> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/control-center/ai-gateway/model-catalog.md).

# Model Catalog

Review models, providers, statuses, filters, and routing availability for projects.

Model Catalog lists models available through AI Gateway. It groups models by family and shows each provider's status. You can't change provider configuration here.

Use Model Catalog to confirm model availability before assigning a model to a tier. For what families, providers, and tiers are, read [How Model Routing Works](/control-center/ai-gateway/how-model-routing-works.md).

Open **Control Center** → **AI Gateway** → **Model Catalog**. The path is `/platform/control-center/ai-gateway/model-catalog`.

## How Model Catalog works

A model family groups models from one source. A provider supplies access to models within that family.

| Term             | Meaning                            | Examples                                             | What it tells you            |
| ---------------- | ---------------------------------- | ---------------------------------------------------- | ---------------------------- |
| Family           | Models from a common source        | Anthropic, Google, OpenAI                            | Related models               |
| Provider         | Service that provides model access | Anthropic direct, GCP Model Garden, Google AI Studio | Where the model is available |
| `Enabled`        | Authentication is configured       | Green status                                         | The provider is available    |
| `Not configured` | Authentication isn't configured    | Orange status                                        | The provider isn't available |

Status applies to each `(model, provider)` pair. One model can be `Enabled` through one provider and `Not configured` through another. Anthropic can use *Anthropic* direct or *GCP Model Garden*. Google can use *Google AI Studio* or *Google Agent Platform*. OpenAI can use *OpenAI* direct or *Azure OpenAI*.

## Choose the right destination

| Goal                           | Go to                                                              | Outcome                       |
| ------------------------------ | ------------------------------------------------------------------ | ----------------------------- |
| Change provider authentication | [Gateway Settings](/control-center/ai-gateway/gateway-settings.md) | Update provider configuration |
| Identify a request's model     | [Runs & Traces](/control-center/observe/runs-and-traces.md)        | Inspect the completed request |
| Review configuration changes   | [Audit Trails](/control-center/observe/audit-trails.md)            | View change history           |
| Stop an agent                  | [Agent Controls](/control-center/govern/agent-controls.md)         | Stop the agent                |

Use Model Catalog when you build an agent, diagnose provider configuration, or compare context windows.

## Review model availability

Select a family to view its models. Each model lists its display name, context window, and provider statuses.

Select the family name to expand or collapse its models.

<figure><img src="https://1326225582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0qmgQjJ5aArDTj2ACFHG%2Fuploads%2Fgit-blob-e05e8580a90789e7e6eea2d7467b03b327b644aa%2Fqore_control-center_control-centre-ai-gateway-model-catalog_rounded_shadow.png?alt=media" alt="Model Catalog with the Anthropic family expanded, listing Claude Haiku, Sonnet, and Opus models with their context windows and per-provider Enabled/Not configured status"><figcaption><p>Model Catalog, with a family expanded to show its models.</p></figcaption></figure>

{% hint style="info" %}
`Enabled` and `Not configured` only report status. To change a status, open [Gateway Settings](/control-center/ai-gateway/gateway-settings.md) and select **Edit configuration**.
{% endhint %}

Review all provider statuses for a model. A provider can be `Enabled` while another remains `Not configured`.

When one provider is `Enabled`, the model is available through that provider.

## Find models

{% tabs %}
{% tab title="Search by name" %}
Enter a model, family, or provider name in **Search models, families, providers…**.
{% endtab %}

{% tab title="Limit by family" %}
Select **All families**, **Anthropic**, **Google**, **OpenAI**, **Qwen**, or **Test model families**.

Some filter options might not have matching model groups.
{% endtab %}

{% tab title="Limit by status" %}
Select **All statuses**, **Enabled**, or **Not configured**.
{% endtab %}

{% tab title="Refresh results" %}
Select **Refresh** to update the catalog results.
{% endtab %}
{% endtabs %}

{% hint style="warning" %}
Search hides families without matching models. It doesn't display empty families.
{% endhint %}

## Models available through the gateway

The catalog in the product is the authoritative inventory for your organization. The tables below are a snapshot of what Uptiq offers, listed so you can compare context windows without opening the screen. Your provider statuses depend on your own credentials.

### Anthropic

Available through **Anthropic** and **GCP Model Garden**.

| Model             | Context |
| ----------------- | ------- |
| Claude Haiku 4.5  | 200K    |
| Claude Sonnet 4.5 | 200K    |
| claude-sonnet-4   | 200K    |
| Claude Sonnet 4.6 | 1M      |
| Claude Sonnet 5   | 1M      |
| Claude Opus 4.5   | 1M      |
| Claude Opus 4.6   | 1M      |
| Claude Opus 5     | 1M      |

### Google

Available through **Google AI Studio** and **Google Agent Platform**.

| Model                           | Context | Providers                               |
| ------------------------------- | ------- | --------------------------------------- |
| gemini-2.0-flash                | 1M      | Google AI Studio                        |
| Gemini 2.5 Flash                | 1M      | Google AI Studio; Google Agent Platform |
| Gemini 3 Flash Preview          | 1M      | Google AI Studio; Google Agent Platform |
| Gemini 3 Flash Preview Priority | 1M      | Google Agent Platform                   |
| Gemini 3.1 Flash Lite           | 1M      | Google AI Studio; Google Agent Platform |
| Gemini 3.1 Pro Preview          | 1M      | Google AI Studio; Google Agent Platform |
| Gemini 3.1 Pro Preview Priority | 1M      | Google Agent Platform                   |
| Gemini 3.5 Flash                | 1M      | Google AI Studio; Google Agent Platform |
| Gemini 3.5 Flash Lite           | 1M      | Google AI Studio                        |
| Gemini 3.5 Flash Priority       | 1M      | Google Agent Platform                   |

{% hint style="info" %}
Priority SKUs run on Google Agent Platform only. They provide dedicated capacity for latency-sensitive workloads.
{% endhint %}

### OpenAI

Available through **OpenAI** and **Azure OpenAI**.

| Model         | Context |
| ------------- | ------- |
| GPT 3.5 Turbo | 16K     |
| GPT 4         | 8K      |
| GPT 4 Turbo   | 128K    |
| GPT 4.1       | 1M      |
| GPT 4.1 Mini  | 1M      |
| GPT 4.1 Nano  | 1M      |
| GPT 4o        | 128K    |
| GPT 4o Mini   | 128K    |
| GPT 5         | 400K    |
| GPT 5 Mini    | 400K    |
| GPT 5 Nano    | 400K    |
| GPT 5.1       | 400K    |
| GPT 5.2       | 400K    |
| GPT 5.4       | 1M      |
| GPT 5.4 Pro   | 1M      |
| GPT 5.6 Luna  | 1M      |
| GPT 5.6 Sol   | 1M      |
| GPT 5.6 Terra | 1M      |
| o1            | 200K    |
| o3            | 200K    |
| o3 Mini       | 200K    |
| o4 Mini       | 200K    |

### Default tier mappings

These are the as-shipped mappings, not a report of your current configuration. Check and change them in [Gateway Settings](/control-center/ai-gateway/gateway-settings.md).

| Family    | Economy           | Smart                  | Premium                |
| --------- | ----------------- | ---------------------- | ---------------------- |
| Anthropic | Claude Sonnet 4.5 | Claude Sonnet 4.5      | Claude Sonnet 4.5      |
| Gemini    | Gemini 2.5 Flash  | Gemini 3 Flash Preview | Gemini 3.1 Pro Preview |
| OpenAI    | GPT 4o Mini       | GPT 4o                 | GPT 4.1                |

{% hint style="warning" %}
The Anthropic default maps all three tiers to the same model. Assign distinct models where you want a real difference in cost or capability.
{% endhint %}

## Examples

### Confirm a specific model is available

Confirm that *Claude Opus 4.6* is available before assigning it to an agent.

{% stepper %}
{% step %}

#### Find the family

Open Model Catalog and select **Anthropic**.
{% endstep %}

{% step %}

#### Find the model

Find *Claude Opus 4.6*.
{% endstep %}

{% step %}

#### Check availability

Confirm that at least one provider is `Enabled`. The model is available through that provider.
{% endstep %}
{% endstepper %}

`Not configured` means the model-provider pair lacks authentication. The provider isn't available for that model.

### Bookmark a runbook filter

Save a filtered view of Sonnet models for an incident runbook.

{% stepper %}
{% step %}

#### Search for Sonnet

Enter `sonnet` in **Search models, families, providers…**. The URL includes `?search=sonnet`.
{% endstep %}

{% step %}

#### Save the URL

Bookmark the URL or add it to the runbook.
{% endstep %}

{% step %}

#### Reuse the filter

Open the bookmark when you investigate an incident.
{% endstep %}
{% endstepper %}

The `?search=` parameter persists in the URL. You can share the filtered view.

### Diagnose why a model is unavailable

Resolve a `provider not configured` error for a model.

{% stepper %}
{% step %}

#### Locate the model

Open Model Catalog, select the model's family, and find the model.
{% endstep %}

{% step %}

#### Check the provider

If the intended provider is `Not configured`, update its configuration elsewhere.
{% endstep %}

{% step %}

#### Configure authentication

Open [Gateway Settings](/control-center/ai-gateway/gateway-settings.md). Select **Edit configuration**, select the family, then configure a **UPTIQ managed key** or **Bring your own key**. Save the family.
{% endstep %}
{% endstepper %}

## Why this matters

* **Model Catalog is read-only.** Use [Gateway Settings](/control-center/ai-gateway/gateway-settings.md) to change provider configuration.
* **Statuses apply to each `(model, provider)` pair.** One `Enabled` provider keeps a model available.
* **Search hides families without matches.** A missing family is filtered, not empty.
* **Google and Gemini refer to the same family.** Model Catalog uses Google. Gateway Settings uses Gemini.

## Related

<table data-view="cards"><thead><tr><th>Title</th><th>Description</th><th data-card-target data-type="content-ref">Link</th></tr></thead><tbody><tr><td><strong>How Model Routing Works</strong></td><td>Families, providers, gateways, credentials, and tiers explained.</td><td><a href="/control-center/ai-gateway/how-model-routing-works.md">How Model Routing Works</a></td></tr><tr><td><strong>Gateway Settings</strong></td><td>Configure families, providers, tier models, and AI Gateway authentication.</td><td><a href="/control-center/ai-gateway/gateway-settings.md">Gateway Settings</a></td></tr><tr><td><strong>Agent Controls</strong></td><td>Stop individual agents or all agents during an emergency.</td><td><a href="/control-center/govern/agent-controls.md">Agent Controls</a></td></tr><tr><td><strong>Runs &#x26; Traces</strong></td><td>Inspect the model and provider for a completed request.</td><td><a href="/control-center/observe/runs-and-traces.md">Runs &amp; Traces</a></td></tr><tr><td><strong>Audit Trails</strong></td><td>Review changes to gateway configuration over time.</td><td><a href="/control-center/observe/audit-trails.md">Audit Trails</a></td></tr><tr><td><strong>Glossary</strong></td><td>Look up gateway, family, provider, and status terms.</td><td><a href="/start-here/glossary.md">Glossary</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.uptiq.ai/control-center/ai-gateway/model-catalog.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.