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