### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

**Description** When trying to integrate local LLMs into Android Studio (2025.2.3) and Xcode (26.2) using the /v1/models endpoint, the models fail to appear in the IDE model list when routed through LiteLLM.

However, when connecting directly to vLLM, the models are correctly identified. After investigation, we noticed a significant difference in the created timestamp and the structure of the response.

LiteLLM returns a very old/static timestamp (1677610602), whereas vLLM and other providers return a current Unix timestamp. It appears that modern IDEs might be filtering or rejecting models with older timestamps or missing detailed permission fields.

**Comparison of Responses**

1. LiteLLM Response (Issue)

Note: The created value is outdated and some metadata is missing compared to vLLM. ``` { "data": [ { "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "object": "model", "created": 1677610602, "owned_by": "openai" } ], "object": "list" }

```

2. vLLM Response (Working) N…