25 signals
HOlO V1 IS LIVEone ranked AI digest a day, scored in publicREAD HOW IT WORKS →HOlO V2 STARTSyour X account, your signals, every day

Model registry / Poolside / Laguna / Laguna XS 2.1

Laguna XS 2.1

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

Line

Laguna

Weights

Open

Released

2026-07-02

Context

262K

Input

$0.06 / 1M

Output

$0.12 / 1M

Max output

33K

Coverage

not covered yet

Overview

Laguna XS 2.1 is an agentic coding model from Poolside in the XS size class, designed for local deployment. It is part of the Laguna line. It has a context window of 262144 tokens and a maximum output of 32768 tokens. The weights are open. It supports reasoning mode and tool calling. It accepts and returns text. Pricing starts at $0.06 per million input tokens and $0.12 per million output tokens, with cached input at $0.03 per million tokens.

Specs

Released2026-07-02
LinePoolside · Laguna
WeightsOpen
Context262K tokens
Max output33K tokens
Inputtext
Outputtext
ReasoningYes
Tool callingYes
Knowledge cutoffnot stated
API idpoolside/laguna-xs-2.1

Pricing

Input$0.06 / 1M tokens
Cached input$0.03 / 1M tokens
Output$0.12 / 1M tokens

Against Laguna M.1: input $0.00 to $0.06, output $0.00 to $0.12, cached input $0.00 to $0.03.

Range across the hosts that serve it: up to $0.10 per 1M input tokens.

Strengths

  • Agentic coding for local deployment
  • Open weights for self-hosting
  • 262k token context window
  • Tool calling and reasoning mode
  • Low input price from $0.06 per million

Best for

  • Reach for it for local agentic coding
  • Reach for it for long-context code generation
  • Reach for it for tool-using coding agents
  • Reach for it for cost-sensitive inference

How to access

ProviderModel id
Kilo Gatewaypoolside/laguna-xs-2.1
LLMTRpoolside/laguna-xs-2.1
Nvidiapoolside/laguna-xs-2.1
OpenRouterpoolside/laguna-xs-2.1
Poolsidepoolside/laguna-xs-2.1

5 hosts serve this model at the price above · the maker's documentation

Laguna: every version

VersionReleasedContextInput
Laguna S 2.1Current2026-07-211.05M$0.09
Laguna XS 2.12026-07-02262K$0.06
Laguna M.12026-04-28262K$0.00

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

FAQ

What is the context window?
262144 tokens.
Does it support tool calling?
Yes, it supports tool calling and reasoning mode.
What is the pricing?
From $0.06 per million input tokens and $0.12 per million output tokens, with cached input at $0.03 per million.
Open weightsReasoning262K context