diff --git a/docs/my-website/docs/anthropic_unified.md b/docs/my-website/docs/anthropic_unified.md
index d4660bf070..03ba8a6884 100644
--- a/docs/my-website/docs/anthropic_unified.md
+++ b/docs/my-website/docs/anthropic_unified.md
@@ -1,7 +1,7 @@
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# /v1/messages [BETA] 
+# /v1/messages
 
 Use LiteLLM to call all your LLM APIs in the Anthropic `v1/messages` format. 
 
diff --git a/docs/my-website/docs/audio_transcription.md b/docs/my-website/docs/audio_transcription.md
index 22517f68e4..8cbc567180 100644
--- a/docs/my-website/docs/audio_transcription.md
+++ b/docs/my-website/docs/audio_transcription.md
@@ -3,13 +3,22 @@ import TabItem from '@theme/TabItem';
 
 # /audio/transcriptions
 
-Use this to loadbalance across Azure + OpenAI. 
+## Overview 
+
+| Feature | Supported | Notes | 
+|-------|-------|-------|
+| Cost Tracking | ✅ |  |
+| Logging | ✅ | works across all integrations |
+| End-user Tracking | ✅ | |
+| Fallbacks | ✅ | between supported models |
+| Loadbalancing | ✅ | between supported models |
+| Support llm providers | `openai`, `azure`, `vertex_ai`, `gemini`, `deepgram`, `groq`, `fireworks_ai` | |
 
 ## Quick Start
 
 ### LiteLLM Python SDK
 
-```python showLineNumbers
+```python showLineNumbers title="Python SDK Example"
 from litellm import transcription
 import os 
 
@@ -30,7 +39,7 @@ print(f"response: {response}")
 <Tabs>
 <TabItem value="openai" label="OpenAI">
 
-```yaml showLineNumbers
+```yaml showLineNumbers title="OpenAI Configuration"
 model_list:
 - model_name: whisper
   litellm_params:
@@ -45,7 +54,7 @@ general_settings:
 </TabItem>
 <TabItem value="openai+azure" label="OpenAI + Azure">
 
-```yaml showLineNumbers
+```yaml showLineNumbers title="OpenAI + Azure Configuration"
 model_list:
 - model_name: whisper
   litellm_params:
@@ -71,7 +80,7 @@ general_settings:
 
 ### Start proxy 
 
-```bash
+```bash showLineNumbers title="Start Proxy Server"
 litellm --config /path/to/config.yaml 
 
 # RUNNING on http://0.0.0.0:8000
@@ -82,7 +91,7 @@ litellm --config /path/to/config.yaml
 <Tabs>
 <TabItem value="curl" label="Curl">
 
-```bash
+```bash showLineNumbers title="Test with cURL"
 curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
 --header 'Authorization: Bearer sk-1234' \
 --form 'file=@"/Users/krrishdholakia/Downloads/gettysburg.wav"' \
@@ -92,7 +101,7 @@ curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
 </TabItem>
 <TabItem value="openai" label="OpenAI Python SDK">
 
-```python showLineNumbers
+```python showLineNumbers title="Test with OpenAI Python SDK"
 from openai import OpenAI
 client = openai.OpenAI(
     api_key="sk-1234",
@@ -115,4 +124,82 @@ transcript = client.audio.transcriptions.create(
 - Azure
 - [Fireworks AI](./providers/fireworks_ai.md#audio-transcription)
 - [Groq](./providers/groq.md#speech-to-text---whisper)
-- [Deepgram](./providers/deepgram.md)
\ No newline at end of file
+- [Deepgram](./providers/deepgram.md)
+
+---
+
+## Fallbacks
+
+You can configure fallbacks for audio transcription to automatically retry with different models if the primary model fails.
+
+<Tabs>
+<TabItem value="curl" label="Curl">
+
+```bash showLineNumbers title="Test with cURL and Fallbacks"
+curl --location 'http://0.0.0.0:4000/v1/audio/transcriptions' \
+--header 'Authorization: Bearer sk-1234' \
+--form 'file=@"gettysburg.wav"' \
+--form 'model="groq/whisper-large-v3"' \
+--form 'fallbacks[]="openai/whisper-1"'
+```
+
+</TabItem>
+<TabItem value="openai" label="OpenAI Python SDK">
+
+```python showLineNumbers title="Test with OpenAI Python SDK and Fallbacks"
+from openai import OpenAI
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+audio_file = open("gettysburg.wav", "rb")
+transcript = client.audio.transcriptions.create(
+    model="groq/whisper-large-v3",
+    file=audio_file,
+    extra_body={
+        "fallbacks": ["openai/whisper-1"]
+    }
+)
+```
+</TabItem>
+</Tabs>
+
+### Testing Fallbacks
+
+You can test your fallback configuration using `mock_testing_fallbacks=true` to simulate failures:
+
+<Tabs>
+<TabItem value="curl" label="Curl">
+
+```bash showLineNumbers title="Test Fallbacks with Mock Testing"
+curl --location 'http://0.0.0.0:4000/v1/audio/transcriptions' \
+--header 'Authorization: Bearer sk-1234' \
+--form 'file=@"gettysburg.wav"' \
+--form 'model="groq/whisper-large-v3"' \
+--form 'fallbacks[]="openai/whisper-1"' \
+--form 'mock_testing_fallbacks=true'
+```
+
+</TabItem>
+<TabItem value="openai" label="OpenAI Python SDK">
+
+```python showLineNumbers title="Test Fallbacks with Mock Testing"
+from openai import OpenAI
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+audio_file = open("gettysburg.wav", "rb")
+transcript = client.audio.transcriptions.create(
+    model="groq/whisper-large-v3",
+    file=audio_file,
+    extra_body={
+        "fallbacks": ["openai/whisper-1"],
+        "mock_testing_fallbacks": True
+    }
+)
+```
+</TabItem>
+</Tabs>
\ No newline at end of file
diff --git a/litellm/proxy/proxy_config.yaml b/litellm/proxy/proxy_config.yaml
index 498cf4dcf7..13724177c0 100644
--- a/litellm/proxy/proxy_config.yaml
+++ b/litellm/proxy/proxy_config.yaml
@@ -1,19 +1,9 @@
 model_list:
-  - model_name: anthropic/*
+  - model_name: groq/*
     litellm_params:
-      model: anthropic/*
+      model: groq/*
+      api_key: bad
   - model_name: openai/*
     litellm_params:
       model: openai/*
 
-router_settings:
-  model_group_alias: {
-    "gemini-2.5-pro": "anthropic/claude-sonnet-4-20250514",
-    "gemini-2.5-flash": "anthropic/claude-sonnet-4-20250514",
-    # "gemini-2.5-pro": "openai/gpt-4o-mini"
-  }
-
-mcp_servers:
-  deepwiki_mcp:
-    url: "https://mcp.deepwiki.com/mcp"
-    transport: "http"