---
metadata:
  - name: generator
    content: Diplodoc Platform v5.63.0
alternate:
  - https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/operations/agent/api-configuration-profiles.md
  - https://vibe.sourcecraft.dev/portal/docs/ru/code-assistant/operations/agent/api-configuration-profiles.md
  - href: https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/operations/agent/api-configuration-profiles.md
    type: text/markdown
    title: Markdown version
  - href: https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/llms.txt
    rel: describedby
title: Models in SourceCraft Code Assistant
description: How to configure model configuration profiles in SourceCraft Code Assistant to work with different AI providers and LLM models.
---
> **Documentation Index:** Fetch the complete configuration index at https://vibe.sourcecraft.dev/portal/docs/en/llms.txt


# Models in SourceCraft Code Assistant

<!-- source: en/_includes/code-assistant/only-in-vscode.md -->
{% note warning %}

This feature is only available in Visual Studio Code.

{% endnote %}
<!-- endsource: en/_includes/code-assistant/only-in-vscode.md -->

_Model configuration profiles_ allow you to create and switch between different Code Assistant sets of settings.

{% note warning %}

The `default` configuration profile includes a powerful coding model by Yandex. Its use is limited by the [service plan](https://vibe.sourcecraft.dev/portal/docs/en/sourcecraft/pricing.md#ca-plans) you select.

{% endnote %}

Having multiple configuration profiles allows you to quickly switch between different AI providers, models, and settings without having to reconfigure each time you want to modify your setup.

Configuration profiles may include:
* AI providers (Yandex Cloud, OpenAI, Anthropic, OpenRouter, Glama, etc.).
* API keys and authentication data.
* Model selection (o3-mini-high, Claude 3.7 Sonnet, DeepSeek R1, etc.).
* Temperature settings to control response randomness.
* Computing budgets.
* Provider-specific settings.
* [Configuration editing via diffs](https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/operations/agent/fast-edits.md).
* Rate limit settings.

Note that available settings vary depending on your provider and model. Each provider offers different configuration options, and even within a single provider, different models may support different ranges of options or features.

{% note tip %}

View the guide on [integrating generative models into Visual Studio Code as a coding assistant](https://yandex.cloud/en/docs/tutorials/ml-ai/ai-model-ide-integration).

{% endnote %}

## Creating and managing profiles {#create-and-manage-profiles}

### Creating a profile {#create-profile}

1. In the chat's top panel, click ![image](../../../_assets/console-icons/gear.svg) **Settings**.
1. Click ![image](../../../_assets/console-icons/plus.svg) next to the **Profile** selector.
1. Enter a name for the new profile and click **Create Profile**.
1. Configure the profile settings:
    * Select an **API Provider**.
    * Enter the **API Key**.

      {% note info %}

      API keys are securely stored in VSCode Secret Storage and are never exposed in plain text.

      {% endnote %}

    * Select a **Model**.
    * Set the **Rate limit** for this profile. The default value is 0 (disabled), which is suitable for most users. If needed, you can set a minimum time (in seconds) between API requests for a specific profile to manage costs or avoid provider limits.
    * Configure the model settings, such as temperature (**Use custom temperature**).

### Switching between profiles {#switch-profiles}

You can switch between profiles in the following ways:
* In the Code Assistant settings:

  1. In the chat's top panel, click ![image](../../../_assets/console-icons/gear.svg) **Settings**.
  1. Under **Profile**, select the required profile.

* In the chat's bottom menu, open the drop-down list of model configuration profiles ![image](../../../_assets/console-icons/chevron-up.svg) and select the profile.

### Pinning and sorting profiles {#pin-profiles}

The drop-down list of model configuration profiles ![image](../../../_assets/console-icons/chevron-up.svg) supports pinning profiles for quick access:
1. Hover over any profile in the drop-down list.
1. To add the profile to your pinned list, click ![image](../../../_assets/console-icons/pin.svg).

    You can unpin the profile by clicking ![image](../../../_assets/console-icons/pin.svg) again.

Pinned profiles are displayed at the top of the drop-down list, sorted alphabetically.

Unpinned profiles are displayed below the divider, also sorted alphabetically.

### Editing and deleting profiles {#edit-profiles}

1. In the chat's top panel, click ![image](../../../_assets/console-icons/gear.svg) **Settings**.
1. Under **Profile**, select the required profile.
1. Edit your profile settings.

    To delete a profile, click ![image](../../../_assets/console-icons/trash-bin.svg) next to it.

    To rename a profile, click ![image](../../../_assets/console-icons/pencil.svg) next to it.

    {% note info %}

    You cannot delete a single profile.

    {% endnote %}

## Linking profiles to modes {#link-profiles-to-modes}

In the chat's top panel, click ![image](../../../_assets/console-icons/ellipsis.svg) and select **Modes**. You can explicitly link a specific configuration profile with a specific [mode](https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/operations/chat-prompts.md). This system also automatically memorizes which profile you last used with each mode, streamlining your workflow.

#### Useful links {#see-also}

[Quick editing (diffs) in SourceCraft Code Assistant](https://vibe.sourcecraft.dev/portal/docs/en/code-assistant/operations/agent/fast-edits.md)