Laguna S 2.1

Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention.

Context
1.05M
Max output
131K
Input
$0.09
Output
$0.18
DECISION SUMMARY

Recommended use cases

Strengths in this dataset

  • 1,048,576-token context window
  • text input
  • 6 supported API parameters listed

Limits and caveats

  • Provider behavior and pricing can change; verify the linked sources before production use.
CAPABILITIES

Capability

Model-native facts

Model
Reasoning
Supported
Open weights
Unknown

Provider endpoint facts

Provider endpoint
Tool calling
Supported
Structured output
Not supported
Streaming
Unknown
Prompt cache
Supported
Batch
Unknown
Fine-tuning
Unknown
PROVIDER PRICING

Laguna S 2.1 Provider pricing

Provider endpoint: poolside/laguna-s-2.1

Input
$0.09
per 1M tokens
Output
$0.18
per 1M tokens
Cached input
$0.009
per 1M tokens
Image output
Unknown
per 1M tokens
SOURCE RECORDS

Sources and verification

Hugging Face model card

Fields: tags, gated, license, summary, library name, pipeline tag

OpenRouter Models API

Fields: identity, description, modalities, context window, maximum output, pricing, supported parameters

MODEL FAQ

Frequently asked questions

Answers are generated from the same sourced model and provider facts shown above.

Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention.

Model specifications and prices may vary by provider and change over time. AIToolly displays sources and verification dates so users can confirm critical details before production use.