8 views
-/https://github.com/berriai/litellm/issues/14052
GitHub · issue

#14052 [Bug]: x-litellm-tags not routing requests to correct model

  • State: open
  • Author: @TeddyAmkie
  • Labels: bug, enterprise, P0, blocking use cases

### What happened?

Expected Behavior Requests should fallback to similar x-litellm-tags if the one provided fails

Environment • LiteLLM image: main-latest • Platform: macOS (Apple Silicon) • Running via Docker

Notes • Consider fallback priority (tag -> model_name -> fallbacks[]) ? * Document fallback priority

---

**Steps to Reproduce**

Config.yaml `model_list: - model_name: gpt-4.1 litellm_params: model: providerA/gpt-4.1 api_key: os.environ/PROVIDER_A_KEY # BAD API_KEY tags: ["provider-a"]

- model_name: othergpt-4.1 # Utilizing the same model_name will default fallback to similar model_name litellm_params: model: providerB/gpt-4.1 api_base: os.environ/PROVIDER_B_BASE api_key: os.environ/PROVIDER_B_KEY api_version: "2024-08-01-preview" tags: ["provider-a"]

router_settings: enable_tag_filtering: true`

1. Run latest LiteLLM container: ``` ```bash docker run -v ${pwd}/config.yaml:/app/config.yaml \ -e PROVIDER_A_KEY=$PROVIDER_A_KEY \ -e PROVIDER_B_KEY=$PROVIDER_B_KEY \ -e PROVIDER_B_BASE=https://<your-endpoint>.example.com \ -p 4000:4000 \ ghcr.io/berriai/litellm:main-lat…

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (1 events)
#0 of 0 · 31d17h40m36s ago — entered · #import:https:::github.com:berriai:litellm post #3216
#14052 requires changes to core routing and fallback semantics, with compatibility considerations, priority rules, and broad regression testing. #35358 appears more localized to a background reconciliation and accounting path with focused persistence and callback tests.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search