Models

Metnos does not bind every request to a model selected by name. It uses functional contracts: a workload declares the capability it needs, and the instance configuration resolves that contract to an effective model and provider. This keeps application code independent of a specific model and makes substitutions reviewable.

Three families with different purposes

Language models (LLMs): They understand, classify, plan, or generate text. They are organised into functional tiers; several tiers may resolve to the same physical model with different parameters.
Embeddings: They turn text or images into comparable vectors used for semantic search, memory, and Tutor. The HTTP UI displays this configuration but does not edit it.
Vision-language model (VLM): It reads image content when an admitted executor needs it. Its configuration, limits, and timeouts are separate from those of the LLMs.

Language tiers

Tier	Intended use
`fast.micro`	Very short decisions, a choice among a few alternatives, and minimal labels.
`fast.procedural`	Deterministic extraction and classification of short text, when configured.
`fast.fidelity`	Faithful transformation of long text without creative additions.
`middle`	Classification, structured extraction, and intermediate evaluation.
`wise`	Planning, synthesis, and deliberative work where overall quality matters.
`creative`	Variants, proposals, and divergent wording; it is the only tier deliberately configured for greater variation.
`frontier`	Explicit, optional use of a highest-capability remote model, never a silent fallback for ordinary production work.

The creative tier does not mean “more precise”; its purpose is to produce alternatives. Metnos favours low-variation contracts for faithful or verifiable work. The frontier tier may incur external usage and must be configured explicitly.

What can be changed

The page can edit LLM and VLM configuration and restore the previous version. Before saving, Metnos validates the structure and values and retains a recovery copy. Passwords, tokens, credentials, and sensitive URL components are neither displayed nor posted by the form; the UI changes visible values only.

Changing a model does not extend Metnos's authority. Executors, policy, user identity, and budgets still determine whether an action is admissible. LRE also records the model binding in its revision, so an incompatible change must not silently mix results produced under different configurations.

The Models screen

The real model-configuration screen in an Italian-language Metnos instance. — The screen reports effective configuration, not a promotional model catalog.

Navigation. Models is under System in Settings.
Reload. Re-reads effective configuration after a controlled external change.
Secret protection. States which values the form never exposes.
Edit and restore. Operate on the admitted family while preserving a recovery path.
Tier cards. Show the resolved endpoint, provider, model, and parameters.

The local path is abbreviated in the image. Structure and labels come from the real HTTP UI.