Skip to main content

Multi-Model Chats

Open WebUI allows you to interact with multiple models simultaneously within a single chat interface. This powerful feature enables you to compare responses, verify facts, and leverage the unique strengths of different LLMs side-by-side.

Overview​

In a Multi-Model Chat, your prompt is sent to two or more selected models at the same time. Their responses are displayed in parallel columns (or stacked, depending on screen size), giving you immediate insight into how different AI architectures approach the same problem.

How to Use​

  1. Enable Compare Mode: In the model picker, click the Compare button, shown beside the search field.
  2. Select Models: With comparison mode enabled, select the models you want to talk to simultaneously and compare.
    • Example Setup: Select GPT-5.6 Sol (for reasoning), Gemini 3.6 Flash (for creative writing), and Claude Sonnet 5 (for overall performance).
  3. Send Prompt: Type your question as usual.
  4. View Results: Watch as all models generate their responses simultaneously in the chat window.

Usage Scenarios​

  • Model Comparison/Benchmarking: Test which model writes better Python code or which one hallucinates less on niche topics.
  • Fact Validation: "Cross-examine" models. If two models say X and one says Y, you can investigate further.
  • Diverse Perspectives: Get a "Creative" take from one model and a "Technical" take from another for the same query.

Permissions​

Admins can control access to Multi-Model Chats on a per-role or per-group basis.

  • Location: Admin Panel > Users > Groups > Default permissions > Permissions > Allow Multiple Models in Chat. To set a group-specific value, edit the group and open its Permissions tab.
  • Environment Variable: USER_PERMISSIONS_CHAT_MULTIPLE_MODELS (Default: True)

If disabled, users will not see the Compare button in the model picker and cannot initiate multi-model sessions.

Merging Responses (Mixture of Agents)​

Once you have responses from multiple models, Open WebUI offers an advanced capability to Merge them into a single, superior answer. This implements a Mixture of Agents (MOA) workflow.

What is Merging?​

Merging takes the outputs from all your active models and sends them (along with your original prompt) to a "Synthesizer Model." This Synthesizer Model reads all the draft answers and combines them into one final, polished response.

How to Merge​

  1. Start a Multi-Model Chat and get responses from your selected models.
  2. Click the branch-shaped icon below the responses, at the right, whose tooltip reads Merge Responses. It only appears on the last exchange in the chat, and only once every model has finished.
  3. Open WebUI adds a Merged Response below the individual answers, aggregating the best parts of the previous outputs.

The merged answer is stored with the chat, so it is still there when you come back to the conversation. Merging works the same on a conversation you have reopened as on one you have only just generated, so you can leave a comparison sitting for days and merge it whenever you return to it.

Advantages of Merging​

  • Higher Accuracy: Research suggests that aggregating outputs from multiple models often outperforms any single model acting alone.
  • Best of Both Worlds: You might get the code accuracy of Model A combined with the clear explanations of Model B.
  • Reduced Hallucinations: The synthesizer model can filter out inconsistencies found in individual responses.

Configuration​

There is nothing to configure, and that is worth knowing before you go looking:

  • Model: the merge runs on one of the models already in the comparison, the one whose response you are viewing when you press Merge. It does not use the Task Model, so the settings under Settings > Admin > Interface have no effect on it.
  • Prompt Template: the merge uses a built-in prompt telling the model how to synthesize the answers. There is no admin field or environment variable for it.
Experimental

The Merging/MOA feature is an advanced capability. The result is only as good as the model doing the synthesizing, so run the merge from your strongest model's response rather than a small one.

This content is for informational purposes only and does not constitute a warranty, guarantee, or contractual commitment. Open WebUI is provided "as is." See your license for applicable terms.