All AI models · LLM benchmarks · Methodology

Poolside

Laguna XS 2.1

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

Model facts

Context window
262K tokens
Maximum output
33K tokens
Cheapest paid input
$0.06 per 1M tokens
Cheapest paid output
$0.12 per 1M tokens
Open weights
yes
Providers
7

Capabilities and modalities

reasoning, tool calling, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 20.3 GiB, Q8_0 35.9 GiB, F16 65.1 GiB working memory.

Parameters
33.4 billion
Architecture
laguna
Model license
openmdw-1.1

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.06 input / $0.12 output per 1M tokens

API providers

  • LLMTR — model id poolside/laguna-xs-2.1; free input / free output per 1M tokens; provider documentation
  • Nvidia — model id poolside/laguna-xs-2.1; free input / free output per 1M tokens; provider documentation
  • OpenRouter (free) — model id poolside/laguna-xs-2.1:free; free input / free output per 1M tokens; provider documentation
  • Poolside — model id poolside/laguna-xs-2.1; free input / free output per 1M tokens; provider documentation
  • OpenRouter — model id poolside/laguna-xs-2.1; $0.06 input / $0.12 output per 1M tokens; provider documentation
  • Kilo Gateway (Poolside) — model id poolside/laguna-xs-2.1; $0.1 input / $0.2 output per 1M tokens; provider documentation
  • Arena — model id laguna-xs-2.1; not published input / not published output per 1M tokens; provider documentation