> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gloo.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> The model catalog and fallback chains — what models the platform can dispatch to, and how Forge picks a model for an agent turn.

**Models** (`/platform/models`) is the model catalog. Forge resolves each agent turn to a model from the agent's own fallback chain when an active one is assigned, and otherwise from the agent's default model. This page exposes the catalog, the providers, and the fallback chains.

![Models](https://mintcdn.com/gloo-b243725a/Ndtg9NEpwGc2OULA/forge/images/console/platform/models-light.png?fit=max\&auto=format\&n=Ndtg9NEpwGc2OULA\&q=85\&s=f3cd889ca927e252f6d0d120a0a7936f)

Models — Forge Console at `/platform/models`

## What you can do

* Browse the model catalog filtered by provider, by family, by capability (chat / embedding / vision).
* Inspect a model's per-token cost, its context window, its capability flags, and its current health.
* Promote, demote, or remove a model in a fallback chain on the **Fallback Chains** tab.

## Organizing the catalog

The catalog uses the shared **collection grammar** — the same Search · Group · Sort · Filter · Layout toolbar every Forge collection carries.

* **Group by** — **Provider** (the default) or **Brand**. Group headers show a live count; models with no brand land in an **Unassigned** bucket that renders last.
* **Sort by** (in the **Display** popover) — **Name** is the default *within every group*, regardless of group size; **Updated** and **Created** are one click away. Name is always the tiebreak.
* **Filter** — by **provider** and by **status**.
* **Layout** — **card** (the default) or **list**, persisted in `?layout=`.

Each card's meta footer shows the model's last-updated time and how many agents reference it. The active view (group, sort, filters, layout, search) is reflected in the URL, so a configured catalog view is bookmarkable — and the `?groupBy=` bookmark from the older provider/brand toggle still works.

## The catalog is the pricing authority

The per-token cost on a catalog row is what the platform actually bills a turn against — it flows into the token ledger, each step's cost, run totals, factory attribution, and the budget gates that can stop a run. Two consequences worth knowing:

* **A row only counts while it is active.** A model with no active catalog row falls back to a built-in rate table keyed by model name. That table tracks published vendor rates but is not guaranteed to match a negotiated or newly-changed one — so a stale or deactivated row means a turn is priced from a guess.
* **An unrecognized model is deliberately over-estimated.** A model that matches nothing at all is priced at the platform's most expensive tier rather than a mid-range average, because cost feeds budget enforcement and over-estimating fails safe. If a model's spend looks implausibly high, an absent catalog row is the first thing to check.

Keeping rows present, active, and re-quoted after **Cost drift** is therefore not just reporting hygiene — it is what makes budget enforcement accurate.

## Correcting a rate

A model's detail page carries **Edit specs & rates** (admin only). It edits the input, output, and cached-input rates directly, so a provider price change reaches the platform without waiting for a deploy.

Three things happen when you save a rate:

* **The change is journaled to the price history** as a manual edit. That journal entry is what protects your number: the deploy-time rate backfill compares every row against the repo fixture and would otherwise revert a hand-set rate on the next release. A manual entry makes it decline.
* **The rate is stamped as verified today.** This is separate from *Last synced* — the provider model-list sync refreshes specs weekly and returns no cost at all, so a row can look freshly synced while its price has been wrong for a year.
* **Rates stay editable even on synced models.** Context window and max output tokens are hidden when the provider supplies them; cost never is, because no provider reports it.

Re-submitting an unchanged rate is a real action, not a no-op: it re-stamps the verification date. That is how you record "I checked, this is still correct" without inventing a price change.

**Editing only the specs does not touch the verification date.** Changing Context Window or Max Output Tokens and saving leaves *Verified Nd ago* exactly where it was, because that edit sends no rate field at all — and the age is what the 90-day staleness alarm and the deploy-time backfill both read. Re-affirming a rate is a claim about the price; adjusting a spec is not, and it must not be able to quiet an alarm about a number nobody looked at.

> [!NOTE]
>
> Editing a rate changes what **future** turns cost. Events already recorded keep the cost they were captured at, so a dashboard spanning the correction shows both regimes. An admin-only repricing action can recompute historical events at the corrected rate; it is deliberately manual, so a correction and a rewrite of history are two decisions rather than one.

## Key state to watch

* **Provider health** — when a call to a chain's model hits a temporary provider failure or a credential refusal, Forge moves to the chain's next model; the badge surfaces the current health.
* **Live model availability** — models the catalog claims but the provider isn't actually serving are flagged.
* **Cost drift** — when a model's per-token cost changes upstream, the catalog flags it for re-quote.
* **Unverified rates** — a rate nobody has affirmed in 90 days raises an attention item in **Observe → Operations**, and the model page shows *Verified Nd ago* (or *Never verified*). Provider price cuts are the most common way a rate silently drifts, and nothing else in the platform notices them.

## Related

* Architecture → [LLM Routing](https://docs.gloo.com/forge/architecture/llm-routing.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.