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

# Model Guide

> Which AI models 48° offers, how to pick one, and how to set your default

48° gives you models from many AI providers in one place. You pick the model per chat, and you can switch at any time. If you're not sure which to use, start with **Auto**.

## Model families

The model selector groups models by provider:

| Provider | What to expect |
| - | - |
| **Auto** | Picks a model for each message based on how complex it is. See below. |
| **OpenAI** | GPT models, from fast mini models to the most capable reasoning models. |
| **Anthropic** | Claude models: Haiku (fast), Sonnet (balanced) and Opus (most capable). |
| **Google** | Gemini models, including fast Flash models and Pro models for complex reasoning. |
| **Mistral** | Mistral Small, Medium and Large, all hosted in the EU. |
| **Open-weight models** | Models from Z.ai, DeepSeek, Qwen, Moonshot AI and MiniMax, hosted in the EU. |

The exact list changes as providers release new models. The selector always shows what's available to you.

## Auto models

Auto models route each message to a suitable model: simple questions go to a fast, inexpensive model, complex tasks to a more capable one.

* **Auto (US)** routes between models from OpenAI and Anthropic.
* **Auto (EU)** uses only models hosted in the EU, for data residency.

## Choose a model

1. Click the model name in the chat input to open the model selector.
2. Hover over a model to see its description, **Speed**, **Cost** and capabilities: **Vision**, **File Upload**, **Thinking** and **Web Search**.
3. Click a model to select it. Your next message uses the new model.

Each model shows a flag for where it's hosted. A blue EU flag means the model is hosted in the EU and your data stays in the EU. A grey flag means your data may be processed outside the EU.

![The model picker](https://mintcdn.com/blackmountaingmbh/XFag3CE4nO-WN3UD/images/screens/en/chat/model-picker.png?fit=max\&auto=format\&n=XFag3CE4nO-WN3UD\&q=85\&s=077feb5f19485a4e39e9a5d8d3f8c3b3)

### Which model for which task

* **Everyday questions, drafts, translations:** a fast model, or **Auto**.
* **Analysis, long documents, complex reasoning:** a more capable model with **Thinking**.
* **Images and scanned documents:** a model with **Vision**.
* **Sensitive data that must stay in the EU:** a model with the blue EU flag, or **Auto (EU)**.

> [!TIP]
>
> Fast models also cost less. Use the most capable models when the task needs them.

## Thinking level

Models that support thinking reason before they answer. When you select one, the chat input shows a **Thinking Level** slider with **Auto**, **Low**, **Medium** and **High**. More thinking gives more thorough answers, but takes longer and costs more.

You can set the default thinking level in **Settings** under **Chats**.

## Set your default model

1. Open **Settings** and go to **Chats**.
2. Under **Default model**, pick a model, or **Platform default**.

New chats start with this model. You can still pick another one in any chat. Assistants and scheduled tasks have their own **Default model** setting.

## Related

> [card] [Premium models](https://docs.blackmountain.io/models/premium-models.md)
>
> The most capable models on bigger plans.

> [card] [Context window](https://docs.blackmountain.io/models/context-window.md)
>
> How much a model can take into account.

> [card] [Chat settings](https://docs.blackmountain.io/account/chat-settings.md)
>
> Your default model and thinking level.

> [card] [Data residency](https://docs.blackmountain.io/admin/security/data-residency.md)
>
> Where your data is processed.


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