litellm - 💡(How to fix) Fix [Bug]: Health check runs for all models with same name instead of selected model instance [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
BerriAI/litellm#25326Fetched 2026-04-09 07:52:48
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
Participants
Timeline (top)
labeled ×2
RAW_BUFFERClick to expand / collapse

Check for existing issues

  • I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

A bug happened!When multiple instances of the same model are added, LiteLLM assigns a unique ID to each instance.

However, when triggering a health check for a specific model instance, the system executes the health check for all models sharing the same model name instead of only the selected instance.

Steps to Reproduce

Steps:

  1. Add the same model multiple times (e.g., watsonX granite small or any model)
  2. Ensure each entry has a unique ID
  3. Click "health check" on one specific model instance
  4. Observe that health check runs for all models with the same name

Expected Behavior:

Health check should run only for the selected model instance (based on unique ID)

Actual Behavior:

Health check runs for all model instances sharing the same model name

Cause:

Health check logic appears to be using model name as identifier instead of unique model ID

Version

LiteLLM version: 1.81.14

Relevant log output

What part of LiteLLM is this about?

SDK (litellm Python package)

What LiteLLM version are you on ?

v1.81.14

Twitter / LinkedIn details

No response

extent analysis

TL;DR

Update the health check logic to use the unique model ID instead of the model name as the identifier.

Guidance

  • Verify that the health check function is correctly receiving the unique ID of the selected model instance.
  • Check the SDK documentation for any existing functions or methods that use the unique model ID for identification.
  • Review the code for any instances where the model name is being used as a key or identifier, and update it to use the unique ID instead.
  • Test the health check function with multiple instances of the same model to ensure it only runs for the selected instance.

Example

No code example is provided as the issue does not include any specific code snippets.

Notes

The fix may require updates to the LiteLLM SDK or the application using it, depending on where the health check logic is implemented.

Recommendation

Apply a workaround by modifying the health check logic to use the unique model ID, as updating to a fixed version is not mentioned as an option in the issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

litellm - 💡(How to fix) Fix [Bug]: Health check runs for all models with same name instead of selected model instance [1 participants]