fix(vertex_ai): improve passthrough endpoint url parsing and construction (#17402)

[krisxia0506]

Title

fix(vertex_ai): improve passthrough endpoint url parsing and construction

Relevant issues

Fixes #17402

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory,
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🐛 Bug Fix

Changes

1. litellm/llms/vertex_ai/common_utils.py:

   • Added get_vertex_model_id_from_url helper function to extract the model ID from Vertex AI URLs.
   • Updated construct_target_url to correctly handle and strip /v1/ and /v1beta1/ version prefixes from the requested route to prevent double versioning in the target URL.

2. litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:

   • Updated _base_vertex_proxy_route to improve project and location resolution. If vertex_project or vertex_location cannot be parsed from the URL, it now attempts to extract the model ID and look up the corresponding deployment in the llm_router to find the configured vertex_project and vertex_location.

3. tests/test_litellm/llms/vertex_ai/test_vertex_ai_common_utils.py:

   • Added unit tests for get_vertex_model_id_from_url covering valid and invalid URLs.
   • Added unit tests for construct_target_url verifying correct handling of /v1/ and /v1beta1/ prefixes.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Ready	Preview	Comment	Dec 5, 2025 6:29am