state) against one or more typed questions and returns calibrated probabilities across a fixed, caller-defined set of outcomes. There are no generated tokens to parse — answers come back as structured labels, probabilities, and confidence scores.
When to use GLiDE
GLiDE is a good fit for structured decisions: classification, categorization, routing (tickets, emails, requests), scoring, triage, content moderation, guardrails, LLM-as-judge replacement, and agent tool-call approval. Use a general-purpose language model instead for free-form generation, multi-turn conversation, open-ended Q&A, summarization, or code generation.Decision Models
Learn the Noul / Choice / Score primitives, the request contract, and confidence.
View the model catalog
Browse Fastino models and their model IDs.