Academy
Automatic Model Selection: How OUPI Routes Your Messages
Understand how OUPI automatically picks the best model for each message you send. Learn the routing logic (task type, complexity, plan, cost, reliability), how failover protects you when a provider goes down, how reasoning effort scales with complexity, how team restrictions shape the eligible pool, and when and how to override the automatic choice.
Plan du cours
1
Why OUPI Offers Many Models — and Four Families to Know
Understand the landscape of model families (frontier, balanced, fast, specialist) so the automatic selector's choices make sense to you.
2
How Automatic Selection Routes Each Message
Learn the five signals OUPI evaluates per message — task type, complexity, plan eligibility, cost and reliability — and how they produce a model choice shown by a badge.
3
Automatic Failover: What Happens When a Provider Fails
Understand that OUPI continuously measures provider reliability and retries on another provider if the first one is unavailable or quota-exhausted.
4
Reasoning Effort: How Depth Scales with Complexity
Learn that for models supporting extended reasoning, OUPI automatically adjusts thinking depth based on detected complexity — no manual setting needed.
5
Team and Plan Restrictions on Model Eligibility
Understand how your plan and your administrator's team settings define which models automatic selection can choose from, keeping data with approved providers.
6
Missions and Agents: Automatic Selection Beyond Chat
Learn that missions use an admin-configured model pool with the same health signals, and that agents may switch models between steps.
7
Overriding: When and How to Choose Manually
Know how to read the model badge, pick a model manually for the rest of a conversation, regenerate with a different model to compare, and switch mid-conversation without losing history.
Suivre ce cours dans OUPI
Progression, quiz et certificat dans votre compte — 6 questions pour valider vos acquis et décrocher un certificat, dans votre espace OUPI.