# Laguna XS.2

> The second-generation model in the XS size class from Poolside, their efficient coding agent series. Combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 8K output tokens. Quantized to fp8 for fast, cost-efficient agentic coding workflows. Licensed under Apache 2.0.

**ID**: `poolside/laguna-xs.2`  
**Creator**: poolside  
**Category**: text  
**Context**: 262K tokens  
**Status**: Disabled (since 2026-08-13) — no longer routable or listed; kept for history/usage reference.  
**Reason**: Poolside's live listing (inference.poolside.ai/v1/models) now carries only laguna-xs-2.1 and laguna-s-2.1 — this generation is gone, so every upstream here 404s.  
**Input**: $0  
**Output**: $0  
**Released**: 2026-04-28  
**Web page**: https://anyrouter.dev/model/poolside/laguna-xs.2

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, streaming, coding, reasoning, function-calling

**Supported parameters**: max_tokens, temperature, top_p, stop

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "poolside/laguna-xs.2",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| hoian | $0 | $0 |
| poolside-byok | $0 | $0 |

## Source

- Upstream docs: https://docs.poolside.ai/laguna-xs.2:free