[Docs] v1.67.4-stable

docs/my-website/docs/audio_transcription.md

@@ -1,13 +1,15 @@
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# Speech to Text
+# /audio/transcriptions
 
 Use this to loadbalance across Azure + OpenAI. 
 
 ## Quick Start
 
-```python
+### LiteLLM Python SDK
+
+```python showLineNumbers
 from litellm import transcription
 import os 
 
@@ -20,15 +22,15 @@ response = transcription(model="whisper", file=audio_file)
 print(f"response: {response}")
 ```
 
-## Proxy Usage
+### LiteLLM Proxy
 
 ### Add model to config 
 
 
 <Tabs>
 <TabItem value="openai" label="OpenAI">
 
-```yaml
+```yaml showLineNumbers
 model_list:
 - model_name: whisper
   litellm_params:
@@ -43,7 +45,7 @@ general_settings:
 </TabItem>
 <TabItem value="openai+azure" label="OpenAI + Azure">
 
-```yaml
+```yaml showLineNumbers
 model_list:
 - model_name: whisper
   litellm_params:
@@ -88,9 +90,9 @@ curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
 ```
 
 </TabItem>
-<TabItem value="openai" label="OpenAI">
+<TabItem value="openai" label="OpenAI Python SDK">
 
-```python
+```python showLineNumbers
 from openai import OpenAI
 client = openai.OpenAI(
     api_key="sk-1234",

docs/my-website/docs/image_generation.md

@@ -1,8 +1,15 @@
-# Images
+
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Image Generations
 
 ## Quick Start
 
-```python
+### LiteLLM Python SDK
+
+```python showLineNumbers
 from litellm import image_generation
 import os 
 
@@ -14,24 +21,23 @@ response = image_generation(prompt="A cute baby sea otter", model="dall-e-3")
 print(f"response: {response}")
 ```
 
-## Proxy Usage
+### LiteLLM Proxy
 
 ### Setup config.yaml 
 
-```yaml
+```yaml showLineNumbers
 model_list:
   - model_name: gpt-image-1 ### RECEIVED MODEL NAME ###
     litellm_params: # all params accepted by litellm.image_generation()
       model: azure/gpt-image-1 ### MODEL NAME sent to `litellm.image_generation()` ###
       api_base: https://my-endpoint-europe-berri-992.openai.azure.com/
       api_key: "os.environ/AZURE_API_KEY_EU" # does os.getenv("AZURE_API_KEY_EU")
-      rpm: 6      # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm)
 
 ```
 
 ### Start proxy 
 
-```bash
+```bash showLineNumbers
 litellm --config /path/to/config.yaml 
 
 # RUNNING on http://0.0.0.0:4000
@@ -57,7 +63,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/images/generations' \
 </TabItem>
 <TabItem value="openai" label="OpenAI">
 
-```python
+```python showLineNumbers
 from openai import OpenAI
 client = openai.OpenAI(
     api_key="sk-1234",

docs/my-website/docs/providers/cohere.md

@@ -13,7 +13,9 @@ os.environ["COHERE_API_KEY"] = ""
 
 ## Usage
 
-```python
+### LiteLLM Python SDK
+
+```python showLineNumbers
 from litellm import completion
 
 ## set ENV variables
@@ -26,9 +28,9 @@ response = completion(
 )
 ```
 
-## Usage - Streaming
+#### Streaming
 
-```python
+```python showLineNumbers
 from litellm import completion
 
 ## set ENV variables
@@ -46,15 +48,90 @@ for chunk in response:
 ```
 
 
+
+## Usage with LiteLLM Proxy 
+
+Here's how to call Cohere with the LiteLLM Proxy Server
+
+### 1. Save key in your environment
+
+```bash
+export COHERE_API_KEY="your-api-key"
+```
+
+### 2. Start the proxy 
+
+Define the cohere models you want to use in the config.yaml
+
+```yaml showLineNumbers
+model_list:
+  - model_name: command-a-03-2025 
+    litellm_params:
+      model: command-a-03-2025
+      api_key: "os.environ/COHERE_API_KEY"
+```
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+
+### 3. Test it
+
+
+<Tabs>
+<TabItem value="Curl" label="Curl Request">
+
+```shell showLineNumbers
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer <your-litellm-api-key>' \
+--data ' {
+      "model": "command-a-03-2025",
+      "messages": [
+        {
+          "role": "user",
+          "content": "what llm are you"
+        }
+      ]
+    }
+'
+```
+</TabItem>
+<TabItem value="openai" label="OpenAI v1.0.0+">
+
+```python showLineNumbers
+import openai
+client = openai.OpenAI(
+    api_key="anything",
+    base_url="http://0.0.0.0:4000"
+)
+
+# request sent to model set on litellm proxy
+response = client.chat.completions.create(model="command-a-03-2025", messages = [
+    {
+        "role": "user",
+        "content": "this is a test request, write a short poem"
+    }
+])
+
+print(response)
+
+```
+</TabItem>
+</Tabs>
+
+
 ## Supported Models
 | Model Name | Function Call |
 |------------|----------------|
-| command-r-plus-08-2024 | `completion('command-r-plus-08-2024', messages)` |  
-| command-r-08-2024 | `completion('command-r-08-2024', messages)` |
-| command-r-plus | `completion('command-r-plus', messages)` |  
-| command-r | `completion('command-r', messages)` |
-| command-light | `completion('command-light', messages)` |  
-| command-nightly | `completion('command-nightly', messages)` |
+| command-a-03-2025 | `litellm.completion('command-a-03-2025', messages)` |
+| command-r-plus-08-2024 | `litellm.completion('command-r-plus-08-2024', messages)` |  
+| command-r-08-2024 | `litellm.completion('command-r-08-2024', messages)` |
+| command-r-plus | `litellm.completion('command-r-plus', messages)` |  
+| command-r | `litellm.completion('command-r', messages)` |
+| command-light | `litellm.completion('command-light', messages)` |  
+| command-nightly | `litellm.completion('command-nightly', messages)` |
 
 
 ## Embedding

docs/my-website/docs/text_to_speech.md

@@ -1,4 +1,8 @@
-# Text to Speech
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# /audio/speech
 
 ## **LiteLLM Python SDK Usage**
 ### Quick Start 

docs/my-website/release_notes/v1.67.4-stable/index.md

@@ -0,0 +1,125 @@
+---
+title: v1.67.4-stable
+slug: v1.67.4-stable
+date: 2025-04-26T10:00:00
+authors:
+  - name: Krrish Dholakia
+    title: CEO, LiteLLM
+    url: https://www.linkedin.com/in/krish-d/
+    image_url: https://media.licdn.com/dms/image/v2/D4D03AQGrlsJ3aqpHmQ/profile-displayphoto-shrink_400_400/B4DZSAzgP7HYAg-/0/1737327772964?e=1749686400&v=beta&t=Hkl3U8Ps0VtvNxX0BNNq24b4dtX5wQaPFp6oiKCIHD8
+  - name: Ishaan Jaffer
+    title: CTO, LiteLLM
+    url: https://www.linkedin.com/in/reffajnaahsi/
+    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+
+tags: ["responses_api", "ui_improvements", "security", "session_management"]
+hide_table_of_contents: false
+---
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+## Key Highlights
+
+
+Let's dive in.
+
+
+
+## New Models / Updated Models
+
+- **OpenAI**
+    1. Added `gpt-image-1` cost tracking [Get Started](https://docs.litellm.ai/docs/image_generation)
+    2. Bug fix: added cost tracking for gpt-image-1 when quality is unspecified [PR](https://github.com/BerriAI/litellm/pull/10247)
+- **Azure**
+    1. Fixed timestamp granularities passing to whisper in Azure [Get Started](https://docs.litellm.ai/docs/audio_transcription)
+    2. Added azure/gpt-image-1 pricing [Get Started](https://docs.litellm.ai/docs/image_generation), [PR](https://github.com/BerriAI/litellm/pull/10327)
+    3. Added cost tracking for `azure/computer-use-preview`, `azure/gpt-4o-audio-preview-2024-12-17`, `azure/gpt-4o-mini-audio-preview-2024-12-17` [PR](https://github.com/BerriAI/litellm/pull/10178)
+- **Bedrock**
+    1. Added support for all compatible Bedrock parameters when model="arn:.." (Bedrock application inference profile models) [Get started](https://docs.litellm.ai/docs/providers/bedrock#bedrock-application-inference-profile), [PR](https://github.com/BerriAI/litellm/pull/10256)
+    2. Fixed wrong system prompt transformation [PR](https://github.com/BerriAI/litellm/pull/10120)
+- **VertexAI / Google AI Studio**
+    1. Allow setting `budget_tokens=0` for `gemini-2.5-flash` [Get Started](https://docs.litellm.ai/docs/providers/gemini#usage---thinking--reasoning_content),[PR](https://github.com/BerriAI/litellm/pull/10198)
+    2. Ensure returned `usage` includes thinking token usage [PR](https://github.com/BerriAI/litellm/pull/10198)
+    3. Added cost tracking for `gemini-2.5-pro-preview-03-25` [PR](https://github.com/BerriAI/litellm/pull/10178)
+- **Cohere**
+    1. Added support for cohere command-a-03-2025 [Get Started](https://docs.litellm.ai/docs/providers/cohere), [PR](https://github.com/BerriAI/litellm/pull/10295)
+- **SageMaker**
+    1. Added support for max_completion_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
+- **Responses API**
+    1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](../../docs/response_api)
+    2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
+    3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
+
+
+## Spend Tracking Improvements
+
+- **Bug Fix**: Fixed spend tracking bug, ensuring default litellm params aren't modified in memory [PR](https://github.com/BerriAI/litellm/pull/10167)
+- **Deprecation Dates**: Added deprecation dates for Azure, VertexAI models [PR](https://github.com/BerriAI/litellm/pull/10308)
+
+## Management Endpoints / UI
+
+#### Users
+- **User Info Panel**: Added a new user information pane [PR](https://github.com/BerriAI/litellm/pull/10213)
+- **Global Sorting/Filtering**: 
+  - Added global filtering to Users tab [PR](https://github.com/BerriAI/litellm/pull/10195)
+  - Enabled global sorting to find users with highest spend [PR](https://github.com/BerriAI/litellm/pull/10211)
+  - Support for filtering by user ID [PR](https://github.com/BerriAI/litellm/pull/10322)
+
+#### Teams
+- **Team Filtering**: 
+  - Added team-based filtering to the models page [PR](https://github.com/BerriAI/litellm/pull/10325)
+  - Support for filtering by team ID and team name [PR](https://github.com/BerriAI/litellm/pull/10324)
+- **Team Model Selector**: Bug fix for team model selection [PR](https://github.com/BerriAI/litellm/pull/10171)
+
+#### Keys
+- **Key Management**: 
+  - Support for cross-filtering and filtering by key hash [PR](https://github.com/BerriAI/litellm/pull/10322)
+  - Fixed key alias reset when resetting filters [PR](https://github.com/BerriAI/litellm/pull/10099)
+  - Fixed table rendering on key creation [PR](https://github.com/BerriAI/litellm/pull/10224)
+
+#### Logs
+
+- **Session Logs**: Added UI Session Logs documentation [PR](https://github.com/BerriAI/litellm/pull/10334)
+
+
+#### Authentication & Security
+- **Required Authentication**: Authentication now required for all dashboard pages [PR](https://github.com/BerriAI/litellm/pull/10229)
+- **SSO Fixes**: Fixed SSO user login invalid token error [PR](https://github.com/BerriAI/litellm/pull/10298)
+- **Encrypted Tokens**: Moved UI to encrypted token usage [PR](https://github.com/BerriAI/litellm/pull/10302)
+- **Token Expiry**: Added token expiry logic to user dashboard [PR](https://github.com/BerriAI/litellm/pull/10250)
+
+#### UI Refinements
+- **Fixed UI Flicker**: Addressed UI flickering issues in Dashboard [PR](https://github.com/BerriAI/litellm/pull/10261)
+- **Improved Terminology**: Better loading and no-data states on Keys and Tools pages [PR](https://github.com/BerriAI/litellm/pull/10253)
+- **Azure Model Support**: Fixed editing Azure public model names and changing model names after creation [PR](https://github.com/BerriAI/litellm/pull/10249)
+
+
+## Logging / Guardrail Integrations
+
+- **Datadog**:
+    1. Fixed Datadog LLM observability logging [Get Started](https://docs.litellm.ai/docs/proxy/logging#datadog), [PR](https://github.com/BerriAI/litellm/pull/10206)
+- **Prometheus / Grafana**: 
+    1. Enable datasource selection on LiteLLM Grafana Template [Get Started](https://docs.litellm.ai/docs/proxy/prometheus#-litellm-maintained-grafana-dashboards-), [PR](https://github.com/BerriAI/litellm/pull/10257)
+- **AgentOps**: 
+    1. Added AgentOps Integration [Get Started](https://docs.litellm.ai/docs/observability/agentops_integration), [PR](https://github.com/BerriAI/litellm/pull/9685)
+- **Arize**: 
+    1. Added missing attributes for Arize & Phoenix Integration [Get Started](https://docs.litellm.ai/docs/observability/arize_integration), [PR](https://github.com/BerriAI/litellm/pull/10215)
+
+
+## General Proxy Improvements
+
+- **Caching**: Fixed caching to account for thinking or reasoning_effort config [PR](https://github.com/BerriAI/litellm/pull/10140)
+- **Model Groups**: Fixed handling for cases where user sets model_group inside model_info [PR](https://github.com/BerriAI/litellm/pull/10191)
+- **Passthrough Endpoints**: Ensured `PassthroughStandardLoggingPayload` is logged with method, URL, request/response body [PR](https://github.com/BerriAI/litellm/pull/10194)
+- **Fix SQL Injection**: Fixed potential SQL injection vulnerability in spend_management_endpoints.py [PR](https://github.com/BerriAI/litellm/pull/9878)
+
+
+
+## Helm
+
+- Fixed serviceAccountName on migration job [PR](https://github.com/BerriAI/litellm/pull/10258)
+
+## Full Changelog
+
+The complete list of changes can be found in the [GitHub release notes](https://github.com/BerriAI/litellm/compare/v1.67.0-stable...v1.67.4-stable).