From 68f2ec308a7e5e9bffd2e03e226c5b727851da94 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Fri, 10 Apr 2026 19:40:38 +0530 Subject: [PATCH] docs(proxy): clarify x-litellm-model-group vs provider model id Made-with: Cursor --- docs/my-website/docs/proxy/response_headers.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/my-website/docs/proxy/response_headers.md b/docs/my-website/docs/proxy/response_headers.md index fa1ab9c4301..0a842778ee1 100644 --- a/docs/my-website/docs/proxy/response_headers.md +++ b/docs/my-website/docs/proxy/response_headers.md @@ -55,7 +55,9 @@ These headers are useful for clients to understand the current rate limit status | `x-litellm-model-id` | string | Unique identifier for the model used | | | `x-litellm-model-api-base` | string | Base URL of the API endpoint | ✅ | | `x-litellm-version` | string | Version of LiteLLM being used | | -| `x-litellm-model-group` | string | Model group identifier | | +| `x-litellm-model-group` | string | Routed **`model_name`** from `model_list` (client-visible alias) | | + +This header names the **model group** LiteLLM selected: the **`model_name`** entry in your proxy `model_list`—the same value clients send as `model`. It does **not** mirror **`litellm_params.model`** (the actual provider model id LiteLLM forwards upstream). Use **`x-litellm-model-id`** when you need the deployment identifier. ## Response headers from LLM providers