Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Laguna S 2.1 and Laguna XS 2.1, or choose any two current ranked language models. Compare capability evidence, price, context, provider availability, and weight access without pretending one field decides every use case.

Current public data

Laguna S 2.1 vs Laguna XS 2.1

Live dataset updated 8/17/2026, 11:13:20 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Laguna S 2.1 and Laguna XS 2.1
Field
Laguna S 2.1

Poolside

ModelCap position#152#213
Index score22.53.0
EvidenceEstimatedglobal corpus prior · leave-one-anchor-out calibratedEstimatedplaced against measured peers on publisher-reported benchmarks, discounted for self-report optimism
Input / 1M$0.09$0.06
Output / 1M$0.18$0.12
Pricing statusfreshfresh
Context1M262K
Providers11
Weight accessRestricted licenseRestricted license

Decision facts

  • Laguna S 2.1 is #152; Laguna XS 2.1 is #213 on the same current language board.
  • Index scores are 22.5 for Laguna S 2.1 and 3.0 for Laguna XS 2.1.
  • Both positions use Estimated evidence.
  • Listed output price per 1M tokens is $0.18 for Laguna S 2.1 and $0.12 for Laguna XS 2.1.
  • Published context is 1,048,576 tokens for Laguna S 2.1 and 262,144 for Laguna XS 2.1.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.

Each comparison page is a permanent, shareable URL with the same live figures as this tool: ModelCap Index position, API pricing, context window, provider count, weight access and every shared benchmark board.