Muse Spark 1.1
FrontierClosed weightsTextReasoning
Muse Spark family model by Meta.
About the Muse Spark family
Meta Superintelligence Labs' post-Llama flagship line (Muse Spark, Muse Spark 1.1), representing Meta's shift toward closed frontier models with high reasoning-effort variants.
All Muse Spark modelsHow this one is configured
This configuration runs in reasoning mode (thinks step-by-step before answering).
Also runs at: xhigh effort
Effort controls how long the model thinks before answering — higher effort usually means better answers on hard problems, at the cost of speed and money. Same model underneath, so they share this page.