Skip to main content

Open WebUI with LiteLLM

This guide walks you through connecting Open WebUI to LiteLLM. Using LiteLLM with Open WebUI allows teams to

  • Access 100+ LLMs on Open WebUI
  • Track Spend / Usage, Set Budget Limits
  • Send Request/Response Logs to logging destinations like langfuse, s3, gcs buckets, etc.
  • Set access controls eg. Control what models Open WebUI can access.

Quickstart​

1. Start LiteLLM & Open WebUI​

2. Create a Virtual Key on LiteLLM​

Virtual Keys are API Keys that allow you to authenticate to LiteLLM Proxy. We will create a Virtual Key that will allow Open WebUI to access LiteLLM.

2.1 LiteLLM User Management Hierarchy​

On LiteLLM, you can create Organizations, Teams, Users and Virtual Keys. For this tutorial, we will create a Team and a Virtual Key.

  • Organization - An Organization is a group of Teams. (US Engineering, EU Developer Tools)
  • Team - A Team is a group of Users. (Open WebUI Team, Data Science Team, etc.)
  • User - A User is an individual user (employee, developer, eg. krrish@litellm.ai)
  • Virtual Key - A Virtual Key is an API Key that allows you to authenticate to LiteLLM Proxy. A Virtual Key is associated with a User or Team.

Once the Team is created, you can invite Users to the Team. You can read more about LiteLLM's User Management here.

2.2 Create a Team on LiteLLM​

Navigate to http://localhost:4000/ui and create a new team.

2.2 Create a Virtual Key on LiteLLM​

Navigate to http://localhost:4000/ui and create a new virtual Key.

LiteLLM allows you to specify what models are available on Open WebUI (by specifying the models the key will have access to).

3. Connect Open WebUI to LiteLLM​

On Open WebUI, navigate to Settings -> Connections and create a new connection to LiteLLM

Enter the following details:

  • URL: http://localhost:4000 (your litellm proxy base url)
  • Key: your-virtual-key (the key you created in the previous step)

3.1 Test Request​

On the top left corner, select models you should only see the models you gave the key access to in Step 2.

Once you selected a model, enter your message content and click on Submit

3.2 Tracking Usage & Spend​

Basic Tracking​

After making requests, navigate to the Logs section in the LiteLLM UI to view Model, Usage and Cost information.

Per-User Tracking​

To track spend and usage for each Open WebUI user, configure both Open WebUI and LiteLLM:

  1. Enable User Info Headers in Open WebUI

    Set the following environment variable for Open WebUI to enable user information in request headers:

    ENABLE_FORWARD_USER_INFO_HEADERS=True

    For more details, see the Environment Variable Configuration Guide.

  2. Configure LiteLLM to Parse User Headers

    Add the following to your LiteLLM config.yaml to specify a header to use for user tracking:

    general_settings:
        user_header_name: X-OpenWebUI-User-Id

    ⓘ Available tracking options

    You can use any of the following headers for user_header_name:

  • X-OpenWebUI-User-Id

  • X-OpenWebUI-User-Email

  • X-OpenWebUI-User-Name

    These may offer better readability and easier mental attribution when hosting for a small group of users that you know well.

    Choose based on your needs, but note that in Open WebUI:

  • Users can modify their own usernames

  • Administrators can modify both usernames and emails of any account

Render thinking content on Open WebUI​

Open WebUI requires reasoning/thinking content to be rendered with <think></think> tags. In order to render this for specific models, you can use the merge_reasoning_content_in_choices litellm parameter.

Example litellm config.yaml:

model_list:
  - model_name: thinking-anthropic-claude-3-7-sonnet
    litellm_params:
      model: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
      thinking: {"type": "enabled", "budget_tokens": 1024}
      max_tokens: 1080
      merge_reasoning_content_in_choices: true

Test it on Open WebUI​

On the models dropdown select thinking-anthropic-claude-3-7-sonnet

Additional Resources​