tokenstat
tokenstat

NVIDIA: Laguna XS 2.1

nvidia/laguna-xs-2.1 · rates as of · Benchmarks · AI plans · Calculator

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

Cheapest input
$0.06
$/MTok · OpenRouter
Cheapest output
$0.12
$/MTok
Context
262K
tokens
Sources
3
4 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (7 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
OpenRoutercheapestpoolside/laguna-xs-2.1OpenRouter$0.06$0.12$0.03262K
LiteLLMpoolside/laguna-xs-2.1N/A$0.06$0.12$0.03N/A
LiteLLMlaguna-xs-2.1N/A$0.06$0.12$0.03N/A
models.devpoolside/laguna-xs-2.1Kilo Gateway$0.1$0.2$0.05262K

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2026-07-02Family: laguna

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.