside/laguna-xs.2","messages":[{"role":"user","content":"Hello"}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
model: "poolside/laguna-xs.2",
messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);The same key routes Laguna XS.2 and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.
Prompting tips for Laguna XS.2
- State the goal, not every step. Laguna XS.2 reasons internally — give it the objective, constraints and success criteria and let it plan the approach; over-scripting each step tends to lower quality. Turn effort up for hard problems.
- Huge 262K context — but anchor the ask. You can paste whole documents or codebases; models attend most to the start and end, so put the key instruction at the top and restate it after long inputs.
- Give it real tools. Pass a
tools=[...]schema instead of asking it to "pretend" — let Laguna XS.2 emit tool calls, execute them, and feed results back for the next turn. - Cheap enough to batch. Great for high-volume classification, extraction and drafting — template the prompt, batch requests, and validate outputs programmatically.
Tips are derived from Laguna XS.2's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.
Open-source tools for Laguna XS.2
Popular open-source projects for running and building with Laguna XS.2 — star counts pulled from GitHub (July 2026).
Listed by GitHub stars; inclusion is by ecosystem relevance (inference engines, agent frameworks and SDKs), not affiliation. Stars change — see each repo for current numbers.
Migrating to Laguna XS.2
Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → poolside/laguna-xs.2. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.
Self-host or use the API?
Laguna XS.2 ships open weights (poolside/Laguna-XS.2, ~88.6K downloads and 316 likes in the last 30 days), with community quantizations (fp8) for smaller GPUs, so you can run it yourself. Most teams still use the API: no GPU to provision or keep warm, no inference ops, and instant access across 1 providers with automatic failover. Self-host when data residency or fixed per-token economics matter most.
Rate limits & reliability
Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff. See the error-code guide and failover setup.
Related reading
Call Laguna XS.2 with one key
300+ models behind one OpenAI-compatible endpoint — better prices, better uptime, no subscriptions.
Get an API keyCompare pricingFrequently asked questions
What is 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 accepts text input with a 262K-token context window and was released on 2026-04-28. On DataLLM Lab it is callable through one OpenAI-compatible endpoint.
How much does Laguna XS.2 cost?
On DataLLM Lab it is $0.10 per 1M input tokens and $0.20 per 1M output tokens, with cached input at $0.05/1M — cheaper than about 89% of the 309-model catalog on output price. Pay-as-you-go, no subscription.
What is the context window of Laguna XS.2?
262K tokens, with up to 33K max output tokens.
Is Laguna XS.2 open source?
Yes — open weights are published on Hugging Face (poolside/Laguna-XS.2), with about 88.6K downloads and 316 likes in the last 30 days. You can self-host it or call it via DataLLM Lab.
How do I call the Laguna XS.2 API?
Point any OpenAI SDK at https://api.datallmlab.com/v1 and set model to "poolside/laguna-xs.2". One DataLLM Lab key routes this model and 300+ others; no code changes beyond the base URL and model string.
What are good alternatives to Laguna XS.2?
Close options by price and capability include Laguna M.1, UI-TARS 7B , Ministral 3 14B 2512 — all callable with the same DataLLM Lab key.