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

# Choose AI models in Hive and restrict them for your workspace

> How the Ask Hive model picker works — Workspace default, Hive Auto and specific models — and how admins set defaults and restrict the workspace to approved models.

Hive can answer with more than one AI model. Most of the time you do not need to choose: the
workspace default is set by your admins. When you do want a particular model — a faster one for a
quick lookup, a more capable one for a long analysis — pick it from the model picker in the Ask
composer.

<Note>
  Hive does not publish a fixed list of models. The picker only offers models your workspace can
  actually use: those whose provider is configured for your deployment, that your admins allow,
  and that can serve a chat turn. The list changes as models are added and retired.
</Note>

## The model picker

Open the picker in the composer (the **Hive · default** button — **Hive · auto** when your workspace routes automatically, or **Hive ·** followed by the model's name once you have chosen one). It shows:

* **Workspace default** — uses your workspace and personal settings. The description names the
  model that will answer.
* **Hive Auto** — shown instead when your workspace's default is automatic routing: "Use
  automatic routing configured by your workspace." Hive picks a suitable model for each turn.
* **Or pick a model** — the specific models available to you, each shown with its provider's icon. Open one to see
  its description and a relative **Usage consumption** meter; **How is this calculated?** explains
  the estimate.

"Workspace and billing rules apply to every turn" — your choice never bypasses spend limits or
seat credits.

### Unavailable models

Admins also see models that exist but cannot be used, with the reason:

| Message | Meaning |
| - | - |
| **No credentials configured.** | The model's provider is not set up for this deployment. |
| **Cannot serve an Ask turn.** | The model lacks a capability Ask needs. |
| **Not enabled for your workspace membership.** | Your admins have not allowed it for you. |

If no model is available at all, Ask still answers with its default.

### What your choice affects

An explicit model choice also governs the internal planning and retrieval steps for that turn, not
just the final wording. Each answer records the model that actually produced it.

When your seat's credits run out, a chat turn falls back to the included efficient model rather
than failing. See [Billing and plans](/admin/billing-and-plans).

## For admins: model settings

Owners and admins manage models under **Settings → Workspace → Models**.

<Steps>
  <Step title="Set the defaults">
    Choose the **Default chat model** (or **Auto** for automatic routing), plus the **Fast
    model** and **Powerful model** Hive uses for lighter and heavier work. Leaving the default chat
    model on **Deployment default** leaves the choice to Hive. Choose **Save model defaults**.
  </Step>

  <Step title="Restrict the workspace (optional)">
    Under **Select the models you allow in your workspace**, pick the models your people may use and
    choose **Save for workspace**. An allowlist holds up to 50 models.
  </Step>

  <Step title="Add a custom model (optional)">
    Where your deployment supports it, **Add custom model** registers a model by name and ID, and
    whether it **Supports image input**.
  </Step>
</Steps>

### How the allowlist behaves

* An **empty allowlist means no restriction**: everyone can use every model the deployment offers,
  and new models appear as they are added.
* Once you restrict the workspace, new models are **never** added automatically — you opt each one
  in. This makes the allowlist a cost, data-residency and vendor-policy control.
* A model you allowed that later stops being offered is simply ignored; it never widens access.

<Tip>
  Vetting AI vendors? Restrict the workspace to the providers you have approved. See
  [AI and models](/security/ai-and-models) for how Hive handles model traffic.
</Tip>

## Models elsewhere in Hive

* **Workflows** — agent, condition, web search and image steps can use **Workspace default** or a
  pinned model. See [Workflow steps](/workflows/workflow-steps).
* **Agent Studio** — each agent has its own model settings, including **Hive Auto**. See
  [Build an agent](/agents/build-an-agent).

## Related

<CardGroup cols={2}>
  <Card title="AI and models" icon="microchip" href="/security/ai-and-models">
    How model requests are routed and what is sent.
  </Card>

  <Card title="Workspace settings" icon="sliders" href="/admin/workspace-settings">
    Every admin setting in one place.
  </Card>
</CardGroup>