Laguna XS 2.1

Tool callingReasoning

Hugging Face Website

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

Context: 262K
Released: 3mo ago
Parameters: —
Input / 1M tokens: $0.06
Output / 1M tokens: $0.12
Cached input / 1M tokens: $0.03

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Poolside
Model family: —
Type: Language model
Predecessor: —
Successor: —
Released: July 2, 2026
Model ID: poolside/laguna-xs-2.1
Openness: Open weights
License: —
Parameters: —
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 256K
Tokenizer: Other
Max output tokens: 33K
Hugging Face: poolside/Laguna-XS-2.1
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: poolside/laguna-xs-2.1
Source family: laguna
Last updated: 2026-07-02
Model context: 262K
Model output limit: 33K
Open weights: Yes
File attachments: No
Reasoning: Yes
Tool calling: Yes
Structured output: No
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Verified	70.9 · resolved	Harbor · 2026-07-02	Source
SWE-Bench Multilingual	63.1 · resolve rate	Harbor · 2026-07-02	Source
SWE-Bench Pro	47.6 · resolve rate	Harbor · 2026-07-02	Source
Terminal-Bench	37.5 · success rate	Harbor · 2.0 · 2026-07-02	Source

Complete source record (JSON)

{
  "id": "poolside/laguna-xs-2.1",
  "name": "Laguna XS 2.1",
  "description": "Agentic coding model from Poolside in the XS size class for local deployment",
  "family": "laguna",
  "last_updated": "2026-07-02",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "structured_output": false,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 32768
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 70.9,
      "source": "https://poolside.ai/blog/introducing-laguna-xs-2-1",
      "metric": "resolved",
      "harness": "Harbor",
      "date": "2026-07-02"
    },
    {
      "name": "SWE-Bench Multilingual",
      "score": 63.1,
      "source": "https://poolside.ai/blog/introducing-laguna-xs-2-1",
      "metric": "resolve rate",
      "harness": "Harbor",
      "date": "2026-07-02"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 47.6,
      "source": "https://poolside.ai/blog/introducing-laguna-xs-2-1",
      "metric": "resolve rate",
      "harness": "Harbor",
      "date": "2026-07-02"
    },
    {
      "name": "Terminal-Bench",
      "score": 37.5,
      "source": "https://poolside.ai/blog/introducing-laguna-xs-2-1",
      "metric": "success rate",
      "harness": "Harbor",
      "version": "2.0",
      "date": "2026-07-02"
    }
  ],
  "release_date": "2026-07-02",
  "open_weights": true
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Poolside	poolside/fp8	262K	$0.06	$0.12	$0.03	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware