[GH-ISSUE #5421] [BUG]: Integration with LM Studio is faulty #5079

Closed
opened 2026-06-05 14:51:53 -04:00 by yindo · 1 comment
Owner

Originally created by @michalpelszyk on GitHub (Apr 13, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5421

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Fresh Windows 11 24H2.
Initial setup.
AnythingLLM discovers LM studio, selects a model.

The auto-detected API is endpoint is http://127.0.0.1:1234/v1. LM Studio says this is the OpenAI-compatible endpoint.
The LM Studio exposes their own APIs at /api/v1 right now 0.4.11 (build 1).

Are there known steps to reproduce?

Install current LM Studio: 0.4.11 (build 1)
Start a server with any (even built-in embedding model).
Install Anything LLM app.
Perform initial setup.

LLM Provider & Model (if applicable)

LM Studio, any model.

Embedder Provider & Model (if applicable)

No response

Originally created by @michalpelszyk on GitHub (Apr 13, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5421 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? Fresh Windows 11 24H2. Initial setup. AnythingLLM discovers LM studio, selects a model. The auto-detected API is endpoint is `http://127.0.0.1:1234/v1`. LM Studio says this is the OpenAI-compatible endpoint. The LM Studio exposes their own APIs at `/api/v1` right now 0.4.11 (build 1). ### Are there known steps to reproduce? Install current LM Studio: 0.4.11 (build 1) Start a server with any (even built-in embedding model). Install Anything LLM app. Perform initial setup. ### LLM Provider & Model (if applicable) LM Studio, any model. ### Embedder Provider & Model (if applicable) _No response_
yindo added the possible bug label 2026-06-05 14:51:53 -04:00
yindo closed this issue 2026-06-05 14:51:53 -04:00
Author
Owner

@timothycarambat commented on GitHub (Apr 13, 2026):

Not sure what the bug is here. We want the OpenAI compatible endpoints. Not the LMStudio one.

<!-- gh-comment-id:4238175439 --> @timothycarambat commented on GitHub (Apr 13, 2026): Not sure what the bug is here. We _want_ the OpenAI compatible endpoints. Not the LMStudio one.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5079