Laguna XS 2.1

PoolsideMCP Tool CallReasoning

poolside/laguna-xs-2.1Open Weights

Agentic coding model from Poolside in the XS size class for local deployment

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out

Context: 262,144 tokens•Max Output: 32,768 tokens•Released: 2026-07-02

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens

Max Output32,76832.8K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Laguna XS 2.1 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved

70.9

SWE-Bench Multilingualresolve rate

63.1

SWE-Bench Proresolve rate

47.6

Terminal-Benchsuccess rate

37.5

API CALL INVOCATION EXAMPLE

// Example: Calling Laguna XS 2.1 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.POOLSIDE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "poolside/laguna-xs-2.1",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);