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

# Harness and models: complete guide to the model picker

> Choose a Harness, model, and reasoning effort in the composer. The Harness is fixed after a session starts while the model can still change, plus the Ultra level and Ultracode toggle.

A **Harness** is the framework that runs the Agent, for example Claude Code or Codex CLI. A **model** is the large language model the Harness calls. Each time you create a session, you choose a Harness and a model in the model button at the bottom right of the composer, and adjust the reasoning effort if needed. For where models come from and where usage is counted, see [Model sources](https://docs.aihubmix.com/en/cloud/models/model-sources.md).

## Availability

| Platform | Support | Notes |
| - | - | - |
| Desktop app | Supported | This page describes the desktop app. |
| Web app | Supported | Same as the desktop app. The web app on Windows has no **Open effort menu** shortcut. |
| Mobile web | Supported | Same popover, narrowed to fit the screen. |

## Entry points

* **Model button** (bottom right of the composer): shows the Harness, the model vendor icon, and the model name. Small text after the model name shows the source: **Subscription** for your subscriptions, **BYOK** for an API key you added, and nothing for models included with Plus.
* **Effort button** (next to the model button): shows the current level, for example **Medium** or **High · Ultracode**. It is hidden when the model does not support adjusting effort.
* **Context usage ring** (in a session, to the left of the model button). See [Context usage ring](#context-usage).
* For shortcuts, see [Keyboard shortcuts](#keyboard).
* When plan limits are reached or an account is disconnected, **Use another model** in the dialog also opens the model picker. See [Plan limits reached](https://docs.aihubmix.com/en/cloud/models/model-sources.md#subscription-limit-reached).

## Model picker

The top part of the model picker is the **Harness** list (the selected one has a check mark), and the bottom part is **Model**, with two tabs, **Subscriptions** and **BYOK**. Models included with Plus and your own API keys are both in the BYOK tab.

| Situation | What you see / what to do |
| - | - |
| Opening the picker | Opens on the tab of the current model. Switching tabs only changes the list; a change takes effect only when you click a model. |
| **Default model** at the top of the list | Selects this tab's default model (usually the recommended model). |
| Subscriptions tab | One group per subscription account. The group title is the account name, with the plan in small text on the right. |
| BYOK tab | The first group is Plus models (with the AIHubMix icon). See [Plus models](https://docs.aihubmix.com/en/cloud/models/model-sources.md#plus-models). The rest are grouped by provider, and when one provider has several keys they are split by key name. Hover a group title and click the pencil icon to edit that group. |
| No content under a source yet | The list area shows only a **Connect subscription** or **Add API key** button. Click it to add in place; you return here when done. |
| Subscriptions connected but no models available | The top reads **Subscription connected, but no models are available right now**, with a reason under each account group (for example, the current Harness does not support that subscription). |
| A group is incompatible with the current Harness | The group moves to the end with the reason (for example **Claude Code only** or **API format not compatible with Claude Code**), and its models are grayed out. In a new session, clicking one switches to a compatible Harness and selects the model; in a session, they cannot be clicked. |
| No Plus plan | The Plus models group is grayed out, with a **Get Plus** button. See [Without Plus](#without-plus). |
| A model cannot be used | The model is grayed out, with a short reason at the end of the row (for example **No Responses API**). Hover to see the full description. |
| Clicking a model | The popover closes and the model button updates. For how effort changes, see [How effort changes after switching models](#effort-after-switch). |

## Supported Harnesses

The Harness list follows what the product shows. It currently includes Claude Code (the default Harness for new sessions, and the only one that supports Ultracode), Codex CLI (some models have an Ultra level), OpenCode, Hermes Agent, DeepSeek, and Pi.

Whether you can add a message during a run or edit a sent message depends on the Harness. See [Composer](https://docs.aihubmix.com/en/cloud/sessions/composer.md).

## Harness and model source combinations

The model picker lets you choose only models the current Harness can use. Other groups are grayed out with a reason.

* **Plus models**: available models vary by Harness.
* **Your subscriptions**: each subscription maps to a specific Agent, for example Claude subscriptions are for Claude Code only and ChatGPT subscriptions are for Codex CLI. See [Supported subscriptions](https://docs.aihubmix.com/en/cloud/models/model-sources.md#supported-subscriptions).
* **Your keys**: Claude Code needs an **Anthropic compatible** API, and Codex CLI needs an **OpenAI compatible** API. See [API format and Harness](https://docs.aihubmix.com/en/cloud/models/model-sources.md#api-format-harness).

## Choose a Harness and model

1. On the new session page, click the model button at the bottom right of the composer.
2. Click a Harness. After you change the Harness, the model returns to **Default model**.
3. Switch to the **Subscriptions** or **BYOK** tab and click a model.
4. If needed, click the effort button to adjust reasoning effort.
5. Enter your message and send it. The session starts with this combination.

## Default selection

* New sessions reuse the choice from the last session you created (Harness, model, source, and the reasoning effort you actively selected). The first time, it is Claude Code + **Default model**.
* If you never actively selected an effort, the effort button shows the model's recommended level.
* If the remembered model or source is no longer available, it returns to **Default model**.
* Ultracode is off by default in new sessions.
* Switching models in a session affects only that session and does not change the defaults for new sessions.
* With several subscription accounts from the same provider, the account marked **Default** is used. See [Default account](https://docs.aihubmix.com/en/cloud/models/model-sources.md#default-account).

## Harness is fixed after the session starts

After the first message in a session is sent, the Harness cannot be changed. You can still change the model, source, and reasoning effort, and changes take effect from the next turn.

* The Harness area of the model picker shows only the current Harness and a lock. Hover to see **This task’s harness is fixed. Start a new task to use another**.
* When the session belongs to a project, you can click **New task with another harness ›** to create a new session in that project with another Harness.

### Switch models in a session

1. In the session, click the model button and click another model (you can switch across sources).
2. If the current context fits in the new model, the switch happens directly and a **Switched to model name** row is left in the session. If it does not fit, you are asked to confirm compaction first. See [Compact and switch](#compact-and-switch).
3. All earlier session history is kept and the new model continues from it.

* You cannot switch while the turn is running. It shows **The task is running. Switch models after this turn ends**.
* If the switch fails, the reason is shown. You can try another source or model, or retry.
* If the session is paused because plan limits were reached or an account was disconnected, it continues automatically after you switch models or accounts.

### Compact and switch

When the current context does not fit in the target model, a **Switch to model name?** confirmation appears in the popover: the chat is compacted into a summary first, then the new model picks it up, and earlier details may be lost. When the effort will change, it also shows **Effort after switching: X**.

* **Cancel**: returns to the model list and keeps the current model.
* **Compact and switch**: compacts and switches to the new model, and leaves a **Compacted the chat and switched to model name** row in the session.
* If the session is too long to compact, it shows **This chat is too long to compact. Try starting a new session**.

### Context usage ring

In a session, the small ring to the left of the model button shows the current context usage. Hover to see the percentage used and the token count. Near the limit, the ring changes color and the session is compacted automatically.

## Reasoning effort

Reasoning effort determines how long the model thinks before answering: higher levels give more thorough answers but are slower and use more. Which levels each model has and which one is recommended depend on the "model + source + Harness" combination, as shown in the product. You can also change it in a session, and changes take effect from the next turn.

### Two styles

| Current model | Style | Entry name |
| - | - | - |
| Claude models, or other models + Claude Code | Level list | Effort |
| GPT models, or other models + other Harnesses | Slider | Effort |

### Level names

| Level list | Slider | Good for |
| - | - | - |
| None | Minimal | Small edits, fastest replies |
| Low | Low (**Light** for GPT models) | Simple, direct changes |
| Medium | Medium | Most tasks |
| High | High | Complex changes |
| Extra | Extra high | Cross-file refactors and tricky bugs |
| Max | Not offered | The hardest tasks; may use a lot of tokens and respond slowly, so use sparingly |
| Not offered | Ultra (Codex CLI only) | Parallel subagents; uses limits faster |

* **Effort level list**: lists only the levels the current model supports. The recommended level is marked **Recommended**. Click a level to apply it. The [Ultracode toggle](#ultracode) is below the list.
* **Effort slider**: drag or click to choose a level. The line below describes what the current level is for. **Reset to default** resets to the recommended level.

### Ultra level

Some models offer an Ultra level in Codex CLI, at the right end of the slider. Selecting it opens a **Turn on Ultra reasoning?** confirmation, which notes that usage is about 2–3× that of **Extra high** and each task takes longer.

* Click **Turn on Ultra** to apply it. Click **Cancel** to keep the original level.
* In a session, you can check **Don’t ask again this session**.

### Ultracode toggle

Ultracode is Claude Code's multi-agent parallel feature, which splits a task into multiple subtasks and completes them in parallel. Usage goes up noticeably. It is a separate toggle below the Effort level list and does not change the Effort level. When it is on, the effort button shows something like **High · Ultracode**. In a session, it takes effect from the next turn.

* Whether it can be turned on depends on the Harness, cloud server, model, and source: it needs Claude Code, a ready cloud server, and a selected model that supports **Extra high**.
* When the conditions are not met, the toggle is grayed out with the reason. In a new session, if changing the model or source means the conditions are no longer met, the toggle turns off automatically.

### How effort changes after switching models

| Situation | Result |
| - | - |
| The level you selected also exists in the new model | It stays the same. |
| The new model does not have this level | It returns to the new model's recommended level. |
| The new model does not support adjusting effort | The effort button is hidden. |
| Switching models in a session | The confirmation shows **Effort after switching: X**. |

## Keyboard shortcuts

| Action | macOS | Windows |
| - | - | - |
| Open or close the model picker | `⌃⇧M` | `Ctrl+Shift+M` |
| Open or close the effort menu | `⌃⇧I` | `Ctrl+Shift+I` (not available in the web app, taken by the browser) |
| Switch between the **Subscriptions** and **BYOK** tabs | `Tab` | `Tab` |
| Select items 1 to 9 in the menu | `1`–`9` | `1`–`9` |
| Move in the Effort list | `↑` `↓` | `↑` `↓` |
| Adjust the effort slider | `←` `→` `↑` `↓` `Home` `End` | Same |
| Close the menu | `Esc` | `Esc` |

## Without Plus

* The model picker opens as usual. In the BYOK tab, the Plus models group is grayed out and shows **Subscribe to Plus to use these models**. Click **Get Plus** to open the Plus subscription dialog.
* On the new session page, the message you send is held and an upgrade card is shown. After you subscribe, it is sent automatically. See [Without Plus](https://docs.aihubmix.com/en/cloud/plus/without-plus.md).

## Notes and limitations

* To change the Harness, create a new session.
* Compaction loses earlier details. If you do not want to compact, click **Cancel**, or choose a model with a larger context limit.
* In a new session, clicking a model in an incompatible group switches the Harness automatically. Watch for the notice.
* The model list, levels, and recommended levels may change. Follow what the product shows.

## Related

* [Model sources: Plus models, your subscriptions, and BYOK](https://docs.aihubmix.com/en/cloud/models/model-sources.md)
* [Model FAQ](https://docs.aihubmix.com/en/cloud/models/model-faq.md)
* [Composer](https://docs.aihubmix.com/en/cloud/sessions/composer.md)
* [Without Plus](https://docs.aihubmix.com/en/cloud/plus/without-plus.md)
* [Glossary](https://docs.aihubmix.com/en/cloud/concepts/glossary.md)


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