From ec2503b7cb8741610cdb092629cd9493f214072c Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Wed, 4 Dec 2024 09:08:56 -0800
Subject: [PATCH] docs(azure.md): add proxy spend tracking for azure models to
 azure docs

Fixes https://github.com/BerriAI/litellm/issues/7004#issuecomment-2516644243
---
 docs/my-website/docs/providers/azure.md | 40 +++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/docs/my-website/docs/providers/azure.md b/docs/my-website/docs/providers/azure.md
index 5728f4c0624..bbcd65ac0e6 100644
--- a/docs/my-website/docs/providers/azure.md
+++ b/docs/my-website/docs/providers/azure.md
@@ -687,3 +687,43 @@ tool_calls = response.choices[0].message.tool_calls
 print("\nTool Choice:\n", tool_calls)
 ```
 
+
+### Spend Tracking for Azure OpenAI Models (PROXY)
+
+Set base model for cost tracking azure image-gen call
+
+#### Image Generation 
+
+```yaml
+model_list: 
+  - model_name: dall-e-3
+    litellm_params:
+        model: azure/dall-e-3-test
+        api_version: 2023-06-01-preview
+        api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
+        api_key: os.environ/AZURE_API_KEY
+        base_model: dall-e-3 # 👈 set dall-e-3 as base model
+    model_info:
+        mode: image_generation
+```
+
+#### Chat Completions / Embeddings
+
+**Problem**: Azure returns `gpt-4` in the response when `azure/gpt-4-1106-preview` is used. This leads to inaccurate cost tracking
+
+**Solution** ✅ :  Set `base_model` on your config so litellm uses the correct model for calculating azure cost
+
+Get the base model name from [here](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)
+
+Example config with `base_model`
+```yaml
+model_list:
+  - model_name: azure-gpt-3.5
+    litellm_params:
+      model: azure/chatgpt-v-2
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+      api_version: "2023-07-01-preview"
+    model_info:
+      base_model: azure/gpt-4-1106-preview
+```