Files
dify-docs/en/guides/application-orchestrate/multiple-llms-debugging.mdx
2025-05-29 11:21:19 +08:00

49 lines
2.1 KiB
Plaintext

---
title: Multiple Model Debugging
---
The **Chatbot** application supports the **“Debug as Multiple Models”** feature, allowing you to simultaneously compare how different models respond to the same question.
![](https://assets-docs.dify.ai/2025/02/6b77275258e6d48a540251beed0d16f3.png)
You can add up to **4** large language models at once.
![](https://assets-docs.dify.ai/2025/02/226b016ca72a7a914fe94f8b804d1334.png)
During debugging, if you find a model that performs well, click **“Debug as Single Model”** to switch to a dedicated preview window for the model.
![](https://assets-docs.dify.ai/2025/02/d273dee2ec4c04f7208a4f7a8b3a86db.png)
## FAQ
### 1. Why aren't additional models visible when adding LLMs?
Go to [“Model Providers”](/guides/model-configuration), and follow the instructions to add the keys for multiple models manually.
### 2. How to exit Multiple Model Debugging mode?
Select any model and click **“Debug with a Single Model”** to exit multiple model debugging mode.
{/*
Contributing Section
DO NOT edit this section!
It will be automatically generated by the script.
*/}
<CardGroup cols="2">
<Card
title="Edit this page"
icon="pen-to-square"
href="https://github.com/langgenius/dify-docs/edit/main/en/guides/application-orchestrate/multiple-llms-debugging.mdx"
>
Help improve our documentation by contributing directly
</Card>
<Card
title="Report an issue"
icon="github"
href="https://github.com/langgenius/dify-docs/issues/new?title=Documentation%20Issue%3A%20ple-llms-debugg&body=%23%23%20Issue%20Description%0A%3C%21--%20Please%20briefly%20describe%20the%20issue%20you%20found%20--%3E%0A%0A%23%23%20Page%20Link%0Ahttps%3A%2F%2Fgithub.com%2Flanggenius%2Fdify-docs%2Fblob%2Fmain%2Fen/guides/application-orchestrate%2Fmultiple-llms-debugging.mdx%0A%0A%23%23%20Suggested%20Changes%0A%3C%21--%20If%20you%20have%20specific%20suggestions%20for%20changes%2C%20please%20describe%20them%20here%20--%3E%0A%0A%3C%21--%20Thank%20you%20for%20helping%20improve%20our%20documentation%21%20--%3E"
>
Found an error or have suggestions? Let us know
</Card>
</CardGroup>