Merge branch 'main' into main

.circleci/config.yml

@@ -3,6 +3,18 @@ orbs:
   codecov: codecov/codecov@4.0.1
   node: circleci/node@5.1.0  # Add this line to declare the node orb
 
+commands:
+  setup_google_dns:
+    steps:
+      - run:
+          name: "Configure Google DNS"
+          command: |
+            # Backup original resolv.conf
+            sudo cp /etc/resolv.conf /etc/resolv.conf.backup
+            # Add both local and Google DNS servers
+            echo "nameserver 127.0.0.11" | sudo tee /etc/resolv.conf
+            echo "nameserver 8.8.8.8" | sudo tee -a /etc/resolv.conf
+            echo "nameserver 8.8.4.4" | sudo tee -a /etc/resolv.conf
 
 jobs:
   local_testing:
@@ -15,7 +27,7 @@ jobs:
 
     steps:
       - checkout
-
+      - setup_google_dns
       - run:
           name: Show git commit hash
           command: |
@@ -49,7 +61,7 @@ jobs:
             pip install opentelemetry-api==1.25.0
             pip install opentelemetry-sdk==1.25.0
             pip install opentelemetry-exporter-otlp==1.25.0
-            pip install openai==1.66.1
+            pip install openai==1.68.2
             pip install prisma==0.11.0
             pip install "detect_secrets==1.5.0"
             pip install "httpx==0.24.1"
@@ -66,7 +78,7 @@ jobs:
             pip install python-multipart
             pip install google-cloud-aiplatform
             pip install prometheus-client==0.20.0
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "diskcache==5.6.1"
             pip install "Pillow==10.3.0"
             pip install "jsonschema==4.22.0"
@@ -134,7 +146,7 @@ jobs:
 
     steps:
       - checkout
-
+      - setup_google_dns
       - run:
           name: Show git commit hash
           command: |
@@ -168,7 +180,7 @@ jobs:
             pip install opentelemetry-api==1.25.0
             pip install opentelemetry-sdk==1.25.0
             pip install opentelemetry-exporter-otlp==1.25.0
-            pip install openai==1.66.1
+            pip install openai==1.68.2
             pip install prisma==0.11.0
             pip install "detect_secrets==1.5.0"
             pip install "httpx==0.24.1"
@@ -185,7 +197,7 @@ jobs:
             pip install python-multipart
             pip install google-cloud-aiplatform
             pip install prometheus-client==0.20.0
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "diskcache==5.6.1"
             pip install "Pillow==10.3.0"
             pip install "jsonschema==4.22.0"
@@ -234,7 +246,13 @@ jobs:
 
     steps:
       - checkout
-
+      - setup_google_dns
+      - run:
+          name: DNS lookup for Redis host
+          command: |
+            sudo apt-get update
+            sudo apt-get install -y dnsutils
+            dig redis-19899.c239.us-east-1-2.ec2.redns.redis-cloud.com +short
       - run:
           name: Show git commit hash
           command: |
@@ -268,7 +286,7 @@ jobs:
             pip install opentelemetry-api==1.25.0
             pip install opentelemetry-sdk==1.25.0
             pip install opentelemetry-exporter-otlp==1.25.0
-            pip install openai==1.66.1
+            pip install openai==1.68.2
             pip install prisma==0.11.0
             pip install "detect_secrets==1.5.0"
             pip install "httpx==0.24.1"
@@ -285,7 +303,7 @@ jobs:
             pip install python-multipart
             pip install google-cloud-aiplatform
             pip install prometheus-client==0.20.0
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "diskcache==5.6.1"
             pip install "Pillow==10.3.0"
             pip install "jsonschema==4.22.0"
@@ -334,6 +352,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -388,6 +407,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -404,7 +424,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest tests/local_testing tests/router_unit_tests --cov=litellm --cov-report=xml -vv -k "router" -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest tests/local_testing tests/router_unit_tests --cov=litellm --cov-report=xml -vv -k "router" -x -v --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -429,6 +449,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Show git commit hash
           command: |
@@ -479,7 +500,13 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
-
+      - run:
+          name: Install PostgreSQL
+          command: |
+            sudo apt-get update
+            sudo apt-get install postgresql postgresql-contrib
+            echo 'export PATH=/usr/lib/postgresql/*/bin:$PATH' >> $BASH_ENV
+      - setup_google_dns
       - run:
           name: Show git commit hash
           command: |
@@ -513,7 +540,7 @@ jobs:
             pip install opentelemetry-api==1.25.0
             pip install opentelemetry-sdk==1.25.0
             pip install opentelemetry-exporter-otlp==1.25.0
-            pip install openai==1.66.1
+            pip install openai==1.68.2
             pip install prisma==0.11.0
             pip install "detect_secrets==1.5.0"
             pip install "httpx==0.24.1"
@@ -530,10 +557,11 @@ jobs:
             pip install python-multipart
             pip install google-cloud-aiplatform
             pip install prometheus-client==0.20.0
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "diskcache==5.6.1"
             pip install "Pillow==10.3.0"
             pip install "jsonschema==4.22.0"
+            pip install "pytest-postgresql==7.0.1"
       - save_cache:
           paths:
             - ./venv
@@ -569,7 +597,7 @@ jobs:
             - litellm_proxy_unit_tests_coverage
   litellm_assistants_api_testing: # Runs all tests with the "assistants" keyword
     docker:
-      - image: cimg/python:3.11
+      - image: cimg/python:3.13.1
         auth:
           username: ${DOCKERHUB_USERNAME}
           password: ${DOCKERHUB_PASSWORD}
@@ -577,10 +605,13 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
             python -m pip install --upgrade pip
+            pip install wheel
+            pip install --upgrade pip wheel setuptools
             python -m pip install -r requirements.txt
             pip install "pytest==7.3.1"
             pip install "respx==0.21.1"
@@ -618,6 +649,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -625,7 +657,13 @@ jobs:
             python -m pip install -r requirements.txt
             pip install "pytest==7.3.1"
             pip install "pytest-retry==1.6.3"
+            pip install "pytest-cov==5.0.0"
             pip install "pytest-asyncio==0.21.1"
+            pip install "respx==0.21.1"
+      - run:
+          name: Show current pydantic version
+          command: |
+            python -m pip show pydantic
       # Run pytest and generate JUnit XML report
       - run:
           name: Run tests
@@ -648,6 +686,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -664,7 +703,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/llm_translation --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/llm_translation --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -680,6 +719,51 @@ jobs:
           paths:
             - llm_translation_coverage.xml
             - llm_translation_coverage
+  mcp_testing:
+    docker:
+      - image: cimg/python:3.11
+        auth:
+          username: ${DOCKERHUB_USERNAME}
+          password: ${DOCKERHUB_PASSWORD}
+    working_directory: ~/project
+
+    steps:
+      - checkout
+      - setup_google_dns
+      - run:
+          name: Install Dependencies
+          command: |
+            python -m pip install --upgrade pip
+            python -m pip install -r requirements.txt
+            pip install "pytest==7.3.1"
+            pip install "pytest-retry==1.6.3"
+            pip install "pytest-cov==5.0.0"
+            pip install "pytest-asyncio==0.21.1"
+            pip install "respx==0.21.1"
+            pip install "pydantic==2.10.2"
+            pip install "mcp==1.5.0"
+      # Run pytest and generate JUnit XML report
+      - run:
+          name: Run tests
+          command: |
+            pwd
+            ls
+            python -m pytest -vv tests/mcp_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+          no_output_timeout: 120m
+      - run:
+          name: Rename the coverage files
+          command: |
+            mv coverage.xml mcp_coverage.xml
+            mv .coverage mcp_coverage
+
+      # Store test results
+      - store_test_results:
+          path: test-results
+      - persist_to_workspace:
+          root: .
+          paths:
+            - mcp_coverage.xml
+            - mcp_coverage
   llm_responses_api_testing:
     docker:
       - image: cimg/python:3.11
@@ -690,6 +774,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -732,6 +817,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -744,6 +830,8 @@ jobs:
             pip install "pytest-asyncio==0.21.1"
             pip install "respx==0.21.1"
             pip install "hypercorn==0.17.3"
+            pip install "pydantic==2.10.2"
+            pip install "mcp==1.5.0"
       # Run pytest and generate JUnit XML report
       - run:
           name: Run tests
@@ -776,6 +864,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -820,10 +909,12 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
             python -m pip install --upgrade pip
+            pip install numpydoc
             python -m pip install -r requirements.txt
             pip install "respx==0.21.1"
             pip install "pytest==7.3.1"
@@ -832,7 +923,6 @@ jobs:
             pip install "pytest-cov==5.0.0"
             pip install "google-generativeai==0.3.2"
             pip install "google-cloud-aiplatform==1.43.0"
-            pip install numpydoc
       # Run pytest and generate JUnit XML report
       - run:
           name: Run tests
@@ -866,6 +956,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -908,6 +999,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -950,6 +1042,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -996,6 +1089,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -1008,8 +1102,8 @@ jobs:
             pip install click
             pip install "boto3==1.34.34"
             pip install jinja2
-            pip install tokenizers=="0.20.0"
-            pip install uvloop==0.21.0
+            pip install "tokenizers==0.20.0"
+            pip install "uvloop==0.21.0"
             pip install jsonschema
       - run:
           name: Run tests
@@ -1028,10 +1122,12 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
             python -m pip install --upgrade pip
+            python -m pip install wheel setuptools
             python -m pip install -r requirements.txt
             pip install "pytest==7.3.1"
             pip install "pytest-retry==1.6.3"
@@ -1052,6 +1148,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       # Install Helm
       - run:
           name: Install Helm
@@ -1121,6 +1218,7 @@ jobs:
 
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Dependencies
           command: |
@@ -1157,6 +1255,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Python 3.9
           command: |
@@ -1231,6 +1330,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1278,7 +1378,7 @@ jobs:
             pip install "aiodynamo==23.10.1"
             pip install "asyncio==3.4.3"
             pip install "PyGithub==1.59.1"
-            pip install "openai==1.66.1"
+            pip install "openai==1.68.2"
       - run:
           name: Install Grype
           command: |
@@ -1353,7 +1453,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -s -vv tests/*.py -x --junitxml=test-results/junit.xml --durations=5 --ignore=tests/otel_tests --ignore=tests/pass_through_tests --ignore=tests/proxy_admin_ui_tests --ignore=tests/load_tests --ignore=tests/llm_translation --ignore=tests/llm_responses_api_testing --ignore=tests/image_gen_tests --ignore=tests/pass_through_unit_tests
+            python -m pytest -s -vv tests/*.py -x --junitxml=test-results/junit.xml --durations=5 --ignore=tests/otel_tests --ignore=tests/spend_tracking_tests --ignore=tests/pass_through_tests --ignore=tests/proxy_admin_ui_tests --ignore=tests/load_tests --ignore=tests/llm_translation --ignore=tests/llm_responses_api_testing --ignore=tests/mcp_tests --ignore=tests/image_gen_tests --ignore=tests/pass_through_unit_tests
           no_output_timeout: 120m
 
       # Store test results
@@ -1366,6 +1466,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1402,6 +1503,7 @@ jobs:
             pip install "boto3==1.34.34"
             pip install "aioboto3==12.3.0"
             pip install langchain
+            pip install "langchain_mcp_adapters==0.0.5"
             pip install "langfuse>=2.0.0"
             pip install "logfire==0.29.0"
             pip install numpydoc
@@ -1414,7 +1516,7 @@ jobs:
             pip install "aiodynamo==23.10.1"
             pip install "asyncio==3.4.3"
             pip install "PyGithub==1.59.1"
-            pip install "openai==1.66.1"
+            pip install "openai==1.68.2"
             # Run pytest and generate JUnit XML report
       - run:
           name: Build Docker image
@@ -1489,6 +1591,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1536,7 +1639,7 @@ jobs:
             pip install "aiodynamo==23.10.1"
             pip install "asyncio==3.4.3"
             pip install "PyGithub==1.59.1"
-            pip install "openai==1.66.1"
+            pip install "openai==1.68.2"
       - run:
           name: Build Docker image
           command: docker build -t my-app:latest -f ./docker/Dockerfile.database .
@@ -1643,6 +1746,96 @@ jobs:
       # Store test results
       - store_test_results:
           path: test-results
+  proxy_spend_accuracy_tests:
+    machine:
+      image: ubuntu-2204:2023.10.1
+    resource_class: xlarge
+    working_directory: ~/project
+    steps:
+      - checkout
+      - setup_google_dns
+      - run:
+          name: Install Docker CLI (In case it's not already installed)
+          command: |
+            sudo apt-get update
+            sudo apt-get install -y docker-ce docker-ce-cli containerd.io
+      - run:
+          name: Install Python 3.9
+          command: |
+            curl https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh --output miniconda.sh
+            bash miniconda.sh -b -p $HOME/miniconda
+            export PATH="$HOME/miniconda/bin:$PATH"
+            conda init bash
+            source ~/.bashrc
+            conda create -n myenv python=3.9 -y
+            conda activate myenv
+            python --version
+      - run:
+          name: Install Dependencies
+          command: |
+            pip install "pytest==7.3.1"
+            pip install "pytest-asyncio==0.21.1"
+            pip install aiohttp
+            python -m pip install --upgrade pip
+            python -m pip install -r requirements.txt
+      - run:
+          name: Build Docker image
+          command: docker build -t my-app:latest -f ./docker/Dockerfile.database .
+      - run:
+          name: Run Docker container
+          # intentionally give bad redis credentials here
+          # the OTEL test - should get this as a trace
+          command: |
+            docker run -d \
+              -p 4000:4000 \
+              -e DATABASE_URL=$PROXY_DATABASE_URL \
+              -e REDIS_HOST=$REDIS_HOST \
+              -e REDIS_PASSWORD=$REDIS_PASSWORD \
+              -e REDIS_PORT=$REDIS_PORT \
+              -e LITELLM_MASTER_KEY="sk-1234" \
+              -e OPENAI_API_KEY=$OPENAI_API_KEY \
+              -e LITELLM_LICENSE=$LITELLM_LICENSE \
+              -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
+              -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
+              -e USE_DDTRACE=True \
+              -e DD_API_KEY=$DD_API_KEY \
+              -e DD_SITE=$DD_SITE \
+              -e AWS_REGION_NAME=$AWS_REGION_NAME \
+              --name my-app \
+              -v $(pwd)/litellm/proxy/example_config_yaml/spend_tracking_config.yaml:/app/config.yaml \
+              my-app:latest \
+              --config /app/config.yaml \
+              --port 4000 \
+              --detailed_debug \
+      - run:
+          name: Install curl and dockerize
+          command: |
+            sudo apt-get update
+            sudo apt-get install -y curl
+            sudo wget https://github.com/jwilder/dockerize/releases/download/v0.6.1/dockerize-linux-amd64-v0.6.1.tar.gz
+            sudo tar -C /usr/local/bin -xzvf dockerize-linux-amd64-v0.6.1.tar.gz
+            sudo rm dockerize-linux-amd64-v0.6.1.tar.gz
+      - run:
+          name: Start outputting logs
+          command: docker logs -f my-app
+          background: true
+      - run:
+          name: Wait for app to be ready
+          command: dockerize -wait http://localhost:4000 -timeout 5m
+      - run:
+          name: Run tests
+          command: |
+            pwd
+            ls
+            python -m pytest -vv tests/spend_tracking_tests -x --junitxml=test-results/junit.xml --durations=5
+          no_output_timeout:
+            120m
+            # Clean up first container
+      - run:
+          name: Stop and remove first container
+          command: |
+            docker stop my-app
+            docker rm my-app
 
   proxy_multi_instance_tests:
     machine:
@@ -1651,6 +1844,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1762,6 +1956,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1801,7 +1996,7 @@ jobs:
           command: |
             docker run -d \
               -p 4000:4000 \
-              -e DATABASE_URL=$PROXY_DATABASE_URL \
+              -e DATABASE_URL=$CLEAN_STORE_MODEL_IN_DB_DATABASE_URL \
               -e STORE_MODEL_IN_DB="True" \
               -e LITELLM_MASTER_KEY="sk-1234" \
               -e LITELLM_LICENSE=$LITELLM_LICENSE \
@@ -1844,6 +2039,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       # Remove Docker CLI installation since it's already available in machine executor
       - run:
           name: Install Python 3.13
@@ -1941,6 +2137,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Install Docker CLI (In case it's not already installed)
           command: |
@@ -1965,10 +2162,10 @@ jobs:
             pip install "pytest-asyncio==0.21.1"
             pip install "google-cloud-aiplatform==1.43.0"
             pip install aiohttp
-            pip install "openai==1.66.1"
+            pip install "openai==1.68.2"
             pip install "assemblyai==0.37.0"
             python -m pip install --upgrade pip
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "pytest==7.3.1"
             pip install "pytest-mock==3.12.0"
             pip install "pytest-asyncio==0.21.1"
@@ -1985,6 +2182,9 @@ jobs:
             pip install "PyGithub==1.59.1"
             pip install "google-cloud-aiplatform==1.59.0"
             pip install "anthropic==0.49.0"
+            pip install "langchain_mcp_adapters==0.0.5"
+            pip install "langchain_openai==0.2.1"
+            pip install "langgraph==0.3.18"
       # Run pytest and generate JUnit XML report
       - run:
           name: Build Docker image
@@ -2112,7 +2312,7 @@ jobs:
             python -m venv venv
             . venv/bin/activate
             pip install coverage
-            coverage combine llm_translation_coverage llm_responses_api_coverage logging_coverage litellm_router_coverage local_testing_coverage litellm_assistants_api_coverage auth_ui_unit_tests_coverage langfuse_coverage caching_coverage litellm_proxy_unit_tests_coverage image_gen_coverage pass_through_unit_tests_coverage batches_coverage litellm_proxy_security_tests_coverage
+            coverage combine llm_translation_coverage llm_responses_api_coverage mcp_coverage logging_coverage litellm_router_coverage local_testing_coverage litellm_assistants_api_coverage auth_ui_unit_tests_coverage langfuse_coverage caching_coverage litellm_proxy_unit_tests_coverage image_gen_coverage pass_through_unit_tests_coverage batches_coverage litellm_proxy_security_tests_coverage
             coverage xml
       - codecov/upload:
           file: ./coverage.xml
@@ -2190,6 +2390,114 @@ jobs:
             echo "triggering load testing server for version ${VERSION} and commit ${CIRCLE_SHA1}"
             curl -X POST "https://proxyloadtester-production.up.railway.app/start/load/test?version=${VERSION}&commit_hash=${CIRCLE_SHA1}&release_type=nightly"
 
+  publish_proxy_extras:
+    docker:
+      - image: cimg/python:3.8
+    working_directory: ~/project/litellm-proxy-extras
+    environment:
+      TWINE_USERNAME: __token__
+
+    steps:
+      - checkout:
+          path: ~/project
+
+      - run:
+          name: Check if litellm-proxy-extras dir or pyproject.toml was modified
+          command: |
+            echo "Install TOML package."
+            python -m pip install toml
+            # Get current version from pyproject.toml
+            CURRENT_VERSION=$(python -c "import toml; print(toml.load('pyproject.toml')['tool']['poetry']['version'])")
+            
+            # Get last published version from PyPI
+            LAST_VERSION=$(curl -s https://pypi.org/pypi/litellm-proxy-extras/json | python -c "import json, sys; print(json.load(sys.stdin)['info']['version'])")
+            
+            echo "Current version: $CURRENT_VERSION"
+            echo "Last published version: $LAST_VERSION"
+            
+            # Compare versions using Python's packaging.version
+            VERSION_COMPARE=$(python -c "from packaging import version; print(1 if version.parse('$CURRENT_VERSION') < version.parse('$LAST_VERSION') else 0)")
+            
+            echo "Version compare: $VERSION_COMPARE"
+            if [ "$VERSION_COMPARE" = "1" ]; then
+              echo "Error: Current version ($CURRENT_VERSION) is less than last published version ($LAST_VERSION)"
+              exit 1
+            fi
+            
+            # If versions are equal or current is greater, check contents
+            pip download --no-deps litellm-proxy-extras==$LAST_VERSION -d /tmp
+            
+            echo "Contents of /tmp directory:"
+            ls -la /tmp
+            
+            # Find the downloaded file (could be .whl or .tar.gz)
+            DOWNLOADED_FILE=$(ls /tmp/litellm_proxy_extras-*)
+            echo "Downloaded file: $DOWNLOADED_FILE"
+            
+            # Extract based on file extension
+            if [[ "$DOWNLOADED_FILE" == *.whl ]]; then
+                echo "Extracting wheel file..."
+                unzip -q "$DOWNLOADED_FILE" -d /tmp/extracted
+                EXTRACTED_DIR="/tmp/extracted"
+            else
+                echo "Extracting tar.gz file..."
+                tar -xzf "$DOWNLOADED_FILE" -C /tmp
+                EXTRACTED_DIR="/tmp/litellm_proxy_extras-$LAST_VERSION"
+            fi
+            
+            echo "Contents of extracted package:"
+            ls -R "$EXTRACTED_DIR"
+            
+            # Compare contents
+            if ! diff -r "$EXTRACTED_DIR/litellm_proxy_extras" ./litellm_proxy_extras; then
+              if [ "$CURRENT_VERSION" = "$LAST_VERSION" ]; then
+                echo "Error: Changes detected in litellm-proxy-extras but version was not bumped"
+                echo "Current version: $CURRENT_VERSION"
+                echo "Last published version: $LAST_VERSION"
+                echo "Changes:"
+                diff -r "$EXTRACTED_DIR/litellm_proxy_extras" ./litellm_proxy_extras
+                exit 1
+              fi
+            else
+              echo "No changes detected in litellm-proxy-extras. Skipping PyPI publish."
+              circleci step halt
+            fi
+
+      - run:
+          name: Get new version
+          command: |
+            cd litellm-proxy-extras
+            NEW_VERSION=$(python -c "import toml; print(toml.load('pyproject.toml')['tool']['poetry']['version'])")
+            echo "export NEW_VERSION=$NEW_VERSION" >> $BASH_ENV
+
+      - run:
+          name: Check if versions match
+          command: |
+            cd ~/project
+            # Check pyproject.toml
+            CURRENT_VERSION=$(python -c "import toml; print(toml.load('pyproject.toml')['tool']['poetry']['dependencies']['litellm-proxy-extras'].split('\"')[1])")
+            if [ "$CURRENT_VERSION" != "$NEW_VERSION" ]; then
+              echo "Error: Version in pyproject.toml ($CURRENT_VERSION) doesn't match new version ($NEW_VERSION)"
+              exit 1
+            fi
+
+            # Check requirements.txt
+            REQ_VERSION=$(grep -oP 'litellm-proxy-extras==\K[0-9.]+' requirements.txt)
+            if [ "$REQ_VERSION" != "$NEW_VERSION" ]; then
+              echo "Error: Version in requirements.txt ($REQ_VERSION) doesn't match new version ($NEW_VERSION)"
+              exit 1
+            fi
+
+      - run:
+          name: Publish to PyPI
+          command: |
+            cd litellm-proxy-extras
+            echo -e "[pypi]\nusername = $PYPI_PUBLISH_USERNAME\npassword = $PYPI_PUBLISH_PASSWORD" > ~/.pypirc
+            python -m pip install --upgrade pip build twine setuptools wheel
+            rm -rf build dist
+            python -m build
+            twine upload --verbose dist/*
+
   e2e_ui_testing:
     machine:
       image: ubuntu-2204:2023.10.1
@@ -2197,6 +2505,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Build UI
           command: |
@@ -2241,9 +2550,9 @@ jobs:
             pip install "pytest-retry==1.6.3"
             pip install "pytest-asyncio==0.21.1"
             pip install aiohttp
-            pip install "openai==1.66.1"
+            pip install "openai==1.68.2"
             python -m pip install --upgrade pip
-            pip install "pydantic==2.7.1"
+            pip install "pydantic==2.10.2"
             pip install "pytest==7.3.1"
             pip install "pytest-mock==3.12.0"
             pip install "pytest-asyncio==0.21.1"
@@ -2311,6 +2620,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Build Docker image
           command: |
@@ -2333,6 +2643,7 @@ jobs:
     working_directory: ~/project
     steps:
       - checkout
+      - setup_google_dns
       - run:
           name: Build Docker image
           command: |
@@ -2443,6 +2754,12 @@ workflows:
               only:
                 - main
                 - /litellm_.*/
+      - proxy_spend_accuracy_tests:
+          filters:
+            branches:
+              only:
+                - main
+                - /litellm_.*/
       - proxy_multi_instance_tests:
           filters:
             branches:
@@ -2473,6 +2790,12 @@ workflows:
               only:
                 - main
                 - /litellm_.*/
+      - mcp_testing:
+          filters:
+            branches:
+              only:
+                - main
+                - /litellm_.*/
       - llm_responses_api_testing:
           filters:
             branches:
@@ -2518,6 +2841,7 @@ workflows:
       - upload-coverage:
           requires:
             - llm_translation_testing
+            - mcp_testing
             - llm_responses_api_testing
             - litellm_mapped_tests
             - batches_testing
@@ -2569,6 +2893,11 @@ workflows:
               only:
                 - main
                 - /litellm_.*/
+      - publish_proxy_extras:
+          filters:
+            branches:
+              only:
+                - main
       - publish_to_pypi:
           requires:
             - local_testing
@@ -2577,6 +2906,7 @@ workflows:
             - load_testing
             - test_bad_database_url
             - llm_translation_testing
+            - mcp_testing
             - llm_responses_api_testing
             - litellm_mapped_tests
             - batches_testing
@@ -2596,12 +2926,11 @@ workflows:
             - installing_litellm_on_python
             - installing_litellm_on_python_3_13
             - proxy_logging_guardrails_model_info_tests
+            - proxy_spend_accuracy_tests
             - proxy_multi_instance_tests
             - proxy_store_model_in_db_tests
             - proxy_build_from_pip_tests
             - proxy_pass_through_endpoint_tests
             - check_code_and_doc_quality
-          filters:
-            branches:
-              only:
-                - main
+            - publish_proxy_extras
+      

.circleci/requirements.txt

@@ -1,13 +1,15 @@
 # used by CI/CD testing
-openai==1.66.1
+openai==1.68.2
 python-dotenv
 tiktoken
 importlib_metadata
 cohere
-redis
+redis==5.2.1
+redisvl==0.4.1
 anthropic
 orjson==3.9.15
-pydantic==2.7.1
+pydantic==2.10.2
 google-cloud-aiplatform==1.43.0
-fastapi-sso==0.10.0
+fastapi-sso==0.16.0 
 uvloop==0.21.0
+mcp==1.5.0    # for MCP server  

.env.example

@@ -20,6 +20,8 @@ REPLICATE_API_TOKEN = ""
 ANTHROPIC_API_KEY = ""
 # Infisical
 INFISICAL_TOKEN = ""
+# INFINITY
+INFINITY_API_KEY = ""
 
 # Development Configs
 LITELLM_MASTER_KEY = "sk-1234"

.github/pull_request_template.md

@@ -10,7 +10,7 @@
 
 **Please complete all items before asking a LiteLLM maintainer to review your PR**
 
-- [ ] I have Added testing in the `tests/litellm/` directory, **Adding at least 1 test is a hard requirement** - [see details](https://docs.litellm.ai/docs/extras/contributing_code)
+- [ ] I have Added testing in the [`tests/litellm/`](https://github.com/BerriAI/litellm/tree/main/tests/litellm) directory, **Adding at least 1 test is a hard requirement** - [see details](https://docs.litellm.ai/docs/extras/contributing_code)
 - [ ] I have added a screenshot of my new test passing locally 
 - [ ] My PR passes all unit tests on (`make test-unit`)[https://docs.litellm.ai/docs/extras/contributing_code]
 - [ ] My PR's scope is as isolated as possible, it only solves 1 specific problem

.github/workflows/ghcr_deploy.yml

@@ -114,8 +114,8 @@ jobs:
           tags: |
             ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
             ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:main-{0}', github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && '${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:main-stable' || '' }}
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-stable', env.REGISTRY) || '' }}
           labels: ${{ steps.meta.outputs.labels }}
           platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
           
@@ -157,8 +157,8 @@ jobs:
           tags: |
             ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
             ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-database:main-{0}', github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && '${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-database:main-stable' || '' }}
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-stable', env.REGISTRY) || '' }}
           labels: ${{ steps.meta-database.outputs.labels }}
           platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
             
@@ -200,8 +200,8 @@ jobs:
           tags: |
             ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
             ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-non_root:main-{0}', github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && '${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-non_root:main-stable' || '' }}
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-stable', env.REGISTRY) || '' }}
           labels: ${{ steps.meta-non_root.outputs.labels }} 
           platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
   
@@ -240,7 +240,11 @@ jobs:
           context: .
           file: ./litellm-js/spend-logs/Dockerfile
           push: true
-          tags: ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }}, ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.release_type }}
+          tags: |
+            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
+            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.release_type }}
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
+            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-stable', env.REGISTRY) || '' }}
           platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
 
   build-and-push-helm-chart:

.github/workflows/publish-migrations.yml

@@ -0,0 +1,206 @@
+name: Publish Prisma Migrations
+
+permissions:
+  contents: write
+  pull-requests: write
+
+on:
+  push:
+    paths:
+      - 'schema.prisma'  # Check root schema.prisma
+    branches:
+      - main
+
+jobs:
+  publish-migrations:
+    runs-on: ubuntu-latest
+    services:
+      postgres:
+        image: postgres:14
+        env:
+          POSTGRES_DB: temp_db
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: postgres
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+      
+      # Add shadow database service
+      postgres_shadow:
+        image: postgres:14
+        env:
+          POSTGRES_DB: shadow_db
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: postgres
+        ports:
+          - 5433:5432
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+
+      - name: Install Dependencies
+        run: |
+          pip install prisma
+          pip install python-dotenv
+
+      - name: Generate Initial Migration if None Exists
+        env:
+          DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
+        run: |
+          mkdir -p deploy/migrations
+          echo 'provider = "postgresql"' > deploy/migrations/migration_lock.toml
+          
+          if [ -z "$(ls -A deploy/migrations/2* 2>/dev/null)" ]; then
+            echo "No existing migrations found, creating baseline..."
+            VERSION=$(date +%Y%m%d%H%M%S)
+            mkdir -p deploy/migrations/${VERSION}_initial
+            
+            echo "Generating initial migration..."
+            # Save raw output for debugging
+            prisma migrate diff \
+              --from-empty \
+              --to-schema-datamodel schema.prisma \
+              --shadow-database-url "${SHADOW_DATABASE_URL}" \
+              --script > deploy/migrations/${VERSION}_initial/raw_migration.sql
+            
+            echo "Raw migration file content:"
+            cat deploy/migrations/${VERSION}_initial/raw_migration.sql
+            
+            echo "Cleaning migration file..."
+            # Clean the file
+            sed '/^Installing/d' deploy/migrations/${VERSION}_initial/raw_migration.sql > deploy/migrations/${VERSION}_initial/migration.sql
+            
+            # Verify the migration file
+            if [ ! -s deploy/migrations/${VERSION}_initial/migration.sql ]; then
+              echo "ERROR: Migration file is empty after cleaning"
+              echo "Original content was:"
+              cat deploy/migrations/${VERSION}_initial/raw_migration.sql
+              exit 1
+            fi
+            
+            echo "Final migration file content:"
+            cat deploy/migrations/${VERSION}_initial/migration.sql
+            
+            # Verify it starts with SQL
+            if ! head -n 1 deploy/migrations/${VERSION}_initial/migration.sql | grep -q "^--\|^CREATE\|^ALTER"; then
+              echo "ERROR: Migration file does not start with SQL command or comment"
+              echo "First line is:"
+              head -n 1 deploy/migrations/${VERSION}_initial/migration.sql
+              echo "Full content is:"
+              cat deploy/migrations/${VERSION}_initial/migration.sql
+              exit 1
+            fi
+            
+            echo "Initial migration generated at $(date -u)" > deploy/migrations/${VERSION}_initial/README.md
+          fi
+
+      - name: Compare and Generate Migration
+        if: success()
+        env:
+          DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
+        run: |
+          # Create temporary migration workspace
+          mkdir -p temp_migrations
+          
+          # Copy existing migrations (will not fail if directory is empty)
+          cp -r deploy/migrations/* temp_migrations/ 2>/dev/null || true
+          
+          VERSION=$(date +%Y%m%d%H%M%S)
+          
+          # Generate diff against existing migrations or empty state
+          prisma migrate diff \
+            --from-migrations temp_migrations \
+            --to-schema-datamodel schema.prisma \
+            --shadow-database-url "${SHADOW_DATABASE_URL}" \
+            --script > temp_migrations/migration_${VERSION}.sql
+          
+          # Check if there are actual changes
+          if [ -s temp_migrations/migration_${VERSION}.sql ]; then
+            echo "Changes detected, creating new migration"
+            mkdir -p deploy/migrations/${VERSION}_schema_update
+            mv temp_migrations/migration_${VERSION}.sql deploy/migrations/${VERSION}_schema_update/migration.sql
+            echo "Migration generated at $(date -u)" > deploy/migrations/${VERSION}_schema_update/README.md
+          else
+            echo "No schema changes detected"
+            exit 0
+          fi
+
+      - name: Verify Migration
+        if: success()
+        env:
+          DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
+          SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
+        run: |
+          # Create test database
+          psql "${SHADOW_DATABASE_URL}" -c 'CREATE DATABASE migration_test;'
+          
+          # Apply all migrations in order to verify
+          for migration in deploy/migrations/*/migration.sql; do
+            echo "Applying migration: $migration"
+            psql "${SHADOW_DATABASE_URL}" -f $migration
+          done
+
+      # Add this step before create-pull-request to debug permissions
+      - name: Check Token Permissions
+        run: |
+          echo "Checking token permissions..."
+          curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+               -H "Accept: application/vnd.github.v3+json" \
+               https://api.github.com/repos/BerriAI/litellm/collaborators
+          
+          echo "\nChecking if token can create PRs..."
+          curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+               -H "Accept: application/vnd.github.v3+json" \
+               https://api.github.com/repos/BerriAI/litellm
+
+      # Add this debug step before git push
+      - name: Debug Changed Files
+        run: |
+          echo "Files staged for commit:"
+          git diff --name-status --staged
+          
+          echo "\nAll changed files:"
+          git status
+
+      - name: Create Pull Request
+        if: success()
+        uses: peter-evans/create-pull-request@v5
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "chore: update prisma migrations"
+          title: "Update Prisma Migrations"
+          body: |
+            Auto-generated migration based on schema.prisma changes.
+            
+            Generated files:
+            - deploy/migrations/${VERSION}_schema_update/migration.sql
+            - deploy/migrations/${VERSION}_schema_update/README.md
+          branch: feat/prisma-migration-${{ env.VERSION }}
+          base: main
+          delete-branch: true
+
+      - name: Generate and Save Migrations
+        run: |
+          # Only add migration files
+          git add deploy/migrations/
+          git status  # Debug what's being committed
+          git commit -m "chore: update prisma migrations" 

.github/workflows/test-linting.yml

@@ -0,0 +1,53 @@
+name: LiteLLM Linting
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Install dependencies
+      run: |
+        poetry install --with dev
+
+    - name: Run Black formatting
+      run: |
+        cd litellm
+        poetry run black .
+        cd ..
+
+    - name: Run Ruff linting
+      run: |
+        cd litellm
+        poetry run ruff check .
+        cd ..
+
+    - name: Run MyPy type checking
+      run: |
+        cd litellm
+        poetry run mypy . --ignore-missing-imports
+        cd ..
+
+    - name: Check for circular imports
+      run: |
+        cd litellm
+        poetry run python ../tests/documentation_tests/test_circular_imports.py
+        cd ..
+
+    - name: Check import safety
+      run: |
+        poetry run python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)

.github/workflows/test-litellm.yml

@@ -0,0 +1,35 @@
+name: LiteLLM Mock Tests (folder - tests/litellm)
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Thank You Message
+      run: |
+        echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
+        echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Install dependencies
+      run: |
+        poetry install --with dev,proxy-dev --extras proxy
+        poetry run pip install pytest-xdist
+
+    - name: Run tests
+      run: |
+        poetry run pytest tests/litellm -x -vv -n 4 

.gitignore

@@ -1,3 +1,4 @@
+.python-version
 .venv
 .env
 .newenv
@@ -72,6 +73,7 @@ tests/local_testing/log.txt
 .codegpt
 litellm/proxy/_new_new_secret_config.yaml
 litellm/proxy/custom_guardrail.py
+.mypy_cache/*
 litellm/proxy/_experimental/out/404.html
 litellm/proxy/_experimental/out/404.html
 litellm/proxy/_experimental/out/model_hub.html
@@ -79,3 +81,10 @@ litellm/proxy/_experimental/out/model_hub.html
 litellm/proxy/application.log
 tests/llm_translation/vertex_test_account.json
 tests/llm_translation/test_vertex_key.json
+litellm/proxy/migrations/0_init/migration.sql
+litellm/proxy/db/migrations/0_init/migration.sql
+litellm/proxy/db/migrations/*
+litellm/proxy/migrations/*config.yaml
+litellm/proxy/migrations/*
+config.yaml
+tests/litellm/litellm_core_utils/llm_cost_calc/log.txt

.pre-commit-config.yaml

@@ -6,44 +6,35 @@ repos:
         entry: pyright
         language: system
         types: [python]
-        files: ^litellm/
+        files: ^(litellm/|litellm_proxy_extras/)
     -   id: isort
         name: isort
         entry: isort
         language: system
         types: [python]
-        files: litellm/.*\.py
+        files: (litellm/|litellm_proxy_extras/).*\.py
         exclude: ^litellm/__init__.py$
--   repo: https://github.com/psf/black
-    rev: 24.2.0
-    hooks:
     -   id: black
+        name: black
+        entry: poetry run black
+        language: system
+        types: [python]
+        files: (litellm/|litellm_proxy_extras/).*\.py
 -   repo: https://github.com/pycqa/flake8
     rev: 7.0.0  # The version of flake8 to use
     hooks:
     -  id: flake8
        exclude: ^litellm/tests/|^litellm/proxy/tests/|^litellm/tests/litellm/|^tests/litellm/
        additional_dependencies: [flake8-print]
-       files: litellm/.*\.py
-    # -  id: flake8
-    #    name: flake8 (router.py function length)
-    #    files: ^litellm/router\.py$
-    #    args: [--max-function-length=40]
-    # #    additional_dependencies: [flake8-functions]
+       files: (litellm/|litellm_proxy_extras/).*\.py
 -   repo: https://github.com/python-poetry/poetry
     rev: 1.8.0
     hooks:
       - id: poetry-check
+        files: ^(pyproject.toml|litellm-proxy-extras/pyproject.toml)$
 -   repo: local
     hooks:
     -   id: check-files-match
         name: Check if files match
         entry: python3 ci_cd/check_files_match.py
         language: system
-    # -   id: check-file-length
-    #     name: Check file length
-    #     entry: python check_file_length.py
-    #     args: ["10000"]  # set your desired maximum number of lines
-    #     language: python
-    #     files: litellm/.*\.py
-    #     exclude: ^litellm/tests/

Dockerfile

@@ -12,8 +12,7 @@ WORKDIR /app
 USER root
 
 # Install build dependencies
-RUN apk update && \
-    apk add --no-cache gcc python3-dev openssl openssl-dev
+RUN apk add --no-cache gcc python3-dev openssl openssl-dev
 
 
 RUN pip install --upgrade pip && \
@@ -37,9 +36,6 @@ RUN pip install dist/*.whl
 # install dependencies as wheels
 RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
 
-# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0 
-RUN pip install redisvl==0.0.7 --no-deps
-
 # ensure pyjwt is used, not jwt
 RUN pip uninstall jwt -y
 RUN pip uninstall PyJWT -y
@@ -55,8 +51,7 @@ FROM $LITELLM_RUNTIME_IMAGE AS runtime
 USER root
 
 # Install runtime dependencies
-RUN apk update && \
-    apk add --no-cache openssl
+RUN apk add --no-cache openssl
 
 WORKDIR /app
 # Copy the current directory contents into the container at /app

Makefile

@@ -9,10 +9,14 @@ help:
 	@echo "  make test               - Run all tests"
 	@echo "  make test-unit          - Run unit tests"
 	@echo "  make test-integration   - Run integration tests"
+	@echo "  make test-unit-helm     - Run helm unit tests"
 
 install-dev:
 	poetry install --with dev
 
+install-proxy-dev:
+	poetry install --with dev,proxy-dev
+
 lint: install-dev
 	poetry run pip install types-requests types-setuptools types-redis types-PyYAML
 	cd litellm && poetry run mypy . --ignore-missing-imports
@@ -26,3 +30,6 @@ test-unit:
 
 test-integration:
 	poetry run pytest tests/ -k "not litellm"
+
+test-unit-helm:
+	helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm

README.md

@@ -16,9 +16,6 @@
     <a href="https://pypi.org/project/litellm/" target="_blank">
         <img src="https://img.shields.io/pypi/v/litellm.svg" alt="PyPI Version">
     </a>
-    <a href="https://dl.circleci.com/status-badge/redirect/gh/BerriAI/litellm/tree/main" target="_blank">
-        <img src="https://dl.circleci.com/status-badge/img/gh/BerriAI/litellm/tree/main.svg?style=svg" alt="CircleCI">
-    </a>
     <a href="https://www.ycombinator.com/companies/berriai">
         <img src="https://img.shields.io/badge/Y%20Combinator-W23-orange?style=flat-square" alt="Y Combinator W23">
     </a>

ci_cd/baseline_db.py

@@ -0,0 +1,60 @@
+import subprocess
+from pathlib import Path
+from datetime import datetime
+
+
+def create_baseline():
+    """Create baseline migration in deploy/migrations"""
+    try:
+        # Get paths
+        root_dir = Path(__file__).parent.parent
+        deploy_dir = root_dir / "deploy"
+        migrations_dir = deploy_dir / "migrations"
+        schema_path = root_dir / "schema.prisma"
+
+        # Create migrations directory
+        migrations_dir.mkdir(parents=True, exist_ok=True)
+
+        # Create migration_lock.toml if it doesn't exist
+        lock_file = migrations_dir / "migration_lock.toml"
+        if not lock_file.exists():
+            lock_file.write_text('provider = "postgresql"\n')
+
+        # Create timestamp-based migration directory
+        timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
+        migration_dir = migrations_dir / f"{timestamp}_baseline"
+        migration_dir.mkdir(parents=True, exist_ok=True)
+
+        # Generate migration SQL
+        result = subprocess.run(
+            [
+                "prisma",
+                "migrate",
+                "diff",
+                "--from-empty",
+                "--to-schema-datamodel",
+                str(schema_path),
+                "--script",
+            ],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+
+        # Write the SQL to migration.sql
+        migration_file = migration_dir / "migration.sql"
+        migration_file.write_text(result.stdout)
+
+        print(f"Created baseline migration in {migration_dir}")
+        return True
+
+    except subprocess.CalledProcessError as e:
+        print(f"Error running prisma command: {e.stderr}")
+        return False
+    except Exception as e:
+        print(f"Error creating baseline migration: {str(e)}")
+        return False
+
+
+if __name__ == "__main__":
+    create_baseline()

ci_cd/publish-proxy-extras.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+# Exit on error
+set -e
+
+echo "🚀 Building and publishing litellm-proxy-extras"
+
+# Navigate to litellm-proxy-extras directory
+cd "$(dirname "$0")/../litellm-proxy-extras"
+
+# Build the package
+echo "📦 Building package..."
+poetry build
+
+# Publish to PyPI
+echo "🌎 Publishing to PyPI..."
+poetry publish
+
+echo "✅ Done! Package published successfully"

ci_cd/run_migration.py

@@ -0,0 +1,95 @@
+import os
+import subprocess
+from pathlib import Path
+from datetime import datetime
+import testing.postgresql
+import shutil
+
+
+def create_migration(migration_name: str = None):
+    """
+    Create a new migration SQL file in the migrations directory by comparing
+    current database state with schema
+
+    Args:
+        migration_name (str): Name for the migration
+    """
+    try:
+        # Get paths
+        root_dir = Path(__file__).parent.parent
+        migrations_dir = root_dir / "litellm-proxy-extras" / "litellm_proxy_extras" / "migrations"
+        schema_path = root_dir / "schema.prisma"
+
+        # Create temporary PostgreSQL database
+        with testing.postgresql.Postgresql() as postgresql:
+            db_url = postgresql.url()
+
+            # Create temporary migrations directory next to schema.prisma
+            temp_migrations_dir = schema_path.parent / "migrations"
+
+            try:
+                # Copy existing migrations to temp directory
+                if temp_migrations_dir.exists():
+                    shutil.rmtree(temp_migrations_dir)
+                shutil.copytree(migrations_dir, temp_migrations_dir)
+
+                # Apply existing migrations to temp database
+                os.environ["DATABASE_URL"] = db_url
+                subprocess.run(
+                    ["prisma", "migrate", "deploy", "--schema", str(schema_path)],
+                    check=True,
+                )
+
+                # Generate diff between current database and schema
+                result = subprocess.run(
+                    [
+                        "prisma",
+                        "migrate",
+                        "diff",
+                        "--from-url",
+                        db_url,
+                        "--to-schema-datamodel",
+                        str(schema_path),
+                        "--script",
+                    ],
+                    capture_output=True,
+                    text=True,
+                    check=True,
+                )
+
+                if result.stdout.strip():
+                    # Generate timestamp and create migration directory
+                    timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
+                    migration_name = migration_name or "unnamed_migration"
+                    migration_dir = migrations_dir / f"{timestamp}_{migration_name}"
+                    migration_dir.mkdir(parents=True, exist_ok=True)
+
+                    # Write the SQL to migration.sql
+                    migration_file = migration_dir / "migration.sql"
+                    migration_file.write_text(result.stdout)
+
+                    print(f"Created migration in {migration_dir}")
+                    return True
+                else:
+                    print("No schema changes detected. Migration not needed.")
+                    return False
+
+            finally:
+                # Clean up: remove temporary migrations directory
+                if temp_migrations_dir.exists():
+                    shutil.rmtree(temp_migrations_dir)
+
+    except subprocess.CalledProcessError as e:
+        print(f"Error generating migration: {e.stderr}")
+        return False
+    except Exception as e:
+        print(f"Error creating migration: {str(e)}")
+        return False
+
+
+if __name__ == "__main__":
+    # If running directly, can optionally pass migration name as argument
+    import sys
+
+    migration_name = sys.argv[1] if len(sys.argv) > 1 else None
+    create_migration(migration_name)

cookbook/LiteLLM_HuggingFace.ipynb

@@ -6,8 +6,9 @@
         "id": "9dKM5k8qsMIj"
       },
       "source": [
-        "## LiteLLM HuggingFace\n",
-        "Docs for huggingface: https://docs.litellm.ai/docs/providers/huggingface"
+        "## LiteLLM Hugging Face\n",
+        "\n",
+        "Docs for huggingface: https://docs.litellm.ai/docs/providers/huggingface\n"
       ]
     },
     {
@@ -27,23 +28,18 @@
         "id": "yp5UXRqtpu9f"
       },
       "source": [
-        "## Hugging Face Free Serverless Inference API\n",
-        "Read more about the Free Serverless Inference API here: https://huggingface.co/docs/api-inference.\n",
+        "## Serverless Inference Providers\n",
         "\n",
-        "In order to use litellm to call Serverless Inference API:\n",
+        "Read more about Inference Providers here: https://huggingface.co/blog/inference-providers.\n",
         "\n",
-        "* Browse Serverless Inference compatible models here: https://huggingface.co/models?inference=warm&pipeline_tag=text-generation.\n",
-        "* Copy the model name from hugging face\n",
-        "* Set `model = \"huggingface/<model-name>\"`\n",
+        "In order to use litellm with Hugging Face Inference Providers, you need to set `model=huggingface/<provider>/<model-id>`.\n",
         "\n",
-        "Example set `model=huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct` to call `meta-llama/Meta-Llama-3.1-8B-Instruct`\n",
-        "\n",
-        "https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct"
+        "Example: `huggingface/together/deepseek-ai/DeepSeek-R1` to run DeepSeek-R1 (https://huggingface.co/deepseek-ai/DeepSeek-R1) through Together AI.\n"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 3,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -51,107 +47,18 @@
         "id": "Pi5Oww8gpCUm",
         "outputId": "659a67c7-f90d-4c06-b94e-2c4aa92d897a"
       },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "ModelResponse(id='chatcmpl-c54dfb68-1491-4d68-a4dc-35e603ea718a', choices=[Choices(finish_reason='eos_token', index=0, message=Message(content=\"I'm just a computer program, so I don't have feelings, but thank you for asking! How can I assist you today?\", role='assistant', tool_calls=None, function_call=None))], created=1724858285, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=27, prompt_tokens=47, total_tokens=74))\n",
-            "ModelResponse(id='chatcmpl-d2ae38e6-4974-431c-bb9b-3fa3f95e5a6d', choices=[Choices(finish_reason='length', index=0, message=Message(content=\"\\n\\nI’m doing well, thank you. I’ve been keeping busy with work and some personal projects. How about you?\\n\\nI'm doing well, thank you. I've been enjoying some time off and catching up on some reading. How can I assist you today?\\n\\nI'm looking for a good book to read. Do you have any recommendations?\\n\\nOf course! Here are a few book recommendations across different genres:\\n\\n1.\", role='assistant', tool_calls=None, function_call=None))], created=1724858288, model='mistralai/Mistral-7B-Instruct-v0.3', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=85, prompt_tokens=6, total_tokens=91))\n"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "import os\n",
-        "import litellm\n",
+        "from litellm import completion\n",
         "\n",
-        "# Make sure to create an API_KEY with inference permissions at https://huggingface.co/settings/tokens/new?globalPermissions=inference.serverless.write&tokenType=fineGrained\n",
-        "os.environ[\"HUGGINGFACE_API_KEY\"] = \"\"\n",
+        "# You can create a HF token here: https://huggingface.co/settings/tokens\n",
+        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
         "\n",
-        "# Call https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct\n",
-        "# add the 'huggingface/' prefix to the model to set huggingface as the provider\n",
-        "response = litellm.completion(\n",
-        "    model=\"huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
-        "    messages=[{ \"content\": \"Hello, how are you?\",\"role\": \"user\"}]\n",
-        ")\n",
-        "print(response)\n",
-        "\n",
-        "\n",
-        "# Call https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3\n",
-        "response = litellm.completion(\n",
-        "    model=\"huggingface/mistralai/Mistral-7B-Instruct-v0.3\",\n",
-        "    messages=[{ \"content\": \"Hello, how are you?\",\"role\": \"user\"}]\n",
-        ")\n",
-        "print(response)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "-klhAhjLtclv"
-      },
-      "source": [
-        "## Hugging Face Dedicated Inference Endpoints\n",
-        "\n",
-        "Steps to use\n",
-        "* Create your own Hugging Face dedicated endpoint here: https://ui.endpoints.huggingface.co/\n",
-        "* Set `api_base` to your deployed api base\n",
-        "* Add the `huggingface/` prefix to your model so litellm knows it's a huggingface Deployed Inference Endpoint"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 9,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "Lbmw8Gl_pHns",
-        "outputId": "ea8408bf-1cc3-4670-ecea-f12666d204a8"
-      },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "{\n",
-            "  \"object\": \"chat.completion\",\n",
-            "  \"choices\": [\n",
-            "    {\n",
-            "      \"finish_reason\": \"length\",\n",
-            "      \"index\": 0,\n",
-            "      \"message\": {\n",
-            "        \"content\": \"\\n\\nI am doing well, thank you for asking. How about you?\\nI am doing\",\n",
-            "        \"role\": \"assistant\",\n",
-            "        \"logprobs\": -8.9481967812\n",
-            "      }\n",
-            "    }\n",
-            "  ],\n",
-            "  \"id\": \"chatcmpl-74dc9d89-3916-47ce-9bea-b80e66660f77\",\n",
-            "  \"created\": 1695871068.8413374,\n",
-            "  \"model\": \"glaiveai/glaive-coder-7b\",\n",
-            "  \"usage\": {\n",
-            "    \"prompt_tokens\": 6,\n",
-            "    \"completion_tokens\": 18,\n",
-            "    \"total_tokens\": 24\n",
-            "  }\n",
-            "}\n"
-          ]
-        }
-      ],
-      "source": [
-        "import os\n",
-        "import litellm\n",
-        "\n",
-        "os.environ[\"HUGGINGFACE_API_KEY\"] = \"\"\n",
-        "\n",
-        "# TGI model: Call https://huggingface.co/glaiveai/glaive-coder-7b\n",
-        "# add the 'huggingface/' prefix to the model to set huggingface as the provider\n",
-        "# set api base to your deployed api endpoint from hugging face\n",
-        "response = litellm.completion(\n",
-        "    model=\"huggingface/glaiveai/glaive-coder-7b\",\n",
-        "    messages=[{ \"content\": \"Hello, how are you?\",\"role\": \"user\"}],\n",
-        "    api_base=\"https://wjiegasee9bmqke2.us-east-1.aws.endpoints.huggingface.cloud\"\n",
+        "# Call DeepSeek-R1 model through Together AI\n",
+        "response = completion(\n",
+        "    model=\"huggingface/together/deepseek-ai/DeepSeek-R1\",\n",
+        "    messages=[{\"content\": \"How many r's are in the word `strawberry`?\", \"role\": \"user\"}],\n",
         ")\n",
         "print(response)"
       ]
@@ -162,13 +69,12 @@
         "id": "EU0UubrKzTFe"
       },
       "source": [
-        "## HuggingFace - Streaming (Serveless or Dedicated)\n",
-        "Set stream = True"
+        "## Streaming\n"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 6,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -176,74 +82,147 @@
         "id": "y-QfIvA-uJKX",
         "outputId": "b007bb98-00d0-44a4-8264-c8a2caed6768"
       },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "<litellm.utils.CustomStreamWrapper object at 0x1278471d0>\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content='I', role='assistant', function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=\"'m\", role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' just', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' a', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' computer', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' program', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=',', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' so', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' I', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' don', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=\"'t\", role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' have', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' feelings', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=',', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' but', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' thank', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' you', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' for', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' asking', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content='!', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' How', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' can', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' I', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' assist', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' you', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content=' today', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content='?', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(content='<|eot_id|>', role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n",
-            "ModelResponse(id='chatcmpl-ffeb4491-624b-4ddf-8005-60358cf67d36', choices=[StreamingChoices(finish_reason='stop', index=0, delta=Delta(content=None, role=None, function_call=None, tool_calls=None), logprobs=None)], created=1724858353, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion.chunk', system_fingerprint=None)\n"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "import os\n",
-        "import litellm\n",
+        "from litellm import completion\n",
         "\n",
-        "# Make sure to create an API_KEY with inference permissions at https://huggingface.co/settings/tokens/new?globalPermissions=inference.serverless.write&tokenType=fineGrained\n",
-        "os.environ[\"HUGGINGFACE_API_KEY\"] = \"\"\n",
+        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
         "\n",
-        "# Call https://huggingface.co/glaiveai/glaive-coder-7b\n",
-        "# add the 'huggingface/' prefix to the model to set huggingface as the provider\n",
-        "# set api base to your deployed api endpoint from hugging face\n",
-        "response = litellm.completion(\n",
-        "    model=\"huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
-        "    messages=[{ \"content\": \"Hello, how are you?\",\"role\": \"user\"}],\n",
-        "    stream=True\n",
+        "response = completion(\n",
+        "    model=\"huggingface/together/deepseek-ai/DeepSeek-R1\",\n",
+        "    messages=[\n",
+        "        {\n",
+        "            \"role\": \"user\",\n",
+        "            \"content\": \"How many r's are in the word `strawberry`?\",\n",
+        "            \n",
+        "        }\n",
+        "    ],\n",
+        "    stream=True,\n",
         ")\n",
         "\n",
-        "print(response)\n",
-        "\n",
         "for chunk in response:\n",
         "    print(chunk)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## With images as input\n"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {
-        "id": "CKXAnK55zQRl"
-      },
+      "metadata": {},
       "outputs": [],
-      "source": []
+      "source": [
+        "from litellm import completion\n",
+        "\n",
+        "# Set your Hugging Face Token\n",
+        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
+        "\n",
+        "messages = [\n",
+        "    {\n",
+        "        \"role\": \"user\",\n",
+        "        \"content\": [\n",
+        "            {\"type\": \"text\", \"text\": \"What's in this image?\"},\n",
+        "            {\n",
+        "                \"type\": \"image_url\",\n",
+        "                \"image_url\": {\n",
+        "                    \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n",
+        "                },\n",
+        "            },\n",
+        "        ],\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "response = completion(\n",
+        "    model=\"huggingface/sambanova/meta-llama/Llama-3.3-70B-Instruct\",\n",
+        "    messages=messages,\n",
+        ")\n",
+        "print(response.choices[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Tools - Function Calling\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from litellm import completion\n",
+        "\n",
+        "\n",
+        "# Set your Hugging Face Token\n",
+        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
+        "\n",
+        "tools = [\n",
+        "    {\n",
+        "        \"type\": \"function\",\n",
+        "        \"function\": {\n",
+        "            \"name\": \"get_current_weather\",\n",
+        "            \"description\": \"Get the current weather in a given location\",\n",
+        "            \"parameters\": {\n",
+        "                \"type\": \"object\",\n",
+        "                \"properties\": {\n",
+        "                    \"location\": {\n",
+        "                        \"type\": \"string\",\n",
+        "                        \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
+        "                    },\n",
+        "                    \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
+        "                },\n",
+        "                \"required\": [\"location\"],\n",
+        "            },\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "messages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}]\n",
+        "\n",
+        "response = completion(\n",
+        "    model=\"huggingface/sambanova/meta-llama/Llama-3.1-8B-Instruct\", messages=messages, tools=tools, tool_choice=\"auto\"\n",
+        ")\n",
+        "print(response)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Hugging Face Dedicated Inference Endpoints\n",
+        "\n",
+        "Steps to use\n",
+        "\n",
+        "- Create your own Hugging Face dedicated endpoint here: https://ui.endpoints.huggingface.co/\n",
+        "- Set `api_base` to your deployed api base\n",
+        "- set the model to `huggingface/tgi` so that litellm knows it's a huggingface Deployed Inference Endpoint.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import litellm\n",
+        "\n",
+        "\n",
+        "response = litellm.completion(\n",
+        "    model=\"huggingface/tgi\",\n",
+        "    messages=[{\"content\": \"Hello, how are you?\", \"role\": \"user\"}],\n",
+        "    api_base=\"https://my-endpoint.endpoints.huggingface.cloud/v1/\",\n",
+        ")\n",
+        "print(response)"
+      ]
     }
   ],
   "metadata": {
@@ -251,7 +230,8 @@
       "provenance": []
     },
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": ".venv",
+      "language": "python",
       "name": "python3"
     },
     "language_info": {
@@ -264,7 +244,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.12.2"
+      "version": "3.12.0"
     }
   },
   "nbformat": 4,

cookbook/litellm-ollama-docker-image/requirements.txt

@@ -1 +1 @@
-litellm==1.55.3
+litellm==1.61.15

cookbook/misc/dev_release.txt

@@ -1,2 +1,11 @@
 python3 -m build
 twine upload --verbose dist/litellm-1.18.13.dev4.tar.gz -u __token__ - 
+
+
+Note: You might need to make a MANIFEST.ini file on root for build process incase it fails 
+
+Place this in MANIFEST.ini
+recursive-exclude venv *
+recursive-exclude myenv *
+recursive-exclude py313_env *
+recursive-exclude **/.venv *

deploy/charts/litellm-helm/Chart.yaml

@@ -18,7 +18,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.4.1
+version: 0.4.3
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

deploy/charts/litellm-helm/README.md

@@ -22,6 +22,8 @@ If `db.useStackgresOperator` is used (not yet implemented):
 | Name                                                       | Description                                                                                                                                                                           | Value |
 | ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
 | `replicaCount`                                             | The number of LiteLLM Proxy pods to be deployed                                                                                                                                       | `1`  |
+| `masterkeySecretName`                                      | The name of the Kubernetes Secret that contains the Master API Key for LiteLLM.  If not specified, use the generated secret name.                                                                                                         | N/A  |
+| `masterkeySecretKey`                                      | The key within the Kubernetes Secret that contains the Master API Key for LiteLLM.  If not specified, use `masterkey` as the key.                                                                                                         | N/A  |
 | `masterkey`                                                | The Master API Key for LiteLLM.  If not specified, a random key is generated.                                                                                                         | N/A  |
 | `environmentSecrets`                                       | An optional array of Secret object names.  The keys and values in these secrets will be presented to the LiteLLM proxy pod as environment variables.  See below for an example Secret object.  | `[]`  |
 | `environmentConfigMaps`                                       | An optional array of ConfigMap object names.  The keys and values in these configmaps will be presented to the LiteLLM proxy pod as environment variables.  See below for an example Secret object.  | `[]`  |

deploy/charts/litellm-helm/templates/deployment.yaml

@@ -78,8 +78,8 @@ spec:
             - name: PROXY_MASTER_KEY
               valueFrom:
                 secretKeyRef:
-                  name: {{ include "litellm.fullname" . }}-masterkey
-                  key: masterkey
+                  name: {{ .Values.masterkeySecretName | default (printf "%s-masterkey" (include "litellm.fullname" .)) }}
+                  key: {{ .Values.masterkeySecretKey | default "masterkey" }}
             {{- if .Values.redis.enabled }}
             - name: REDIS_HOST
               value: {{ include "litellm.redis.serviceName" . }}
@@ -97,6 +97,9 @@ spec:
               value: {{ $val | quote }}
             {{- end }}
             {{- end }}
+            {{- with .Values.extraEnvVars }}
+              {{- toYaml . | nindent 12 }}
+            {{- end }}
           envFrom:
           {{- range .Values.environmentSecrets }}
             - secretRef:

deploy/charts/litellm-helm/templates/secret-masterkey.yaml

@@ -1,3 +1,4 @@
+{{- if not .Values.masterkeySecretName }}
 {{ $masterkey := (.Values.masterkey | default (randAlphaNum 17)) }}
 apiVersion: v1
 kind: Secret
@@ -6,3 +7,4 @@ metadata:
 data:
   masterkey: {{ $masterkey | b64enc }}
 type: Opaque
+{{- end }}

deploy/charts/litellm-helm/templates/service.yaml

@@ -2,6 +2,10 @@ apiVersion: v1
 kind: Service
 metadata:
   name: {{ include "litellm.fullname" . }}
+  {{- with .Values.service.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
   labels:
     {{- include "litellm.labels" . | nindent 4 }}
 spec:

deploy/charts/litellm-helm/tests/deployment_tests.yaml

@@ -52,3 +52,66 @@ tests:
       - equal:
           path: spec.template.spec.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[0]
           value: antarctica-east1
+  - it: should work without masterkeySecretName or masterkeySecretKey
+    template: deployment.yaml
+    set:
+      masterkeySecretName: ""
+      masterkeySecretKey: ""
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: PROXY_MASTER_KEY
+            valueFrom:
+              secretKeyRef:
+                name: RELEASE-NAME-litellm-masterkey
+                key: masterkey
+  - it: should work with masterkeySecretName and masterkeySecretKey
+    template: deployment.yaml
+    set:
+      masterkeySecretName: my-secret
+      masterkeySecretKey: my-key
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: PROXY_MASTER_KEY
+            valueFrom:
+              secretKeyRef:
+                name: my-secret
+                key: my-key
+  - it: should work with extraEnvVars
+    template: deployment.yaml
+    set:
+      extraEnvVars:
+        - name: EXTRA_ENV_VAR
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.labels['env']
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: EXTRA_ENV_VAR
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['env']
+  - it: should work with both extraEnvVars and envVars
+    template: deployment.yaml
+    set:
+      envVars:
+        ENV_VAR: ENV_VAR_VALUE
+      extraEnvVars:
+        - name: EXTRA_ENV_VAR
+          value: EXTRA_ENV_VAR_VALUE
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: ENV_VAR
+            value: ENV_VAR_VALUE
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: EXTRA_ENV_VAR
+            value: EXTRA_ENV_VAR_VALUE

deploy/charts/litellm-helm/tests/masterkey-secret_tests.yaml

@@ -0,0 +1,18 @@
+suite: test masterkey secret
+templates:
+  - secret-masterkey.yaml
+tests:
+  - it: should create a secret if masterkeySecretName is not set
+    template: secret-masterkey.yaml
+    set:
+      masterkeySecretName: ""
+    asserts:
+      - isKind:
+          of: Secret
+  - it: should not create a secret if masterkeySecretName is set
+    template: secret-masterkey.yaml
+    set:
+      masterkeySecretName: my-secret
+    asserts:
+      - hasDocuments:
+          count: 0

deploy/charts/litellm-helm/values.yaml

@@ -75,6 +75,12 @@ ingress:
 
 # masterkey: changeit
 
+# if set, use this secret for the master key; otherwise, autogenerate a new one
+masterkeySecretName: ""
+
+# if set, use this secret key for the master key; otherwise, use the default key
+masterkeySecretKey: ""
+
 # The elements within proxy_config are rendered as config.yaml for the proxy
 #  Examples: https://github.com/BerriAI/litellm/tree/main/litellm/proxy/example_config_yaml
 #  Reference: https://docs.litellm.ai/docs/proxy/configs
@@ -189,9 +195,15 @@ migrationJob:
   annotations: {}
   ttlSecondsAfterFinished: 120
 
-# Additional environment variables to be added to the deployment
+# Additional environment variables to be added to the deployment as a map of key-value pairs
 envVars: {
     # USE_DDTRACE: "true"
 }
 
+# Additional environment variables to be added to the deployment as a list of k8s env vars
+extraEnvVars: {
+    # - name: EXTRA_ENV_VAR
+    #   value: EXTRA_ENV_VAR_VALUE
+}
+
 

docker-compose.yml

@@ -66,5 +66,3 @@ volumes:
   postgres_data:
     name: litellm_postgres_data  # Named volume for Postgres data persistence
 
-
-# ...rest of your docker-compose config if any

docker/Dockerfile.alpine

@@ -35,7 +35,7 @@ RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
 # Update dependencies and clean up
-RUN apk update && apk upgrade && rm -rf /var/cache/apk/*
+RUN apk upgrade --no-cache
 
 WORKDIR /app
 

docker/Dockerfile.database

@@ -12,8 +12,7 @@ WORKDIR /app
 USER root
 
 # Install build dependencies
-RUN apk update && \
-    apk add --no-cache gcc python3-dev openssl openssl-dev
+RUN apk add --no-cache gcc python3-dev openssl openssl-dev
 
 
 RUN pip install --upgrade pip && \
@@ -44,8 +43,7 @@ FROM $LITELLM_RUNTIME_IMAGE AS runtime
 USER root
 
 # Install runtime dependencies
-RUN apk update && \
-    apk add --no-cache openssl
+RUN apk add --no-cache openssl
 
 WORKDIR /app
 # Copy the current directory contents into the container at /app
@@ -59,9 +57,6 @@ COPY --from=builder /wheels/ /wheels/
 # Install the built wheel using pip; again using a wildcard if it's the only file
 RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ && rm -f *.whl && rm -rf /wheels
 
-# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0 
-RUN pip install redisvl==0.0.7 --no-deps
-
 # ensure pyjwt is used, not jwt
 RUN pip uninstall jwt -y
 RUN pip uninstall PyJWT -y

docker/Dockerfile.non_root

@@ -14,7 +14,7 @@ SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 
 # Install build dependencies
 RUN apt-get clean && apt-get update && \
-    apt-get install -y gcc python3-dev && \
+    apt-get install -y gcc g++ python3-dev && \
     rm -rf /var/lib/apt/lists/*
 
 RUN pip install --no-cache-dir --upgrade pip && \
@@ -56,10 +56,8 @@ COPY --from=builder /wheels/ /wheels/
 # Install the built wheel using pip; again using a wildcard if it's the only file
 RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ && rm -f *.whl && rm -rf /wheels
 
-# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0
 # ensure pyjwt is used, not jwt
-RUN pip install redisvl==0.0.7 --no-deps --no-cache-dir && \
-    pip uninstall jwt -y && \
+RUN pip uninstall jwt -y && \
     pip uninstall PyJWT -y && \
     pip install PyJWT==2.9.0 --no-cache-dir
 

docs/my-website/docs/anthropic_unified.md

@@ -3,9 +3,10 @@ import TabItem from '@theme/TabItem';
 
 # /v1/messages [BETA] 
 
-LiteLLM provides a BETA endpoint in the spec of Anthropic's `/v1/messages` endpoint. 
+Use LiteLLM to call all your LLM APIs in the Anthropic `v1/messages` format. 
 
-This currently just supports the Anthropic API. 
+
+## Overview 
 
 | Feature | Supported | Notes | 
 |-------|-------|-------|
@@ -21,9 +22,61 @@ Planned improvement:
 - Bedrock Anthropic support
 
 ## Usage 
+---
+
+### LiteLLM Python SDK 
+
+#### Non-streaming example
+```python showLineNumbers title="Example using LiteLLM Python SDK"
+import litellm
+response = await litellm.anthropic.messages.acreate(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    api_key=api_key,
+    model="anthropic/claude-3-haiku-20240307",
+    max_tokens=100,
+)
+```
+
+Example response:
+```json
+{
+  "content": [
+    {
+      "text": "Hi! this is a very short joke",
+      "type": "text"
+    }
+  ],
+  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
+  "model": "claude-3-7-sonnet-20250219",
+  "role": "assistant",
+  "stop_reason": "end_turn",
+  "stop_sequence": null,
+  "type": "message",
+  "usage": {
+    "input_tokens": 2095,
+    "output_tokens": 503,
+    "cache_creation_input_tokens": 2095,
+    "cache_read_input_tokens": 0
+  }
+}
+```
+
+#### Streaming example
+```python showLineNumbers title="Example using LiteLLM Python SDK"
+import litellm
+response = await litellm.anthropic.messages.acreate(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    api_key=api_key,
+    model="anthropic/claude-3-haiku-20240307",
+    max_tokens=100,
+    stream=True,
+)
+async for chunk in response:
+    print(chunk)
+```
+
+### LiteLLM Proxy Server 
 
-<Tabs>
-<TabItem label="PROXY" value="proxy">
 
 1. Setup config.yaml
 
@@ -42,7 +95,28 @@ litellm --config /path/to/config.yaml
 
 3. Test it! 
 
-```bash
+<Tabs>
+<TabItem label="Anthropic Python SDK" value="python">
+
+```python showLineNumbers title="Example using LiteLLM Proxy Server"
+import anthropic
+
+# point anthropic sdk to litellm proxy 
+client = anthropic.Anthropic(
+    base_url="http://0.0.0.0:4000",
+    api_key="sk-1234",
+)
+
+response = client.messages.create(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    model="anthropic-claude",
+    max_tokens=100,
+)
+```
+</TabItem>
+<TabItem label="curl" value="curl">
+
+```bash showLineNumbers title="Example using LiteLLM Proxy Server"
 curl -L -X POST 'http://0.0.0.0:4000/v1/messages' \
 -H 'content-type: application/json' \
 -H 'x-api-key: $LITELLM_API_KEY' \
@@ -52,41 +126,176 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/messages' \
   "messages": [
     {
       "role": "user",
-      "content": [
-        {
-          "type": "text",
-          "text": "List 5 important events in the XIX century"
-        }
-      ]
+      "content": "Hello, can you tell me a short joke?"
     }
   ],
-  "max_tokens": 4096
+  "max_tokens": 100
 }'
 ```
-</TabItem>
-<TabItem value="sdk" label="SDK">
-
-```python
-from litellm.llms.anthropic.experimental_pass_through.messages.handler import anthropic_messages
-import asyncio 
-import os 
-
-# set env 
-os.environ["ANTHROPIC_API_KEY"] = "my-api-key"
-
-messages = [{"role": "user", "content": "Hello, can you tell me a short joke?"}]
-
-# Call the handler
-async def call(): 
-    response = await anthropic_messages(
-        messages=messages,
-        api_key=api_key,
-        model="claude-3-haiku-20240307",
-        max_tokens=100,
-    )
-
-asyncio.run(call())
-```
 
 </TabItem>
 </Tabs>
+
+
+## Request Format
+---
+
+Request body will be in the Anthropic messages API format. **litellm follows the Anthropic messages specification for this endpoint.**
+
+#### Example request body
+
+```json
+{
+  "model": "claude-3-7-sonnet-20250219",
+  "max_tokens": 1024,
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello, world"
+    }
+  ]
+}
+```
+
+#### Required Fields
+- **model** (string):  
+  The model identifier (e.g., `"claude-3-7-sonnet-20250219"`).
+- **max_tokens** (integer):  
+  The maximum number of tokens to generate before stopping.  
+  _Note: The model may stop before reaching this limit; value must be greater than 1._
+- **messages** (array of objects):  
+  An ordered list of conversational turns.  
+  Each message object must include:
+  - **role** (enum: `"user"` or `"assistant"`):  
+    Specifies the speaker of the message.
+  - **content** (string or array of content blocks):  
+    The text or content blocks (e.g., an array containing objects with a `type` such as `"text"`) that form the message.  
+    _Example equivalence:_
+    ```json
+    {"role": "user", "content": "Hello, Claude"}
+    ```
+    is equivalent to:
+    ```json
+    {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]}
+    ```
+
+#### Optional Fields
+- **metadata** (object):  
+  Contains additional metadata about the request (e.g., `user_id` as an opaque identifier).
+- **stop_sequences** (array of strings):  
+  Custom sequences that, when encountered in the generated text, cause the model to stop.
+- **stream** (boolean):  
+  Indicates whether to stream the response using server-sent events.
+- **system** (string or array):  
+  A system prompt providing context or specific instructions to the model.
+- **temperature** (number):  
+  Controls randomness in the model’s responses. Valid range: `0 < temperature < 1`.
+- **thinking** (object):  
+  Configuration for enabling extended thinking. If enabled, it includes:
+  - **budget_tokens** (integer):  
+    Minimum of 1024 tokens (and less than `max_tokens`).
+  - **type** (enum):  
+    E.g., `"enabled"`.
+- **tool_choice** (object):  
+  Instructs how the model should utilize any provided tools.
+- **tools** (array of objects):  
+  Definitions for tools available to the model. Each tool includes:
+  - **name** (string):  
+    The tool’s name.
+  - **description** (string):  
+    A detailed description of the tool.
+  - **input_schema** (object):  
+    A JSON schema describing the expected input format for the tool.
+- **top_k** (integer):  
+  Limits sampling to the top K options.
+- **top_p** (number):  
+  Enables nucleus sampling with a cumulative probability cutoff. Valid range: `0 < top_p < 1`.
+
+
+## Response Format
+---
+
+Responses will be in the Anthropic messages API format.
+
+#### Example Response
+
+```json
+{
+  "content": [
+    {
+      "text": "Hi! My name is Claude.",
+      "type": "text"
+    }
+  ],
+  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
+  "model": "claude-3-7-sonnet-20250219",
+  "role": "assistant",
+  "stop_reason": "end_turn",
+  "stop_sequence": null,
+  "type": "message",
+  "usage": {
+    "input_tokens": 2095,
+    "output_tokens": 503,
+    "cache_creation_input_tokens": 2095,
+    "cache_read_input_tokens": 0
+  }
+}
+```
+
+#### Response fields
+
+- **content** (array of objects):  
+  Contains the generated content blocks from the model. Each block includes:
+  - **type** (string):  
+    Indicates the type of content (e.g., `"text"`, `"tool_use"`, `"thinking"`, or `"redacted_thinking"`).
+  - **text** (string):  
+    The generated text from the model.  
+    _Note: Maximum length is 5,000,000 characters._
+  - **citations** (array of objects or `null`):  
+    Optional field providing citation details. Each citation includes:
+    - **cited_text** (string):  
+      The excerpt being cited.
+    - **document_index** (integer):  
+      An index referencing the cited document.
+    - **document_title** (string or `null`):  
+      The title of the cited document.
+    - **start_char_index** (integer):  
+      The starting character index for the citation.
+    - **end_char_index** (integer):  
+      The ending character index for the citation.
+    - **type** (string):  
+      Typically `"char_location"`.
+
+- **id** (string):  
+  A unique identifier for the response message.  
+  _Note: The format and length of IDs may change over time._
+
+- **model** (string):  
+  Specifies the model that generated the response.
+
+- **role** (string):  
+  Indicates the role of the generated message. For responses, this is always `"assistant"`.
+
+- **stop_reason** (string):  
+  Explains why the model stopped generating text. Possible values include:
+  - `"end_turn"`: The model reached a natural stopping point.
+  - `"max_tokens"`: The generation stopped because the maximum token limit was reached.
+  - `"stop_sequence"`: A custom stop sequence was encountered.
+  - `"tool_use"`: The model invoked one or more tools.
+
+- **stop_sequence** (string or `null`):  
+  Contains the specific stop sequence that caused the generation to halt, if applicable; otherwise, it is `null`.
+
+- **type** (string):  
+  Denotes the type of response object, which is always `"message"`.
+
+- **usage** (object):  
+  Provides details on token usage for billing and rate limiting. This includes:
+  - **input_tokens** (integer):  
+    Total number of input tokens processed.
+  - **output_tokens** (integer):  
+    Total number of output tokens generated.
+  - **cache_creation_input_tokens** (integer or `null`):  
+    Number of tokens used to create a cache entry.
+  - **cache_read_input_tokens** (integer or `null`):  
+    Number of tokens read from the cache.

docs/my-website/docs/caching/all_caches.md

@@ -3,7 +3,7 @@ import TabItem from '@theme/TabItem';
 
 # Caching - In-Memory, Redis, s3, Redis Semantic Cache, Disk
 
-[**See Code**](https://github.com/BerriAI/litellm/blob/main/litellm.caching.caching.py)
+[**See Code**](https://github.com/BerriAI/litellm/blob/main/litellm/caching/caching.py)
 
 :::info
 
@@ -26,7 +26,7 @@ Install redis
 pip install redis
 ```
 
-For the hosted version you can setup your own Redis DB here: https://app.redislabs.com/
+For the hosted version you can setup your own Redis DB here: https://redis.io/try-free/
 
 ```python
 import litellm
@@ -91,12 +91,12 @@ response2 = completion(
 
 <TabItem value="redis-sem" label="redis-semantic cache">
 
-Install redis
+Install redisvl client
 ```shell
-pip install redisvl==0.0.7
+pip install redisvl==0.4.1
 ```
 
-For the hosted version you can setup your own Redis DB here: https://app.redislabs.com/
+For the hosted version you can setup your own Redis DB here: https://redis.io/try-free/
 
 ```python
 import litellm
@@ -114,6 +114,7 @@ litellm.cache = Cache(
     port=os.environ["REDIS_PORT"],
     password=os.environ["REDIS_PASSWORD"],
     similarity_threshold=0.8, # similarity threshold for cache hits, 0 == no similarity, 1 = exact matches, 0.5 == 50% similarity
+    ttl=120,
     redis_semantic_cache_embedding_model="text-embedding-ada-002", # this model is passed to litellm.embedding(), any litellm.embedding() model is supported here
 )
 response1 = completion(
@@ -471,11 +472,13 @@ def __init__(
     password: Optional[str] = None,
     namespace: Optional[str] = None,
     default_in_redis_ttl: Optional[float] = None,
-    similarity_threshold: Optional[float] = None,
-    redis_semantic_cache_use_async=False,
-    redis_semantic_cache_embedding_model="text-embedding-ada-002",
     redis_flush_size=None,
 
+    # redis semantic cache params
+    similarity_threshold: Optional[float] = None,
+    redis_semantic_cache_embedding_model: str = "text-embedding-ada-002",
+    redis_semantic_cache_index_name: Optional[str] = None,
+
     # s3 Bucket, boto3 configuration
     s3_bucket_name: Optional[str] = None,
     s3_region_name: Optional[str] = None,

docs/my-website/docs/completion/document_understanding.md

@@ -27,16 +27,18 @@ os.environ["AWS_REGION_NAME"] = ""
 
 
 # pdf url
-image_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
+file_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
 
 # model
 model = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
 
-image_content = [
+file_content = [
     {"type": "text", "text": "What's this file about?"},
     {
-        "type": "image_url",
-        "image_url": image_url, # OR {"url": image_url}
+        "type": "file",
+        "file": {
+            "file_id": file_url,
+        }
     },
 ]
 
@@ -46,7 +48,7 @@ if not supports_pdf_input(model, None):
 
 response = completion(
     model=model,
-    messages=[{"role": "user", "content": image_content}],
+    messages=[{"role": "user", "content": file_content}],
 )
 assert response is not None
 ```
@@ -80,11 +82,15 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 -d '{
     "model": "bedrock-model",
     "messages": [
-        {"role": "user", "content": {"type": "text", "text": "What's this file about?"}},
+        {"role": "user", "content": [
+            {"type": "text", "text": "What's this file about?"},
             {
-            "type": "image_url",
-            "image_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
+                "type": "file",
+                "file": {
+                    "file_id": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
                 }
+            }
+        ]},
     ]
 }'
 ```
@@ -116,11 +122,13 @@ base64_url = f"data:application/pdf;base64,{encoded_file}"
 # model
 model = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
 
-image_content = [
+file_content = [
     {"type": "text", "text": "What's this file about?"},
     {
-        "type": "image_url",
-        "image_url": base64_url, # OR {"url": base64_url}
+        "type": "file",
+        "file": {
+            "file_data": base64_url,
+        }
     },
 ]
 
@@ -130,11 +138,53 @@ if not supports_pdf_input(model, None):
 
 response = completion(
     model=model,
-    messages=[{"role": "user", "content": image_content}],
+    messages=[{"role": "user", "content": file_content}],
 )
 assert response is not None
 ```
 </TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: bedrock-model
+    litellm_params:
+      model: bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
+      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
+      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
+      aws_region_name: os.environ/AWS_REGION_NAME
+```
+
+2. Start the proxy 
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "bedrock-model",
+    "messages": [
+        {"role": "user", "content": [
+            {"type": "text", "text": "What's this file about?"},
+            {
+                "type": "file",
+                "file": {
+                    "file_data": "data:application/pdf;base64...",
+                }
+            }
+        ]},
+    ]
+}'
+```
+</TabItem>
 </Tabs>
 
 ## Checking if a model supports pdf input

docs/my-website/docs/completion/drop_params.md

@@ -108,3 +108,75 @@ response = litellm.completion(
 </Tabs>
 
 **additional_drop_params**: List or null - Is a list of openai params you want to drop when making a call to the model.
+
+## Specify allowed openai params in a request
+
+Tell litellm to allow specific openai params in a request. Use this if you get a `litellm.UnsupportedParamsError` and want to allow a param. LiteLLM will pass the param as is to the model.
+
+
+
+<Tabs>
+<TabItem value="sdk" label="LiteLLM Python SDK">
+
+In this example we pass `allowed_openai_params=["tools"]` to allow the `tools` param.
+
+```python showLineNumbers title="Pass allowed_openai_params to LiteLLM Python SDK"
+await litellm.acompletion(
+    model="azure/o_series/<my-deployment-name>",
+    api_key="xxxxx",
+    api_base=api_base,
+    messages=[{"role": "user", "content": "Hello! return a json object"}],
+    tools=[{"type": "function", "function": {"name": "get_current_time", "description": "Get the current time in a given location.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city name, e.g. San Francisco"}}, "required": ["location"]}}}]
+    allowed_openai_params=["tools"],
+)
+```
+</TabItem>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+When using litellm proxy you can pass `allowed_openai_params` in two ways:
+
+1. Dynamically pass `allowed_openai_params` in a request
+2. Set `allowed_openai_params` on the config.yaml file for a specific model
+
+#### Dynamically pass allowed_openai_params in a request
+In this example we pass `allowed_openai_params=["tools"]` to allow the `tools` param for a request sent to the model set on the proxy.
+
+```python showLineNumbers title="Dynamically pass allowed_openai_params in a request"
+import openai
+from openai import AsyncAzureOpenAI
+
+import openai
+client = openai.OpenAI(
+    api_key="anything",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.chat.completions.create(
+    model="gpt-3.5-turbo",
+    messages = [
+        {
+            "role": "user",
+            "content": "this is a test request, write a short poem"
+        }
+    ],
+    extra_body={ 
+        "allowed_openai_params": ["tools"]
+    }
+)
+```
+
+#### Set allowed_openai_params on config.yaml
+
+You can also set `allowed_openai_params` on the config.yaml file for a specific model. This means that all requests to this deployment are allowed to pass in the `tools` param.
+
+```yaml showLineNumbers title="Set allowed_openai_params on config.yaml"
+model_list:
+  - model_name: azure-o1-preview
+    litellm_params:
+      model: azure/o_series/<my-deployment-name>
+      api_key: xxxxx
+      api_base: https://openai-prod-test.openai.azure.com/openai/deployments/o1/chat/completions?api-version=2025-01-01-preview
+      allowed_openai_params: ["tools"]
+```
+</TabItem>
+</Tabs>

docs/my-website/docs/completion/prompt_caching.md

@@ -4,7 +4,7 @@ import TabItem from '@theme/TabItem';
 # Prompt Caching 
 
 Supported Providers:
-- OpenAI (`deepseek/`)
+- OpenAI (`openai/`)
 - Anthropic API (`anthropic/`)
 - Bedrock (`bedrock/`, `bedrock/invoke/`, `bedrock/converse`) ([All models bedrock supports prompt caching on](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html))
 - Deepseek API (`deepseek/`)

docs/my-website/docs/completion/web_search.md

@@ -0,0 +1,308 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Using Web Search
+
+Use web search with litellm
+
+| Feature | Details |
+|---------|---------|
+| Supported Endpoints | - `/chat/completions` <br/> - `/responses` |
+| Supported Providers | `openai` |
+| LiteLLM Cost Tracking | ✅ Supported |
+| LiteLLM Version | `v1.63.15-nightly` or higher |
+
+
+## `/chat/completions` (litellm.completion)
+
+### Quick Start
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+from litellm import completion
+
+response = completion(
+    model="openai/gpt-4o-search-preview",
+    messages=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?",
+        }
+    ],
+)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: gpt-4o-search-preview
+    litellm_params:
+      model: openai/gpt-4o-search-preview
+      api_key: os.environ/OPENAI_API_KEY
+```
+
+2. Start the proxy 
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```python showLineNumbers
+from openai import OpenAI
+
+# Point to your proxy server
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.chat.completions.create(
+    model="gpt-4o-search-preview",
+    messages=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?"
+        }
+    ]
+)
+```
+</TabItem>
+</Tabs>
+
+### Search context size
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+from litellm import completion
+
+# Customize search context size
+response = completion(
+    model="openai/gpt-4o-search-preview",
+    messages=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?",
+        }
+    ],
+    web_search_options={
+        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
+    }
+)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```python showLineNumbers
+from openai import OpenAI
+
+# Point to your proxy server
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+# Customize search context size
+response = client.chat.completions.create(
+    model="gpt-4o-search-preview",
+    messages=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?"
+        }
+    ],
+    web_search_options={
+        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
+    }
+)
+```
+</TabItem>
+</Tabs>
+
+## `/responses` (litellm.responses)
+
+### Quick Start
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+from litellm import responses
+
+response = responses(
+    model="openai/gpt-4o",
+    input=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?"
+        }
+    ],
+    tools=[{
+        "type": "web_search_preview"  # enables web search with default medium context size
+    }]
+)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: openai/gpt-4o
+      api_key: os.environ/OPENAI_API_KEY
+```
+
+2. Start the proxy 
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```python showLineNumbers
+from openai import OpenAI
+
+# Point to your proxy server
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.responses.create(
+    model="gpt-4o",
+    tools=[{
+        "type": "web_search_preview"
+    }],
+    input="What was a positive news story from today?",
+)
+
+print(response.output_text)
+```
+</TabItem>
+</Tabs>
+
+### Search context size
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+from litellm import responses
+
+# Customize search context size
+response = responses(
+    model="openai/gpt-4o",
+    input=[
+        {
+            "role": "user",
+            "content": "What was a positive news story from today?"
+        }
+    ],
+    tools=[{
+        "type": "web_search_preview",
+        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
+    }]
+)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```python showLineNumbers
+from openai import OpenAI
+
+# Point to your proxy server
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+# Customize search context size
+response = client.responses.create(
+    model="gpt-4o",
+    tools=[{
+        "type": "web_search_preview",
+        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
+    }],
+    input="What was a positive news story from today?",
+)
+
+print(response.output_text)
+```
+</TabItem>
+</Tabs>
+
+
+
+
+
+
+## Checking if a model supports web search
+
+<Tabs>
+<TabItem label="SDK" value="sdk">
+
+Use `litellm.supports_web_search(model="openai/gpt-4o-search-preview")` -> returns `True` if model can perform web searches
+
+```python showLineNumbers
+assert litellm.supports_web_search(model="openai/gpt-4o-search-preview") == True
+```
+</TabItem>
+
+<TabItem label="PROXY" value="proxy">
+
+1. Define OpenAI models in config.yaml
+
+```yaml
+model_list:
+  - model_name: gpt-4o-search-preview
+    litellm_params:
+      model: openai/gpt-4o-search-preview
+      api_key: os.environ/OPENAI_API_KEY
+    model_info:
+      supports_web_search: True
+```
+
+2. Run proxy server
+
+```bash
+litellm --config config.yaml
+```
+
+3. Call `/model_group/info` to check if a model supports web search
+
+```shell
+curl -X 'GET' \
+  'http://localhost:4000/model_group/info' \
+  -H 'accept: application/json' \
+  -H 'x-api-key: sk-1234'
+```
+
+Expected Response 
+
+```json showLineNumbers
+{
+  "data": [
+    {
+      "model_group": "gpt-4o-search-preview",
+      "providers": ["openai"],
+      "max_tokens": 128000,
+      "supports_web_search": true, # 👈 supports_web_search is true
+    }
+  ]
+}
+```
+
+</TabItem>
+</Tabs>

docs/my-website/docs/enterprise.md

@@ -1,3 +1,5 @@
+import Image from '@theme/IdealImage';
+
 # Enterprise
 For companies that need SSO, user management and professional support for LiteLLM Proxy
 
@@ -7,6 +9,8 @@ Get free 7-day trial key [here](https://www.litellm.ai/#trial)
 
 Includes all enterprise features.
 
+<Image img={require('../img/enterprise_vs_oss.png')} />
+
 [**Procurement available via AWS / Azure Marketplace**](./data_security.md#legalcompliance-faqs)
 
 
@@ -34,9 +38,9 @@ You can use our cloud product where we setup a dedicated instance for you.
 
 Professional Support can assist with LLM/Provider integrations, deployment, upgrade management, and LLM Provider troubleshooting.  We can’t solve your own infrastructure-related issues but we will guide you to fix them.
 
-- 1 hour for Sev0 issues
-- 6 hours for Sev1
-- 24h for Sev2-Sev3 between 7am – 7pm PT (Monday through Saturday)
+- 1 hour for Sev0 issues - 100% production traffic is failing
+- 6 hours for Sev1 - <100% production traffic is failing
+- 24h for Sev2-Sev3 between 7am – 7pm PT (Monday through Saturday) - setup issues e.g. Redis working on our end, but not on your infrastructure.
 - 72h SLA for patching vulnerabilities in the software. 
 
 **We can offer custom SLAs** based on your needs and the severity of the issue

docs/my-website/docs/files_endpoints.md

@@ -2,10 +2,12 @@
 import TabItem from '@theme/TabItem';
 import Tabs from '@theme/Tabs';
 
-# /files
+# Provider Files Endpoints
 
 Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.
 
+Use this to call the provider's `/files` endpoints directly, in the OpenAI format. 
+
 ## Quick Start
 
 - Upload a File
@@ -14,48 +16,105 @@ Files are used to upload documents that can be used with features like Assistant
 - Delete File
 - Get File Content
 
+
+
 <Tabs>
 <TabItem value="proxy" label="LiteLLM PROXY Server">
 
-```bash
-$ export OPENAI_API_KEY="sk-..."
+1. Setup config.yaml
 
-$ litellm
-
-# RUNNING on http://0.0.0.0:4000
+```
+# for /files endpoints
+files_settings:
+  - custom_llm_provider: azure
+    api_base: https://exampleopenaiendpoint-production.up.railway.app
+    api_key: fake-key
+    api_version: "2023-03-15-preview"
+  - custom_llm_provider: openai
+    api_key: os.environ/OPENAI_API_KEY
 ```
 
-**Upload a File**
+2. Start LiteLLM PROXY Server
+
 ```bash
-curl http://localhost:4000/v1/files \
-  -H "Authorization: Bearer sk-1234" \
-  -F purpose="fine-tune" \
-  -F file="@mydata.jsonl"
+litellm --config /path/to/config.yaml
+
+## RUNNING on http://0.0.0.0:4000
 ```
 
-**List Files**
-```bash
-curl http://localhost:4000/v1/files \
-  -H "Authorization: Bearer sk-1234"
+3. Use OpenAI's /files endpoints
+
+Upload a File
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-...",
+    base_url="http://0.0.0.0:4000/v1"
+)
+
+client.files.create(
+    file=wav_data,
+    purpose="user_data",
+    extra_body={"custom_llm_provider": "openai"}
+)
 ```
 
-**Retrieve File Information**
-```bash
-curl http://localhost:4000/v1/files/file-abc123 \
-  -H "Authorization: Bearer sk-1234"
+List Files
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-...",
+    base_url="http://0.0.0.0:4000/v1"
+)
+
+files = client.files.list(extra_body={"custom_llm_provider": "openai"})
+print("files=", files)
 ```
 
-**Delete File**
-```bash
-curl http://localhost:4000/v1/files/file-abc123 \
-  -X DELETE \
-  -H "Authorization: Bearer sk-1234"
+Retrieve File Information
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-...",
+    base_url="http://0.0.0.0:4000/v1"
+)
+
+file = client.files.retrieve(file_id="file-abc123", extra_body={"custom_llm_provider": "openai"})
+print("file=", file)
 ```
 
-**Get File Content**
-```bash
-curl http://localhost:4000/v1/files/file-abc123/content \
-  -H "Authorization: Bearer sk-1234"
+Delete File
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-...",
+    base_url="http://0.0.0.0:4000/v1"
+)
+
+response = client.files.delete(file_id="file-abc123", extra_body={"custom_llm_provider": "openai"})
+print("delete response=", response)
+```
+
+Get File Content
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-...",
+    base_url="http://0.0.0.0:4000/v1"
+)
+
+content = client.files.content(file_id="file-abc123", extra_body={"custom_llm_provider": "openai"})
+print("content=", content)
 ```
 
 </TabItem>
@@ -120,7 +179,7 @@ print("file content=", content)
 
 ### [OpenAI](#quick-start)
 
-## [Azure OpenAI](./providers/azure#azure-batches-api)
+### [Azure OpenAI](./providers/azure#azure-batches-api)
 
 ### [Vertex AI](./providers/vertex#batch-apis)
 

docs/my-website/docs/guides/security_settings.md

@@ -0,0 +1,66 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# SSL Security Settings
+
+If you're in an environment using an older TTS bundle, with an older encryption, follow this guide. 
+
+
+LiteLLM uses HTTPX for network requests, unless otherwise specified. 
+
+1. Disable SSL verification
+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm
+litellm.ssl_verify = False
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```yaml
+litellm_settings:
+  ssl_verify: false
+```
+
+</TabItem>  
+<TabItem value="env_var" label="Environment Variables">
+
+```bash
+export SSL_VERIFY="False"
+```
+</TabItem>
+</Tabs>
+
+2. Lower security settings
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm
+litellm.ssl_security_level = 1
+litellm.ssl_certificate = "/path/to/certificate.pem"
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```yaml
+litellm_settings:
+  ssl_security_level: 1
+  ssl_certificate: "/path/to/certificate.pem"
+```
+</TabItem>
+<TabItem value="env_var" label="Environment Variables">
+
+```bash
+export SSL_SECURITY_LEVEL="1"
+export SSL_CERTIFICATE="/path/to/certificate.pem"
+```
+</TabItem>
+</Tabs>
+
+

docs/my-website/docs/index.md

@@ -111,8 +111,8 @@ from litellm import completion
 import os
 
 # auth: run 'gcloud auth application-default'
-os.environ["VERTEX_PROJECT"] = "hardy-device-386718"
-os.environ["VERTEX_LOCATION"] = "us-central1"
+os.environ["VERTEXAI_PROJECT"] = "hardy-device-386718"
+os.environ["VERTEXAI_LOCATION"] = "us-central1"
 
 response = completion(
   model="vertex_ai/gemini-1.5-pro",

docs/my-website/docs/mcp.md

@@ -0,0 +1,427 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import Image from '@theme/IdealImage';
+
+# /mcp [BETA] - Model Context Protocol
+
+## Expose MCP tools on LiteLLM Proxy Server
+
+This allows you to define tools that can be called by any MCP compatible client. Define your `mcp_servers` with LiteLLM and all your clients can list and call available tools.
+
+<Image 
+  img={require('../img/mcp_2.png')}
+  style={{width: '100%', display: 'block', margin: '2rem auto'}}
+/>
+<p style={{textAlign: 'left', color: '#666'}}>
+  LiteLLM MCP Architecture: Use MCP tools with all LiteLLM supported models
+</p>
+
+#### How it works
+
+LiteLLM exposes the following MCP endpoints:
+
+- `/mcp/tools/list` - List all available tools
+- `/mcp/tools/call` - Call a specific tool with the provided arguments
+
+When MCP clients connect to LiteLLM they can follow this workflow:
+
+1. Connect to the LiteLLM MCP server
+2. List all available tools on LiteLLM
+3. Client makes LLM API request with tool call(s)
+4. LLM API returns which tools to call and with what arguments
+5. MCP client makes MCP tool calls to LiteLLM
+6. LiteLLM makes the tool calls to the appropriate MCP server
+7. LiteLLM returns the tool call results to the MCP client
+
+#### Usage
+
+#### 1. Define your tools on under `mcp_servers` in your config.yaml file.
+
+LiteLLM allows you to define your tools on the `mcp_servers` section in your config.yaml file. All tools listed here will be available to MCP clients (when they connect to LiteLLM and call `list_tools`).
+
+```yaml title="config.yaml" showLineNumbers
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: openai/gpt-4o
+      api_key: sk-xxxxxxx
+
+mcp_servers:
+  {
+    "zapier_mcp": {
+      "url": "https://actions.zapier.com/mcp/sk-akxxxxx/sse"
+    },
+    "fetch": {
+      "url": "http://localhost:8000/sse"
+    }
+  }
+```
+
+
+#### 2. Start LiteLLM Gateway
+
+<Tabs>
+<TabItem value="docker" label="Docker Run">
+
+```shell title="Docker Run" showLineNumbers
+docker run -d \
+  -p 4000:4000 \
+  -e OPENAI_API_KEY=$OPENAI_API_KEY \
+  --name my-app \
+  -v $(pwd)/my_config.yaml:/app/config.yaml \
+  my-app:latest \
+  --config /app/config.yaml \
+  --port 4000 \
+  --detailed_debug \
+```
+
+</TabItem>
+
+<TabItem value="py" label="litellm pip">
+
+```shell title="litellm pip" showLineNumbers
+litellm --config config.yaml --detailed_debug
+```
+
+</TabItem>
+</Tabs>
+
+
+#### 3. Make an LLM API request 
+
+In this example we will do the following:
+
+1. Use MCP client to list MCP tools on LiteLLM Proxy
+2. Use `transform_mcp_tool_to_openai_tool` to convert MCP tools to OpenAI tools
+3. Provide the MCP tools to `gpt-4o`
+4. Handle tool call from `gpt-4o`
+5. Convert OpenAI tool call to MCP tool call
+6. Execute tool call on MCP server
+
+```python title="MCP Client List Tools" showLineNumbers
+import asyncio
+from openai import AsyncOpenAI
+from openai.types.chat import ChatCompletionUserMessageParam
+from mcp import ClientSession
+from mcp.client.sse import sse_client
+from litellm.experimental_mcp_client.tools import (
+    transform_mcp_tool_to_openai_tool,
+    transform_openai_tool_call_request_to_mcp_tool_call_request,
+)
+
+
+async def main():
+    # Initialize clients
+    
+    # point OpenAI client to LiteLLM Proxy
+    client = AsyncOpenAI(api_key="sk-1234", base_url="http://localhost:4000")
+
+    # Point MCP client to LiteLLM Proxy
+    async with sse_client("http://localhost:4000/mcp/") as (read, write):
+        async with ClientSession(read, write) as session:
+            await session.initialize()
+
+            # 1. List MCP tools on LiteLLM Proxy
+            mcp_tools = await session.list_tools()
+            print("List of MCP tools for MCP server:", mcp_tools.tools)
+
+            # Create message
+            messages = [
+                ChatCompletionUserMessageParam(
+                    content="Send an email about LiteLLM supporting MCP", role="user"
+                )
+            ]
+
+            # 2. Use `transform_mcp_tool_to_openai_tool` to convert MCP tools to OpenAI tools
+            # Since OpenAI only supports tools in the OpenAI format, we need to convert the MCP tools to the OpenAI format.
+            openai_tools = [
+                transform_mcp_tool_to_openai_tool(tool) for tool in mcp_tools.tools
+            ]
+
+            # 3. Provide the MCP tools to `gpt-4o`
+            response = await client.chat.completions.create(
+                model="gpt-4o",
+                messages=messages,
+                tools=openai_tools,
+                tool_choice="auto",
+            )
+
+            # 4. Handle tool call from `gpt-4o`
+            if response.choices[0].message.tool_calls:
+                tool_call = response.choices[0].message.tool_calls[0]
+                if tool_call:
+
+                    # 5. Convert OpenAI tool call to MCP tool call
+                    # Since MCP servers expect tools in the MCP format, we need to convert the OpenAI tool call to the MCP format.
+                    # This is done using litellm.experimental_mcp_client.tools.transform_openai_tool_call_request_to_mcp_tool_call_request
+                    mcp_call = (
+                        transform_openai_tool_call_request_to_mcp_tool_call_request(
+                            openai_tool=tool_call.model_dump()
+                        )
+                    )
+
+                    # 6. Execute tool call on MCP server
+                    result = await session.call_tool(
+                        name=mcp_call.name, arguments=mcp_call.arguments
+                    )
+
+                    print("Result:", result)
+
+
+# Run it
+asyncio.run(main())
+```
+
+## LiteLLM Python SDK MCP Bridge
+
+LiteLLM Python SDK acts as a MCP bridge to utilize MCP tools with all LiteLLM supported models. LiteLLM offers the following features for using MCP
+
+- **List** Available MCP Tools: OpenAI clients can view all available MCP tools
+  - `litellm.experimental_mcp_client.load_mcp_tools` to list all available MCP tools
+- **Call** MCP Tools: OpenAI clients can call MCP tools
+  - `litellm.experimental_mcp_client.call_openai_tool` to call an OpenAI tool on an MCP server
+
+
+### 1. List Available MCP Tools
+
+In this example we'll use `litellm.experimental_mcp_client.load_mcp_tools` to list all available MCP tools on any MCP server. This method can be used in two ways:
+
+- `format="mcp"` - (default) Return MCP tools 
+  - Returns: `mcp.types.Tool`
+- `format="openai"` - Return MCP tools converted to OpenAI API compatible tools. Allows using with OpenAI endpoints.
+  - Returns: `openai.types.chat.ChatCompletionToolParam`
+
+<Tabs>
+<TabItem value="sdk" label="LiteLLM Python SDK">
+
+```python title="MCP Client List Tools" showLineNumbers
+# Create server parameters for stdio connection
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+import os
+import litellm
+from litellm import experimental_mcp_client
+
+
+server_params = StdioServerParameters(
+    command="python3",
+    # Make sure to update to the full absolute path to your mcp_server.py file
+    args=["./mcp_server.py"],
+)
+
+async with stdio_client(server_params) as (read, write):
+    async with ClientSession(read, write) as session:
+        # Initialize the connection
+        await session.initialize()
+
+        # Get tools
+        tools = await experimental_mcp_client.load_mcp_tools(session=session, format="openai")
+        print("MCP TOOLS: ", tools)
+
+        messages = [{"role": "user", "content": "what's (3 + 5)"}]
+        llm_response = await litellm.acompletion(
+            model="gpt-4o",
+            api_key=os.getenv("OPENAI_API_KEY"),
+            messages=messages,
+            tools=tools,
+        )
+        print("LLM RESPONSE: ", json.dumps(llm_response, indent=4, default=str))
+```
+
+</TabItem>
+
+<TabItem value="openai" label="OpenAI SDK + LiteLLM Proxy">
+
+In this example we'll walk through how you can use the OpenAI SDK pointed to the LiteLLM proxy to call MCP tools. The key difference here is we use the OpenAI SDK to make the LLM API request
+
+```python title="MCP Client List Tools" showLineNumbers
+# Create server parameters for stdio connection
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+import os
+from openai import OpenAI
+from litellm import experimental_mcp_client
+
+server_params = StdioServerParameters(
+    command="python3",
+    # Make sure to update to the full absolute path to your mcp_server.py file
+    args=["./mcp_server.py"],
+)
+
+async with stdio_client(server_params) as (read, write):
+    async with ClientSession(read, write) as session:
+        # Initialize the connection
+        await session.initialize()
+
+        # Get tools using litellm mcp client
+        tools = await experimental_mcp_client.load_mcp_tools(session=session, format="openai")
+        print("MCP TOOLS: ", tools)
+
+        # Use OpenAI SDK pointed to LiteLLM proxy
+        client = OpenAI(
+            api_key="your-api-key",  # Your LiteLLM proxy API key
+            base_url="http://localhost:4000"  # Your LiteLLM proxy URL
+        )
+
+        messages = [{"role": "user", "content": "what's (3 + 5)"}]
+        llm_response = client.chat.completions.create(
+            model="gpt-4",
+            messages=messages,
+            tools=tools
+        )
+        print("LLM RESPONSE: ", llm_response)
+```
+</TabItem>
+</Tabs>
+
+
+### 2. List and Call MCP Tools
+
+In this example we'll use 
+- `litellm.experimental_mcp_client.load_mcp_tools` to list all available MCP tools on any MCP server
+- `litellm.experimental_mcp_client.call_openai_tool` to call an OpenAI tool on an MCP server
+
+The first llm response returns a list of OpenAI tools. We take the first tool call from the LLM response and pass it to `litellm.experimental_mcp_client.call_openai_tool` to call the tool on the MCP server.
+
+#### How `litellm.experimental_mcp_client.call_openai_tool` works
+
+- Accepts an OpenAI Tool Call from the LLM response
+- Converts the OpenAI Tool Call to an MCP Tool
+- Calls the MCP Tool on the MCP server
+- Returns the result of the MCP Tool call
+
+<Tabs>
+<TabItem value="sdk" label="LiteLLM Python SDK">
+
+```python title="MCP Client List and Call Tools" showLineNumbers
+# Create server parameters for stdio connection
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+import os
+import litellm
+from litellm import experimental_mcp_client
+
+
+server_params = StdioServerParameters(
+    command="python3",
+    # Make sure to update to the full absolute path to your mcp_server.py file
+    args=["./mcp_server.py"],
+)
+
+async with stdio_client(server_params) as (read, write):
+    async with ClientSession(read, write) as session:
+        # Initialize the connection
+        await session.initialize()
+
+        # Get tools
+        tools = await experimental_mcp_client.load_mcp_tools(session=session, format="openai")
+        print("MCP TOOLS: ", tools)
+
+        messages = [{"role": "user", "content": "what's (3 + 5)"}]
+        llm_response = await litellm.acompletion(
+            model="gpt-4o",
+            api_key=os.getenv("OPENAI_API_KEY"),
+            messages=messages,
+            tools=tools,
+        )
+        print("LLM RESPONSE: ", json.dumps(llm_response, indent=4, default=str))
+
+        openai_tool = llm_response["choices"][0]["message"]["tool_calls"][0]
+        # Call the tool using MCP client
+        call_result = await experimental_mcp_client.call_openai_tool(
+            session=session,
+            openai_tool=openai_tool,
+        )
+        print("MCP TOOL CALL RESULT: ", call_result)
+
+        # send the tool result to the LLM
+        messages.append(llm_response["choices"][0]["message"])
+        messages.append(
+            {
+                "role": "tool",
+                "content": str(call_result.content[0].text),
+                "tool_call_id": openai_tool["id"],
+            }
+        )
+        print("final messages with tool result: ", messages)
+        llm_response = await litellm.acompletion(
+            model="gpt-4o",
+            api_key=os.getenv("OPENAI_API_KEY"),
+            messages=messages,
+            tools=tools,
+        )
+        print(
+            "FINAL LLM RESPONSE: ", json.dumps(llm_response, indent=4, default=str)
+        )
+```
+
+</TabItem>
+<TabItem value="proxy" label="OpenAI SDK + LiteLLM Proxy">
+
+In this example we'll walk through how you can use the OpenAI SDK pointed to the LiteLLM proxy to call MCP tools. The key difference here is we use the OpenAI SDK to make the LLM API request
+
+```python title="MCP Client with OpenAI SDK" showLineNumbers
+# Create server parameters for stdio connection
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+import os
+from openai import OpenAI
+from litellm import experimental_mcp_client
+
+server_params = StdioServerParameters(
+    command="python3",
+    # Make sure to update to the full absolute path to your mcp_server.py file
+    args=["./mcp_server.py"],
+)
+
+async with stdio_client(server_params) as (read, write):
+    async with ClientSession(read, write) as session:
+        # Initialize the connection
+        await session.initialize()
+
+        # Get tools using litellm mcp client
+        tools = await experimental_mcp_client.load_mcp_tools(session=session, format="openai")
+        print("MCP TOOLS: ", tools)
+
+        # Use OpenAI SDK pointed to LiteLLM proxy
+        client = OpenAI(
+            api_key="your-api-key",  # Your LiteLLM proxy API key
+            base_url="http://localhost:8000"  # Your LiteLLM proxy URL
+        )
+
+        messages = [{"role": "user", "content": "what's (3 + 5)"}]
+        llm_response = client.chat.completions.create(
+            model="gpt-4",
+            messages=messages,
+            tools=tools
+        )
+        print("LLM RESPONSE: ", llm_response)
+
+        # Get the first tool call
+        tool_call = llm_response.choices[0].message.tool_calls[0]
+        
+        # Call the tool using MCP client
+        call_result = await experimental_mcp_client.call_openai_tool(
+            session=session,
+            openai_tool=tool_call.model_dump(),
+        )
+        print("MCP TOOL CALL RESULT: ", call_result)
+
+        # Send the tool result back to the LLM
+        messages.append(llm_response.choices[0].message.model_dump())
+        messages.append({
+            "role": "tool",
+            "content": str(call_result.content[0].text),
+            "tool_call_id": tool_call.id,
+        })
+
+        final_response = client.chat.completions.create(
+            model="gpt-4",
+            messages=messages,
+            tools=tools
+        )
+        print("FINAL RESPONSE: ", final_response)
+```
+
+</TabItem>
+</Tabs>

docs/my-website/docs/observability/agentops_integration.md

@@ -0,0 +1,83 @@
+# 🖇️ AgentOps - LLM Observability Platform
+
+:::tip
+
+This is community maintained. Please make an issue if you run into a bug:
+https://github.com/BerriAI/litellm
+
+:::
+
+[AgentOps](https://docs.agentops.ai) is an observability platform that enables tracing and monitoring of LLM calls, providing detailed insights into your AI operations.
+
+## Using AgentOps with LiteLLM
+
+LiteLLM provides `success_callbacks` and `failure_callbacks`, allowing you to easily integrate AgentOps for comprehensive tracing and monitoring of your LLM operations.
+
+### Integration
+
+Use just a few lines of code to instantly trace your responses **across all providers** with AgentOps:
+Get your AgentOps API Keys from https://app.agentops.ai/
+```python
+import litellm
+
+# Configure LiteLLM to use AgentOps
+litellm.success_callback = ["agentops"]
+
+# Make your LLM calls as usual
+response = litellm.completion(
+    model="gpt-3.5-turbo",
+    messages=[{"role": "user", "content": "Hello, how are you?"}],
+)
+```
+
+Complete Code:
+
+```python
+import os
+from litellm import completion
+
+# Set env variables
+os.environ["OPENAI_API_KEY"] = "your-openai-key"
+os.environ["AGENTOPS_API_KEY"] = "your-agentops-api-key"
+
+# Configure LiteLLM to use AgentOps
+litellm.success_callback = ["agentops"]
+
+# OpenAI call
+response = completion(
+    model="gpt-4",
+    messages=[{"role": "user", "content": "Hi 👋 - I'm OpenAI"}],
+)
+
+print(response)
+```
+
+### Configuration Options
+
+The AgentOps integration can be configured through environment variables:
+
+- `AGENTOPS_API_KEY` (str, optional): Your AgentOps API key
+- `AGENTOPS_ENVIRONMENT` (str, optional): Deployment environment (defaults to "production")
+- `AGENTOPS_SERVICE_NAME` (str, optional): Service name for tracing (defaults to "agentops")
+
+### Advanced Usage
+
+You can configure additional settings through environment variables:
+
+```python
+import os
+
+# Configure AgentOps settings
+os.environ["AGENTOPS_API_KEY"] = "your-agentops-api-key"
+os.environ["AGENTOPS_ENVIRONMENT"] = "staging"
+os.environ["AGENTOPS_SERVICE_NAME"] = "my-service"
+
+# Enable AgentOps tracing
+litellm.success_callback = ["agentops"]
+```
+
+### Support
+
+For issues or questions, please refer to:
+- [AgentOps Documentation](https://docs.agentops.ai)
+- [LiteLLM Documentation](https://docs.litellm.ai) 

docs/my-website/docs/observability/arize_integration.md

@@ -1,4 +1,7 @@
+
 import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
 
 # Arize AI
 
@@ -11,6 +14,8 @@ https://github.com/BerriAI/litellm
 
 :::
 
+<Image img={require('../../img/arize.png')} />
+
 
 
 ## Pre-Requisites
@@ -24,7 +29,9 @@ You can also use the instrumentor option instead of the callback, which you can
 ```python
 litellm.callbacks = ["arize"]
 ```
+
 ```python
+
 import litellm
 import os
 
@@ -48,7 +55,7 @@ response = litellm.completion(
 
 ### Using with LiteLLM Proxy
 
-
+1. Setup config.yaml
 ```yaml
 model_list:
   - model_name: gpt-4
@@ -60,13 +67,134 @@ model_list:
 litellm_settings:
   callbacks: ["arize"]
 
+general_settings:
+  master_key: "sk-1234" # can also be set as an environment variable
+
 environment_variables:
     ARIZE_SPACE_KEY: "d0*****"
     ARIZE_API_KEY: "141a****"
     ARIZE_ENDPOINT: "https://otlp.arize.com/v1" # OPTIONAL - your custom arize GRPC api endpoint
-    ARIZE_HTTP_ENDPOINT: "https://otlp.arize.com/v1" # OPTIONAL - your custom arize HTTP api endpoint. Set either this or ARIZE_ENDPOINT
+    ARIZE_HTTP_ENDPOINT: "https://otlp.arize.com/v1" # OPTIONAL - your custom arize HTTP api endpoint. Set either this or ARIZE_ENDPOINT or Neither (defaults to https://otlp.arize.com/v1 on grpc)
 ```
 
+2. Start the proxy
+
+```bash
+litellm --config config.yaml
+```
+
+3. Test it!
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "Hi 👋 - i'm openai"}]}'
+```
+
+## Pass Arize Space/Key per-request
+
+Supported parameters:
+- `arize_api_key`
+- `arize_space_key`
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm
+import os
+
+# LLM API Keys
+os.environ['OPENAI_API_KEY']=""
+
+# set arize as a callback, litellm will send the data to arize
+litellm.callbacks = ["arize"]
+ 
+# openai call
+response = litellm.completion(
+  model="gpt-3.5-turbo",
+  messages=[
+    {"role": "user", "content": "Hi 👋 - i'm openai"}
+  ],
+  arize_api_key=os.getenv("ARIZE_SPACE_2_API_KEY"),
+  arize_space_key=os.getenv("ARIZE_SPACE_2_KEY"),
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: gpt-4
+    litellm_params:
+      model: openai/fake
+      api_key: fake-key
+      api_base: https://exampleopenaiendpoint-production.up.railway.app/
+
+litellm_settings:
+  callbacks: ["arize"]
+
+general_settings:
+  master_key: "sk-1234" # can also be set as an environment variable
+```
+
+2. Start the proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it!
+
+<Tabs>
+<TabItem value="curl" label="CURL">
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "gpt-4",
+  "messages": [{"role": "user", "content": "Hi 👋 - i'm openai"}],
+  "arize_api_key": "ARIZE_SPACE_2_API_KEY",
+  "arize_space_key": "ARIZE_SPACE_2_KEY"
+}'
+```
+</TabItem>
+<TabItem value="openai_python" label="OpenAI Python">
+
+```python
+import openai
+client = openai.OpenAI(
+    api_key="anything",
+    base_url="http://0.0.0.0:4000"
+)
+
+# request sent to model set on litellm proxy, `litellm --model`
+response = client.chat.completions.create(
+    model="gpt-3.5-turbo",
+    messages = [
+        {
+            "role": "user",
+            "content": "this is a test request, write a short poem"
+        }
+    ],
+    extra_body={
+      "arize_api_key": "ARIZE_SPACE_2_API_KEY",
+      "arize_space_key": "ARIZE_SPACE_2_KEY"
+    }
+)
+
+print(response)
+```
+</TabItem>
+</Tabs>
+</TabItem>
+</Tabs>
+
 ## Support & Talk to Founders
 
 - [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)

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

@@ -4,7 +4,7 @@ Pass-through endpoints for Cohere - call provider-specific endpoint, in native f
 
 | Feature | Supported | Notes | 
 |-------|-------|-------|
-| Cost Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) |
+| Cost Tracking | ✅ | Supported for `/v1/chat`, and `/v2/chat` |
 | Logging | ✅ | works across all integrations |
 | End-user Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) |
 | Streaming | ✅ | |

docs/my-website/docs/pass_through/mistral.md

@@ -0,0 +1,217 @@
+# Mistral
+
+Pass-through endpoints for Mistral - call provider-specific endpoint, in native format (no translation).
+
+| Feature | Supported | Notes | 
+|-------|-------|-------|
+| Cost Tracking | ❌ | Not supported |
+| Logging | ✅ | works across all integrations |
+| End-user Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) |
+| Streaming | ✅ | |
+
+Just replace `https://api.mistral.ai/v1` with `LITELLM_PROXY_BASE_URL/mistral` 🚀
+
+#### **Example Usage**
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/mistral/v1/ocr' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "mistral-ocr-latest",
+    "document": {
+        "type": "image_url",
+        "image_url": "https://raw.githubusercontent.com/mistralai/cookbook/refs/heads/main/mistral/ocr/receipt.png"
+    }
+
+}'
+```
+
+Supports **ALL** Mistral Endpoints (including streaming).
+
+## Quick Start
+
+Let's call the Mistral [`/chat/completions` endpoint](https://docs.mistral.ai/api/#tag/chat/operation/chat_completion_v1_chat_completions_post)
+
+1. Add MISTRAL_API_KEY to your environment 
+
+```bash
+export MISTRAL_API_KEY="sk-1234"
+```
+
+2. Start LiteLLM Proxy 
+
+```bash
+litellm
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+3. Test it! 
+
+Let's call the Mistral `/ocr` endpoint
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/mistral/v1/ocr' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "mistral-ocr-latest",
+    "document": {
+        "type": "image_url",
+        "image_url": "https://raw.githubusercontent.com/mistralai/cookbook/refs/heads/main/mistral/ocr/receipt.png"
+    }
+
+}'
+```
+
+
+## Examples
+
+Anything after `http://0.0.0.0:4000/mistral` is treated as a provider-specific route, and handled accordingly.
+
+Key Changes: 
+
+| **Original Endpoint**                                | **Replace With**                  |
+|------------------------------------------------------|-----------------------------------|
+| `https://api.mistral.ai/v1`          | `http://0.0.0.0:4000/mistral` (LITELLM_PROXY_BASE_URL="http://0.0.0.0:4000")      |
+| `bearer $MISTRAL_API_KEY`                                 | `bearer anything` (use `bearer LITELLM_VIRTUAL_KEY` if Virtual Keys are setup on proxy)                    |
+
+
+### **Example 1: OCR endpoint**
+
+#### LiteLLM Proxy Call 
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/mistral/v1/ocr' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_API_KEY' \
+-d '{
+    "model": "mistral-ocr-latest",
+    "document": {
+        "type": "image_url",
+        "image_url": "https://raw.githubusercontent.com/mistralai/cookbook/refs/heads/main/mistral/ocr/receipt.png"
+    }
+}'
+```
+
+
+#### Direct Mistral API Call 
+
+```bash
+curl https://api.mistral.ai/v1/ocr \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer ${MISTRAL_API_KEY}" \
+  -d '{
+    "model": "mistral-ocr-latest",
+    "document": {
+        "type": "document_url",
+        "document_url": "https://arxiv.org/pdf/2201.04234"
+    },
+    "include_image_base64": true
+  }'
+```
+
+### **Example 2: Chat API**
+
+#### LiteLLM Proxy Call 
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/mistral/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_VIRTUAL_KEY' \
+-d '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "mistral-large-latest",
+}'
+```
+
+#### Direct Mistral API Call 
+
+```bash
+curl -L -X POST 'https://api.mistral.ai/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-d '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "mistral-large-latest",
+}'
+```
+
+
+## Advanced - Use with Virtual Keys 
+
+Pre-requisites
+- [Setup proxy with DB](../proxy/virtual_keys.md#setup)
+
+Use this, to avoid giving developers the raw Mistral API key, but still letting them use Mistral endpoints.
+
+### Usage
+
+1. Setup environment
+
+```bash
+export DATABASE_URL=""
+export LITELLM_MASTER_KEY=""
+export MISTRAL_API_BASE=""
+```
+
+```bash
+litellm
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+2. Generate virtual key 
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/key/generate' \
+-H 'Authorization: Bearer sk-1234' \
+-H 'Content-Type: application/json' \
+-d '{}'
+```
+
+Expected Response 
+
+```bash
+{
+    ...
+    "key": "sk-1234ewknldferwedojwojw"
+}
+```
+
+3. Test it! 
+
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/mistral/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234ewknldferwedojwojw' \
+  --data '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "qwen2.5-7b-instruct",
+}'
+```

docs/my-website/docs/pass_through/vertex_ai.md

@@ -13,8 +13,102 @@ Pass-through endpoints for Vertex AI - call provider-specific endpoint, in nativ
 | End-user Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) |
 | Streaming | ✅ | |
 
+## Supported Endpoints
+
+LiteLLM supports 2 vertex ai passthrough routes:
+
+1. `/vertex_ai` → routes to `https://{vertex_location}-aiplatform.googleapis.com/`
+2. `/vertex_ai/discovery` → routes to [`https://discoveryengine.googleapis.com`](https://discoveryengine.googleapis.com/)
+
+## How to use
+
 Just replace `https://REGION-aiplatform.googleapis.com` with `LITELLM_PROXY_BASE_URL/vertex_ai`
 
+LiteLLM supports 3 flows for calling Vertex AI endpoints via pass-through:
+
+1. **Specific Credentials**: Admin sets passthrough credentials for a specific project/region.
+
+2. **Default Credentials**: Admin sets default credentials.
+
+3. **Client-Side Credentials**: User can send client-side credentials through to Vertex AI (default behavior - if no default or mapped credentials are found, the request is passed through directly).
+
+
+## Example Usage
+
+<Tabs>
+<TabItem value="specific_credentials" label="Specific Project/Region">
+
+```yaml
+model_list:
+  - model_name: gemini-1.0-pro
+    litellm_params:
+      model: vertex_ai/gemini-1.0-pro
+      vertex_project: adroit-crow-413218
+      vertex_region: us-central1
+      vertex_credentials: /path/to/credentials.json
+      use_in_pass_through: true # 👈 KEY CHANGE
+```
+
+</TabItem>
+<TabItem value="default_credentials" label="Default Credentials">
+
+<Tabs>
+<TabItem value="yaml" label="Set in config.yaml">
+
+```yaml
+default_vertex_config: 
+  vertex_project: adroit-crow-413218
+  vertex_region: us-central1
+  vertex_credentials: /path/to/credentials.json
+```
+</TabItem>
+<TabItem value="env_var" label="Set in environment variables">
+
+```bash
+export DEFAULT_VERTEXAI_PROJECT="adroit-crow-413218"
+export DEFAULT_VERTEXAI_LOCATION="us-central1"
+export DEFAULT_GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
+```
+
+</TabItem>
+</Tabs>
+</TabItem>
+<TabItem value="client_credentials" label="Client Credentials">
+
+Try Gemini 2.0 Flash (curl)
+
+```
+MODEL_ID="gemini-2.0-flash-001"
+PROJECT_ID="YOUR_PROJECT_ID"
+```
+
+```bash
+curl \
+  -X POST \
+  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
+  -H "Content-Type: application/json" \
+  "${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:streamGenerateContent" -d \
+  $'{
+    "contents": {
+      "role": "user",
+      "parts": [
+        {
+        "fileData": {
+          "mimeType": "image/png",
+          "fileUri": "gs://generativeai-downloads/images/scones.jpg"
+          }
+        },
+        {
+          "text": "Describe this picture."
+        }
+      ]
+    }
+  }'
+```
+
+</TabItem>
+</Tabs>
+
 
 #### **Example Usage**
 
@@ -22,7 +116,7 @@ Just replace `https://REGION-aiplatform.googleapis.com` with `LITELLM_PROXY_BASE
 <TabItem value="curl" label="curl">
 
 ```bash
-curl http://localhost:4000/vertex_ai/publishers/google/models/gemini-1.0-pro:generateContent \
+curl http://localhost:4000/vertex_ai/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:generateContent \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{
@@ -101,7 +195,7 @@ litellm
 Let's call the Google AI Studio token counting endpoint
 
 ```bash
-curl http://localhost:4000/vertex-ai/publishers/google/models/gemini-1.0-pro:generateContent \
+curl http://localhost:4000/vertex-ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.0-pro:generateContent \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
@@ -140,7 +234,7 @@ LiteLLM Proxy Server supports two methods of authentication to Vertex AI:
 
 
 ```shell
-curl http://localhost:4000/vertex_ai/publishers/google/models/gemini-1.5-flash-001:generateContent \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.5-flash-001:generateContent \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{"contents":[{"role": "user", "parts":[{"text": "hi"}]}]}'
@@ -152,7 +246,7 @@ curl http://localhost:4000/vertex_ai/publishers/google/models/gemini-1.5-flash-0
 
 
 ```shell
-curl http://localhost:4000/vertex_ai/publishers/google/models/textembedding-gecko@001:predict \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/textembedding-gecko@001:predict \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{"instances":[{"content": "gm"}]}'
@@ -162,7 +256,7 @@ curl http://localhost:4000/vertex_ai/publishers/google/models/textembedding-geck
 ### Imagen API
 
 ```shell
-curl http://localhost:4000/vertex_ai/publishers/google/models/imagen-3.0-generate-001:predict \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/imagen-3.0-generate-001:predict \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{"instances":[{"prompt": "make an otter"}], "parameters": {"sampleCount": 1}}'
@@ -172,7 +266,7 @@ curl http://localhost:4000/vertex_ai/publishers/google/models/imagen-3.0-generat
 ### Count Tokens API
 
 ```shell
-curl http://localhost:4000/vertex_ai/publishers/google/models/gemini-1.5-flash-001:countTokens \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.5-flash-001:countTokens \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{"contents":[{"role": "user", "parts":[{"text": "hi"}]}]}'
@@ -183,7 +277,7 @@ Create Fine Tuning Job
 
 
 ```shell
-curl http://localhost:4000/vertex_ai/tuningJobs \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.5-flash-001:tuningJobs \
       -H "Content-Type: application/json" \
       -H "x-litellm-api-key: Bearer sk-1234" \
       -d '{
@@ -243,7 +337,7 @@ Expected Response
 
 
 ```bash
-curl http://localhost:4000/vertex_ai/publishers/google/models/gemini-1.0-pro:generateContent \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.0-pro:generateContent \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -d '{
@@ -268,7 +362,7 @@ tags: ["vertex-js-sdk", "pass-through-endpoint"]
 <TabItem value="curl" label="curl">
 
 ```bash
-curl http://localhost:4000/vertex-ai/publishers/google/models/gemini-1.0-pro:generateContent \
+curl http://localhost:4000/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/gemini-1.0-pro:generateContent \
   -H "Content-Type: application/json" \
   -H "x-litellm-api-key: Bearer sk-1234" \
   -H "tags: vertex-js-sdk,pass-through-endpoint" \

docs/my-website/docs/pass_through/vllm.md

@@ -0,0 +1,185 @@
+# VLLM
+
+Pass-through endpoints for VLLM - call provider-specific endpoint, in native format (no translation).
+
+| Feature | Supported | Notes | 
+|-------|-------|-------|
+| Cost Tracking | ❌ | Not supported |
+| Logging | ✅ | works across all integrations |
+| End-user Tracking | ❌ | [Tell us if you need this](https://github.com/BerriAI/litellm/issues/new) |
+| Streaming | ✅ | |
+
+Just replace `https://my-vllm-server.com` with `LITELLM_PROXY_BASE_URL/vllm` 🚀
+
+#### **Example Usage**
+
+```bash
+curl -L -X GET 'http://0.0.0.0:4000/vllm/metrics' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+```
+
+Supports **ALL** VLLM Endpoints (including streaming).
+
+## Quick Start
+
+Let's call the VLLM [`/metrics` endpoint](https://vllm.readthedocs.io/en/latest/api_reference/api_reference.html)
+
+1. Add HOSTED VLLM API BASE to your environment 
+
+```bash
+export HOSTED_VLLM_API_BASE="https://my-vllm-server.com"
+```
+
+2. Start LiteLLM Proxy 
+
+```bash
+litellm
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+3. Test it! 
+
+Let's call the VLLM `/metrics` endpoint
+
+```bash
+curl -L -X GET 'http://0.0.0.0:4000/vllm/metrics' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+```
+
+
+## Examples
+
+Anything after `http://0.0.0.0:4000/vllm` is treated as a provider-specific route, and handled accordingly.
+
+Key Changes: 
+
+| **Original Endpoint**                                | **Replace With**                  |
+|------------------------------------------------------|-----------------------------------|
+| `https://my-vllm-server.com`          | `http://0.0.0.0:4000/vllm` (LITELLM_PROXY_BASE_URL="http://0.0.0.0:4000")      |
+| `bearer $VLLM_API_KEY`                                 | `bearer anything` (use `bearer LITELLM_VIRTUAL_KEY` if Virtual Keys are setup on proxy)                    |
+
+
+### **Example 1: Metrics endpoint**
+
+#### LiteLLM Proxy Call 
+
+```bash
+curl -L -X GET 'http://0.0.0.0:4000/vllm/metrics' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_VIRTUAL_KEY' \
+```
+
+
+#### Direct VLLM API Call 
+
+```bash
+curl -L -X GET 'https://my-vllm-server.com/metrics' \
+-H 'Content-Type: application/json' \
+```
+
+### **Example 2: Chat API**
+
+#### LiteLLM Proxy Call 
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/vllm/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_VIRTUAL_KEY' \
+-d '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "qwen2.5-7b-instruct",
+}'
+```
+
+#### Direct VLLM API Call 
+
+```bash
+curl -L -X POST 'https://my-vllm-server.com/chat/completions' \
+-H 'Content-Type: application/json' \
+-d '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "qwen2.5-7b-instruct",
+}'
+```
+
+
+## Advanced - Use with Virtual Keys 
+
+Pre-requisites
+- [Setup proxy with DB](../proxy/virtual_keys.md#setup)
+
+Use this, to avoid giving developers the raw Cohere API key, but still letting them use Cohere endpoints.
+
+### Usage
+
+1. Setup environment
+
+```bash
+export DATABASE_URL=""
+export LITELLM_MASTER_KEY=""
+export HOSTED_VLLM_API_BASE=""
+```
+
+```bash
+litellm
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+2. Generate virtual key 
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/key/generate' \
+-H 'Authorization: Bearer sk-1234' \
+-H 'Content-Type: application/json' \
+-d '{}'
+```
+
+Expected Response 
+
+```bash
+{
+    ...
+    "key": "sk-1234ewknldferwedojwojw"
+}
+```
+
+3. Test it! 
+
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/vllm/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234ewknldferwedojwojw' \
+  --data '{
+    "messages": [
+        {
+            "role": "user",
+            "content": "I am going to Paris, what should I see?"
+        }
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.8,
+    "top_p": 0.1,
+    "model": "qwen2.5-7b-instruct",
+}'
+```

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

@@ -821,6 +821,14 @@ print(f"\nResponse: {resp}")
 
 ## Usage - Thinking / `reasoning_content`
 
+LiteLLM translates OpenAI's `reasoning_effort` to Anthropic's `thinking` parameter. [Code](https://github.com/BerriAI/litellm/blob/23051d89dd3611a81617d84277059cd88b2df511/litellm/llms/anthropic/chat/transformation.py#L298)
+
+| reasoning_effort | thinking |
+| ---------------- | -------- |
+| "low"            | "budget_tokens": 1024 |
+| "medium"         | "budget_tokens": 2048 |
+| "high"           | "budget_tokens": 4096 |
+
 <Tabs>
 <TabItem value="sdk" label="SDK">
 
@@ -830,7 +838,7 @@ from litellm import completion
 resp = completion(
     model="anthropic/claude-3-7-sonnet-20250219",
     messages=[{"role": "user", "content": "What is the capital of France?"}],
-    thinking={"type": "enabled", "budget_tokens": 1024},
+    reasoning_effort="low",
 )
 
 ```
@@ -863,7 +871,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
   -d '{
     "model": "claude-3-7-sonnet-20250219",
     "messages": [{"role": "user", "content": "What is the capital of France?"}],
-    "thinking": {"type": "enabled", "budget_tokens": 1024}
+    "reasoning_effort": "low"
   }'
 ```
 
@@ -927,6 +935,44 @@ ModelResponse(
 )
 ```
 
+### Pass `thinking` to Anthropic models
+
+You can also pass the `thinking` parameter to Anthropic models.
+
+
+You can also pass the `thinking` parameter to Anthropic models.
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+response = litellm.completion(
+  model="anthropic/claude-3-7-sonnet-20250219",
+  messages=[{"role": "user", "content": "What is the capital of France?"}],
+  thinking={"type": "enabled", "budget_tokens": 1024},
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "anthropic/claude-3-7-sonnet-20250219",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "thinking": {"type": "enabled", "budget_tokens": 1024}
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+
+
 ## **Passing Extra Headers to Anthropic API**
 
 Pass `extra_headers: dict` to `litellm.completion`
@@ -1035,8 +1081,10 @@ response = completion(
             "content": [
                 {"type": "text", "text": "You are a very professional document summarization specialist. Please summarize the given document."},
                 {
-                    "type": "image_url",
-                    "image_url": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                    "type": "file",
+                    "file": {
+                       "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                    }
                 },
             ],
         }
@@ -1081,8 +1129,10 @@ curl http://0.0.0.0:4000/v1/chat/completions \
             "text": "You are a very professional document summarization specialist. Please summarize the given document"
           },
           {
-                "type": "image_url",
-                "image_url": "data:application/pdf;base64,{encoded_file}" # 👈 PDF
+                "type": "file",
+                "file": {
+                    "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                }
             }
           }
         ]

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

@@ -291,14 +291,15 @@ response = completion(
 )
 ```
 
-## Azure O1 Models
+## O-Series Models
 
-| Model Name          | Function Call                                      |
-|---------------------|----------------------------------------------------|
-| o1-mini | `response = completion(model="azure/<your deployment name>", messages=messages)` |
-| o1-preview | `response = completion(model="azure/<your deployment name>", messages=messages)` |
+Azure OpenAI O-Series models are supported on LiteLLM. 
 
-Set `litellm.enable_preview_features = True` to use Azure O1 Models with streaming support. 
+LiteLLM routes any deployment name with `o1` or `o3` in the model name, to the O-Series [transformation](https://github.com/BerriAI/litellm/blob/91ed05df2962b8eee8492374b048d27cc144d08c/litellm/llms/azure/chat/o1_transformation.py#L4) logic.
+
+To set this explicitly, set `model` to `azure/o_series/<your-deployment-name>`.
+
+**Automatic Routing**
 
 <Tabs>
 <TabItem value="sdk" label="SDK">
@@ -306,32 +307,88 @@ Set `litellm.enable_preview_features = True` to use Azure O1 Models with streami
 ```python
 import litellm
 
-litellm.enable_preview_features = True # 👈 KEY CHANGE
-
-response = litellm.completion(
-    model="azure/<your deployment name>",
-    messages=[{"role": "user", "content": "What is the weather like in Boston?"}],
-    stream=True
-)
-
-for chunk in response:
-    print(chunk)
+litellm.completion(model="azure/my-o3-deployment", messages=[{"role": "user", "content": "Hello, world!"}]) # 👈 Note: 'o3' in the deployment name
 ```
 </TabItem>
-<TabItem value="proxy" label="Proxy">
+<TabItem value="proxy" label="PROXY">
 
-1. Setup config.yaml
 ```yaml
 model_list:
-  - model_name: o1-mini
+  - model_name: o3-mini
     litellm_params:
-      model: azure/o1-mini
-      api_base: "os.environ/AZURE_API_BASE"
-      api_key: "os.environ/AZURE_API_KEY"
-      api_version: "os.environ/AZURE_API_VERSION"
+      model: azure/o3-model
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+```
 
-litellm_settings:
-    enable_preview_features: true # 👈 KEY CHANGE
+</TabItem>
+</Tabs>
+
+**Explicit Routing**
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm
+
+litellm.completion(model="azure/o_series/my-random-deployment-name", messages=[{"role": "user", "content": "Hello, world!"}]) # 👈 Note: 'o_series/' in the deployment name
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```yaml
+model_list:
+  - model_name: o3-mini
+    litellm_params:
+      model: azure/o_series/my-random-deployment-name
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+```
+</TabItem>
+</Tabs>
+
+
+## Azure Audio Model
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+os.environ["AZURE_API_KEY"] = ""
+os.environ["AZURE_API_BASE"] = ""
+os.environ["AZURE_API_VERSION"] = ""
+
+response = completion(
+    model="azure/azure-openai-4o-audio",
+    messages=[
+      {
+        "role": "user",
+        "content": "I want to try out speech to speech"
+      }
+    ],
+    modalities=["text","audio"],
+    audio={"voice": "alloy", "format": "wav"}
+)
+
+print(response)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: azure-openai-4o-audio
+    litellm_params:
+      model: azure/azure-openai-4o-audio
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+      api_version: os.environ/AZURE_API_VERSION
 ```
 
 2. Start proxy
@@ -340,26 +397,22 @@ litellm_settings:
 litellm --config /path/to/config.yaml
 ```
 
-3. Test it 
+3. Test it!
 
-```python
-import openai
-client = openai.OpenAI(
-    api_key="anything",
-    base_url="http://0.0.0.0:4000"
-)
 
-response = client.chat.completions.create(model="o1-mini", messages = [
-    {
-        "role": "user",
-        "content": "this is a test request, write a short poem"
-    }
-],
-stream=True)
-
-for chunk in response:
-    print(chunk)
+```bash
+curl http://localhost:4000/v1/chat/completions \
+  -H "Authorization: Bearer $LITELLM_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "azure-openai-4o-audio",
+    "messages": [{"role": "user", "content": "I want to try out speech to speech"}],
+    "modalities": ["text","audio"],
+    "audio": {"voice": "alloy", "format": "wav"}
+  }'
 ```
+
+
 </TabItem>
 </Tabs>
 
@@ -425,7 +478,7 @@ response.stream_to_file(speech_file_path)
 ## **Authentication**
 
 
-### Entrata ID - use `azure_ad_token`
+### Entra ID - use `azure_ad_token`
 
 This is a walkthrough on how to use Azure Active Directory Tokens - Microsoft Entra ID to make `litellm.completion()` calls 
 
@@ -492,7 +545,7 @@ model_list:
 </TabItem>
 </Tabs>
 
-### Entrata ID - use tenant_id, client_id, client_secret
+### Entra ID - use tenant_id, client_id, client_secret
 
 Here is an example of setting up `tenant_id`, `client_id`, `client_secret` in your litellm proxy `config.yaml`
 ```yaml
@@ -528,7 +581,7 @@ Example video of using `tenant_id`, `client_id`, `client_secret` with LiteLLM Pr
 
 <iframe width="840" height="500" src="https://www.loom.com/embed/70d3f219ee7f4e5d84778b7f17bba506?sid=04b8ff29-485f-4cb8-929e-6b392722f36d" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>
 
-### Entrata ID - use client_id, username, password
+### Entra ID - use client_id, username, password
 
 Here is an example of setting up `client_id`, `azure_username`, `azure_password` in your litellm proxy `config.yaml`
 ```yaml
@@ -948,60 +1001,124 @@ Expected Response:
 {"data":[{"id":"batch_R3V...}
 ```
 
-## O-Series Models
 
-Azure OpenAI O-Series models are supported on LiteLLM. 
+## **Azure Responses API**
 
-LiteLLM routes any deployment name with `o1` or `o3` in the model name, to the O-Series [transformation](https://github.com/BerriAI/litellm/blob/91ed05df2962b8eee8492374b048d27cc144d08c/litellm/llms/azure/chat/o1_transformation.py#L4) logic.
+| Property | Details |
+|-------|-------|
+| Description | Azure OpenAI Responses API |
+| `custom_llm_provider` on LiteLLM | `azure/` |
+| Supported Operations | `/v1/responses`|
+| Azure OpenAI Responses API | [Azure OpenAI Responses API ↗](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/responses?tabs=python-secure) |
+| Cost Tracking, Logging Support | ✅ LiteLLM will log, track cost for Responses API Requests |
+| Supported OpenAI Params | ✅ All OpenAI params are supported, [See here](https://github.com/BerriAI/litellm/blob/0717369ae6969882d149933da48eeb8ab0e691bd/litellm/llms/openai/responses/transformation.py#L23) |
 
-To set this explicitly, set `model` to `azure/o_series/<your-deployment-name>`.
+## Usage
 
-**Automatic Routing**
+## Create a model response
 
 <Tabs>
-<TabItem value="sdk" label="SDK">
+<TabItem value="litellm-sdk" label="LiteLLM SDK">
 
-```python
+#### Non-streaming
+
+```python showLineNumbers title="Azure Responses API"
 import litellm
 
-litellm.completion(model="azure/my-o3-deployment", messages=[{"role": "user", "content": "Hello, world!"}]) # 👈 Note: 'o3' in the deployment name
-```
-</TabItem>
-<TabItem value="proxy" label="PROXY">
+# Non-streaming response
+response = litellm.responses(
+    model="azure/o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    max_output_tokens=100,
+    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
+    api_base="https://litellm8397336933.openai.azure.com/",
+    api_version="2023-03-15-preview",
+)
 
-```yaml
-model_list:
-  - model_name: o3-mini
-    litellm_params:
-      model: azure/o3-model
-      api_base: os.environ/AZURE_API_BASE
-      api_key: os.environ/AZURE_API_KEY
+print(response)
 ```
 
-</TabItem>
-</Tabs>
-
-**Explicit Routing**
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-```python
+#### Streaming
+```python showLineNumbers title="Azure Responses API"
 import litellm
 
-litellm.completion(model="azure/o_series/my-random-deployment-name", messages=[{"role": "user", "content": "Hello, world!"}]) # 👈 Note: 'o_series/' in the deployment name
-```
-</TabItem>
-<TabItem value="proxy" label="PROXY">
+# Streaming response
+response = litellm.responses(
+    model="azure/o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True,
+    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
+    api_base="https://litellm8397336933.openai.azure.com/",
+    api_version="2023-03-15-preview",
+)
 
-```yaml
-model_list:
-  - model_name: o3-mini
-    litellm_params:
-      model: azure/o_series/my-random-deployment-name
-      api_base: os.environ/AZURE_API_BASE
-      api_key: os.environ/AZURE_API_KEY
+for event in response:
+    print(event)
 ```
+
+</TabItem>
+<TabItem value="proxy" label="OpenAI SDK with LiteLLM Proxy">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="Azure Responses API"
+model_list:
+  - model_name: o1-pro
+    litellm_params:
+      model: azure/o1-pro
+      api_key: os.environ/AZURE_RESPONSES_OPENAI_API_KEY
+      api_base: https://litellm8397336933.openai.azure.com/
+      api_version: 2023-03-15-preview
+```
+
+Start your LiteLLM proxy:
+```bash
+litellm --config /path/to/config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+Then use the OpenAI SDK pointed to your proxy:
+
+#### Non-streaming
+```python showLineNumbers
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
 </TabItem>
 </Tabs>
 
@@ -1076,32 +1193,24 @@ print(response)
 ```
 
 
-### Parallel Function calling
+### Tool Calling / Function Calling
+
 See a detailed walthrough of parallel function calling with litellm [here](https://docs.litellm.ai/docs/completion/function_call)
+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
 ```python
 # set Azure env variables
 import os
+import litellm
+import json
+
 os.environ['AZURE_API_KEY'] = "" # litellm reads AZURE_API_KEY from .env and sends the request
 os.environ['AZURE_API_BASE'] = "https://openai-gpt-4-test-v-1.openai.azure.com/"
 os.environ['AZURE_API_VERSION'] = "2023-07-01-preview"
 
-import litellm
-import json
-# Example dummy function hard coded to return the same weather
-# In production, this could be your backend API or an external API
-def get_current_weather(location, unit="fahrenheit"):
-    """Get the current weather in a given location"""
-    if "tokyo" in location.lower():
-        return json.dumps({"location": "Tokyo", "temperature": "10", "unit": "celsius"})
-    elif "san francisco" in location.lower():
-        return json.dumps({"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"})
-    elif "paris" in location.lower():
-        return json.dumps({"location": "Paris", "temperature": "22", "unit": "celsius"})
-    else:
-        return json.dumps({"location": location, "temperature": "unknown"})
-
-## Step 1: send the conversation and available functions to the model
-messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
 tools = [
     {
         "type": "function",
@@ -1125,7 +1234,7 @@ tools = [
 
 response = litellm.completion(
     model="azure/chatgpt-functioncalling", # model = azure/<your-azure-deployment-name>
-    messages=messages,
+    messages=[{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}],
     tools=tools,
     tool_choice="auto",  # auto is default, but we'll be explicit
 )
@@ -1134,8 +1243,49 @@ response_message = response.choices[0].message
 tool_calls = response.choices[0].message.tool_calls
 print("\nTool Choice:\n", tool_calls)
 ```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: azure-gpt-3.5
+    litellm_params:
+      model: azure/chatgpt-functioncalling
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+      api_version: "2023-07-01-preview"
+```
+
+2. Start proxy
+
+```bash
+litellm --config config.yaml
+```
+
+3. Test it
+
+```bash
+curl -L -X POST 'http://localhost:4000/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "azure-gpt-3.5",
+    "messages": [
+        {
+            "role": "user",
+            "content": "Hey, how'\''s it going? Thinking long and hard before replying - what is the meaning of the world and life itself"
+        }
+    ]
+}'
+```
 
 
+
+
+</TabItem>
+</Tabs>
 ### Spend Tracking for Azure OpenAI Models (PROXY)
 
 Set base model for cost tracking azure image-gen call

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

@@ -79,6 +79,7 @@ aws_session_name: Optional[str],
 aws_profile_name: Optional[str],
 aws_role_name: Optional[str],
 aws_web_identity_token: Optional[str],
+aws_bedrock_runtime_endpoint: Optional[str],
 ```
 
 ### 2. Start the proxy 
@@ -475,7 +476,7 @@ os.environ["AWS_REGION_NAME"] = ""
 resp = completion(
     model="bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0",
     messages=[{"role": "user", "content": "What is the capital of France?"}],
-    thinking={"type": "enabled", "budget_tokens": 1024},
+    reasoning_effort="low",
 )
 
 print(resp)
@@ -490,7 +491,7 @@ model_list:
   - model_name: bedrock-claude-3-7
     litellm_params:
       model: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
-      thinking: {"type": "enabled", "budget_tokens": 1024} # 👈 EITHER HERE OR ON REQUEST
+      reasoning_effort: "low" # 👈 EITHER HERE OR ON REQUEST
 ```
 
 2. Start proxy 
@@ -508,7 +509,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
   -d '{
     "model": "bedrock-claude-3-7",
     "messages": [{"role": "user", "content": "What is the capital of France?"}],
-    "thinking": {"type": "enabled", "budget_tokens": 1024} # 👈 EITHER HERE OR ON CONFIG.YAML
+    "reasoning_effort": "low" # 👈 EITHER HERE OR ON CONFIG.YAML
   }'
 ```
 
@@ -557,6 +558,10 @@ Same as [Anthropic API response](../providers/anthropic#usage---thinking--reason
 }
 ```
 
+### Pass `thinking` to Anthropic models
+
+Same as [Anthropic API response](../providers/anthropic#usage---thinking--reasoning_content).
+
 
 ## Usage - Structured Output / JSON mode 
 
@@ -663,6 +668,58 @@ curl http://0.0.0.0:4000/v1/chat/completions \
 </TabItem>
 </Tabs>
 
+## Usage - Latency Optimized Inference
+
+Valid from v1.65.1+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+response = completion(
+    model="bedrock/anthropic.claude-3-7-sonnet-20250219-v1:0",
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+    performanceConfig={"latency": "optimized"},
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: bedrock-claude-3-7
+    litellm_params:
+      model: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
+      performanceConfig: {"latency": "optimized"} # 👈 EITHER HERE OR ON REQUEST
+```
+
+2. Start proxy 
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it!
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "bedrock-claude-3-7",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "performanceConfig": {"latency": "optimized"} # 👈 EITHER HERE OR ON CONFIG.YAML
+  }'
+```
+
+</TabItem>
+</Tabs>
+
 ## Usage - Bedrock Guardrails
 
 Example of using [Bedrock Guardrails with LiteLLM](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-use-converse-api.html)
@@ -1115,14 +1172,22 @@ os.environ["AWS_REGION_NAME"] = ""
 # pdf url
 image_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
 
+# Download the file
+response = requests.get(url)
+file_data = response.content
+
+encoded_file = base64.b64encode(file_data).decode("utf-8")
+
 # model
 model = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
 
 image_content = [
     {"type": "text", "text": "What's this file about?"},
     {
-        "type": "image_url",
-        "image_url": image_url, # OR {"url": image_url}
+        "type": "file",
+        "file": {
+            "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+        }
     },
 ]
 
@@ -1168,8 +1233,10 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
     "messages": [
         {"role": "user", "content": {"type": "text", "text": "What's this file about?"}},
         {
-            "type": "image_url",
-            "image_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
+            "type": "file",
+            "file": {
+                "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+            }
         }
     ]
 }'
@@ -1427,10 +1494,14 @@ response = litellm.embedding(
 
 
 ## Supported AWS Bedrock Models
+
+LiteLLM supports ALL Bedrock models. 
+
 Here's an example of using a bedrock model with LiteLLM. For a complete list, refer to the [model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)
 
 | Model Name                 | Command                                                          |
 |----------------------------|------------------------------------------------------------------|
+| Deepseek R1    | `completion(model='bedrock/us.deepseek.r1-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude-V3.5 Sonnet    | `completion(model='bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude-V3  sonnet    | `completion(model='bedrock/anthropic.claude-3-sonnet-20240229-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude-V3 Haiku     | `completion(model='bedrock/anthropic.claude-3-haiku-20240307-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
@@ -1771,6 +1842,7 @@ response = completion(
 )
 ```
 </TabItem>
+
 <TabItem value="proxy" label="PROXY">
 
 1. Setup config.yaml 
@@ -1815,11 +1887,13 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 ```
 
 </TabItem>
+
 </Tabs>
 
 ### SSO Login (AWS Profile)
 - Set `AWS_PROFILE` environment variable
 - Make bedrock completion call
+
 ```python
 import os
 from litellm import completion
@@ -1912,12 +1986,46 @@ model_list:
 
 </Tabs>
 
+Text to Image : 
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/images/generations' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_VIRTUAL_KEY' \
+-d '{
+    "model": "amazon.nova-canvas-v1:0",
+    "prompt": "A cute baby sea otter"
+}'
+```
+
+Color Guided Generation:
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/images/generations' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer $LITELLM_VIRTUAL_KEY' \
+-d '{
+    "model": "amazon.nova-canvas-v1:0",
+    "prompt": "A cute baby sea otter",
+    "taskType": "COLOR_GUIDED_GENERATION",
+    "colorGuidedGenerationParams":{"colors":["#FFFFFF"]}
+}'
+```
+
+| Model Name              | Function Call                               |
+|-------------------------|---------------------------------------------|
+| Stable Diffusion 3 - v0 | `image_generation(model="bedrock/stability.stability.sd3-large-v1:0", prompt=prompt)` |
+| Stable Diffusion - v0   | `image_generation(model="bedrock/stability.stable-diffusion-xl-v0", prompt=prompt)` |
+| Stable Diffusion - v1   | `image_generation(model="bedrock/stability.stable-diffusion-xl-v1", prompt=prompt)` |
+| Amazon Nova Canvas - v0 | `image_generation(model="bedrock/amazon.nova-canvas-v1:0", prompt=prompt)` |
+  
   
 ### Passing an external BedrockRuntime.Client as a parameter - Completion()
   
+This is a deprecated flow. Boto3 is not async. And boto3.client does not let us make the http call through httpx. Pass in your aws params through the method above 👆. [See Auth Code](https://github.com/BerriAI/litellm/blob/55a20c7cce99a93d36a82bf3ae90ba3baf9a7f89/litellm/llms/bedrock_httpx.py#L284) [Add new auth flow](https://github.com/BerriAI/litellm/issues)
+
 :::warning
 
-This is a deprecated flow. Boto3 is not async. And boto3.client does not let us make the http call through httpx. Pass in your aws params through the method above 👆. [See Auth Code](https://github.com/BerriAI/litellm/blob/55a20c7cce99a93d36a82bf3ae90ba3baf9a7f89/litellm/llms/bedrock_httpx.py#L284) [Add new auth flow](https://github.com/BerriAI/litellm/issues)
+
+
 
 
 Experimental - 2024-Jun-23:

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

@@ -1,7 +1,7 @@
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# 🆕 Databricks
+# Databricks
 
 LiteLLM supports all models on Databricks
 
@@ -154,7 +154,205 @@ response = completion(
         temperature: 0.5
 ```
 
-## Passings Databricks specific params - 'instruction'
+
+## Usage - Thinking / `reasoning_content`
+
+LiteLLM translates OpenAI's `reasoning_effort` to Anthropic's `thinking` parameter. [Code](https://github.com/BerriAI/litellm/blob/23051d89dd3611a81617d84277059cd88b2df511/litellm/llms/anthropic/chat/transformation.py#L298)
+
+| reasoning_effort | thinking |
+| ---------------- | -------- |
+| "low"            | "budget_tokens": 1024 |
+| "medium"         | "budget_tokens": 2048 |
+| "high"           | "budget_tokens": 4096 |
+
+
+Known Limitations:
+- Support for passing thinking blocks back to Claude [Issue](https://github.com/BerriAI/litellm/issues/9790)
+ 
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+# set ENV variables (can also be passed in to .completion() - e.g. `api_base`, `api_key`)
+os.environ["DATABRICKS_API_KEY"] = "databricks key"
+os.environ["DATABRICKS_API_BASE"] = "databricks base url"
+
+resp = completion(
+    model="databricks/databricks-claude-3-7-sonnet",
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+    reasoning_effort="low",
+)
+
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+- model_name: claude-3-7-sonnet
+  litellm_params:
+    model: databricks/databricks-claude-3-7-sonnet
+    api_key: os.environ/DATABRICKS_API_KEY
+    api_base: os.environ/DATABRICKS_API_BASE
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
+  -d '{
+    "model": "claude-3-7-sonnet",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "reasoning_effort": "low"
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+**Expected Response**
+
+```python
+ModelResponse(
+    id='chatcmpl-c542d76d-f675-4e87-8e5f-05855f5d0f5e',
+    created=1740470510,
+    model='claude-3-7-sonnet-20250219',
+    object='chat.completion',
+    system_fingerprint=None,
+    choices=[
+        Choices(
+            finish_reason='stop',
+            index=0,
+            message=Message(
+                content="The capital of France is Paris.",
+                role='assistant',
+                tool_calls=None,
+                function_call=None,
+                provider_specific_fields={
+                    'citations': None,
+                    'thinking_blocks': [
+                        {
+                            'type': 'thinking',
+                            'thinking': 'The capital of France is Paris. This is a very straightforward factual question.',
+                            'signature': 'EuYBCkQYAiJAy6...'
+                        }
+                    ]
+                }
+            ),
+            thinking_blocks=[
+                {
+                    'type': 'thinking',
+                    'thinking': 'The capital of France is Paris. This is a very straightforward factual question.',
+                    'signature': 'EuYBCkQYAiJAy6AGB...'
+                }
+            ],
+            reasoning_content='The capital of France is Paris. This is a very straightforward factual question.'
+        )
+    ],
+    usage=Usage(
+        completion_tokens=68,
+        prompt_tokens=42,
+        total_tokens=110,
+        completion_tokens_details=None,
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            audio_tokens=None,
+            cached_tokens=0,
+            text_tokens=None,
+            image_tokens=None
+        ),
+        cache_creation_input_tokens=0,
+        cache_read_input_tokens=0
+    )
+)
+```
+
+### Pass `thinking` to Anthropic models
+
+You can also pass the `thinking` parameter to Anthropic models.
+
+
+You can also pass the `thinking` parameter to Anthropic models.
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+# set ENV variables (can also be passed in to .completion() - e.g. `api_base`, `api_key`)
+os.environ["DATABRICKS_API_KEY"] = "databricks key"
+os.environ["DATABRICKS_API_BASE"] = "databricks base url"
+
+response = litellm.completion(
+  model="databricks/databricks-claude-3-7-sonnet",
+  messages=[{"role": "user", "content": "What is the capital of France?"}],
+  thinking={"type": "enabled", "budget_tokens": 1024},
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "databricks/databricks-claude-3-7-sonnet",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "thinking": {"type": "enabled", "budget_tokens": 1024}
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+
+
+
+## Supported Databricks Chat Completion Models 
+
+:::tip
+
+**We support ALL Databricks models, just set `model=databricks/<any-model-on-databricks>` as a prefix when sending litellm requests**
+
+:::
+
+
+| Model Name                 | Command                                                          |
+|----------------------------|------------------------------------------------------------------|
+| databricks/databricks-claude-3-7-sonnet    | `completion(model='databricks/databricks/databricks-claude-3-7-sonnet', messages=messages)`   | 
+| databricks-meta-llama-3-1-70b-instruct    | `completion(model='databricks/databricks-meta-llama-3-1-70b-instruct', messages=messages)`   | 
+| databricks-meta-llama-3-1-405b-instruct    | `completion(model='databricks/databricks-meta-llama-3-1-405b-instruct', messages=messages)`   | 
+| databricks-dbrx-instruct    | `completion(model='databricks/databricks-dbrx-instruct', messages=messages)`   | 
+| databricks-meta-llama-3-70b-instruct    | `completion(model='databricks/databricks-meta-llama-3-70b-instruct', messages=messages)`   | 
+| databricks-llama-2-70b-chat    | `completion(model='databricks/databricks-llama-2-70b-chat', messages=messages)`   | 
+| databricks-mixtral-8x7b-instruct    | `completion(model='databricks/databricks-mixtral-8x7b-instruct', messages=messages)`   | 
+| databricks-mpt-30b-instruct    | `completion(model='databricks/databricks-mpt-30b-instruct', messages=messages)`   | 
+| databricks-mpt-7b-instruct    | `completion(model='databricks/databricks-mpt-7b-instruct', messages=messages)`   | 
+
+
+## Embedding Models
+
+### Passing Databricks specific params - 'instruction'
 
 For embedding models, databricks lets you pass in an additional param 'instruction'. [Full Spec](https://github.com/BerriAI/litellm/blob/43353c28b341df0d9992b45c6ce464222ebd7984/litellm/llms/databricks.py#L164)
 
@@ -187,27 +385,6 @@ response = litellm.embedding(
         instruction: "Represent this sentence for searching relevant passages:"
 ```
 
-
-## Supported Databricks Chat Completion Models 
-
-:::tip
-
-**We support ALL Databricks models, just set `model=databricks/<any-model-on-databricks>` as a prefix when sending litellm requests**
-
-:::
-
-
-| Model Name                 | Command                                                          |
-|----------------------------|------------------------------------------------------------------|
-| databricks-meta-llama-3-1-70b-instruct    | `completion(model='databricks/databricks-meta-llama-3-1-70b-instruct', messages=messages)`   | 
-| databricks-meta-llama-3-1-405b-instruct    | `completion(model='databricks/databricks-meta-llama-3-1-405b-instruct', messages=messages)`   | 
-| databricks-dbrx-instruct    | `completion(model='databricks/databricks-dbrx-instruct', messages=messages)`   | 
-| databricks-meta-llama-3-70b-instruct    | `completion(model='databricks/databricks-meta-llama-3-70b-instruct', messages=messages)`   | 
-| databricks-llama-2-70b-chat    | `completion(model='databricks/databricks-llama-2-70b-chat', messages=messages)`   | 
-| databricks-mixtral-8x7b-instruct    | `completion(model='databricks/databricks-mixtral-8x7b-instruct', messages=messages)`   | 
-| databricks-mpt-30b-instruct    | `completion(model='databricks/databricks-mpt-30b-instruct', messages=messages)`   | 
-| databricks-mpt-7b-instruct    | `completion(model='databricks/databricks-mpt-7b-instruct', messages=messages)`   | 
-
 ## Supported Databricks Embedding Models 
 
 :::tip

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

@@ -39,14 +39,164 @@ response = completion(
 - temperature
 - top_p
 - max_tokens
+- max_completion_tokens
 - stream
 - tools
 - tool_choice
+- functions
 - response_format
 - n
 - stop
+- logprobs
+- frequency_penalty
+- modalities
+- reasoning_content
+
+**Anthropic Params**
+- thinking (used to set max budget tokens across anthropic/gemini models)
+
+[**See Updated List**](https://github.com/BerriAI/litellm/blob/main/litellm/llms/gemini/chat/transformation.py#L70)
+
+
+
+## Usage - Thinking / `reasoning_content`
+
+LiteLLM translates OpenAI's `reasoning_effort` to Gemini's `thinking` parameter. [Code](https://github.com/BerriAI/litellm/blob/620664921902d7a9bfb29897a7b27c1a7ef4ddfb/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py#L362)
+
+**Mapping**
+
+| reasoning_effort | thinking |
+| ---------------- | -------- |
+| "low"            | "budget_tokens": 1024 |
+| "medium"         | "budget_tokens": 2048 |
+| "high"           | "budget_tokens": 4096 |
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+resp = completion(
+    model="gemini/gemini-2.5-flash-preview-04-17",
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+    reasoning_effort="low",
+)
+
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+- model_name: gemini-2.5-flash
+  litellm_params:
+    model: gemini/gemini-2.5-flash-preview-04-17
+    api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
+  -d '{
+    "model": "gemini-2.5-flash",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "reasoning_effort": "low"
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+**Expected Response**
+
+```python
+ModelResponse(
+    id='chatcmpl-c542d76d-f675-4e87-8e5f-05855f5d0f5e',
+    created=1740470510,
+    model='claude-3-7-sonnet-20250219',
+    object='chat.completion',
+    system_fingerprint=None,
+    choices=[
+        Choices(
+            finish_reason='stop',
+            index=0,
+            message=Message(
+                content="The capital of France is Paris.",
+                role='assistant',
+                tool_calls=None,
+                function_call=None,
+                reasoning_content='The capital of France is Paris. This is a very straightforward factual question.'
+            ),
+        )
+    ],
+    usage=Usage(
+        completion_tokens=68,
+        prompt_tokens=42,
+        total_tokens=110,
+        completion_tokens_details=None,
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            audio_tokens=None,
+            cached_tokens=0,
+            text_tokens=None,
+            image_tokens=None
+        ),
+        cache_creation_input_tokens=0,
+        cache_read_input_tokens=0
+    )
+)
+```
+
+### Pass `thinking` to Gemini models
+
+You can also pass the `thinking` parameter to Gemini models.
+
+This is translated to Gemini's [`thinkingConfig` parameter](https://ai.google.dev/gemini-api/docs/thinking#set-budget).
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+response = litellm.completion(
+  model="gemini/gemini-2.5-flash-preview-04-17",
+  messages=[{"role": "user", "content": "What is the capital of France?"}],
+  thinking={"type": "enabled", "budget_tokens": 1024},
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "gemini/gemini-2.5-flash-preview-04-17",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "thinking": {"type": "enabled", "budget_tokens": 1024}
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+
 
-[**See Updated List**](https://github.com/BerriAI/litellm/blob/1c747f3ad372399c5b95cc5696b06a5fbe53186b/litellm/llms/vertex_httpx.py#L122)
 
 ## Passing Gemini Specific Params
 ### Response schema 
@@ -365,7 +515,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 </Tabs>
 
 ## Specifying Safety Settings 
-In certain use-cases you may need to make calls to the models and pass [safety settigns](https://ai.google.dev/docs/safety_setting_gemini) different from the defaults. To do so, simple pass the `safety_settings` argument to `completion` or `acompletion`. For example:
+In certain use-cases you may need to make calls to the models and pass [safety settings](https://ai.google.dev/docs/safety_setting_gemini) different from the defaults. To do so, simple pass the `safety_settings` argument to `completion` or `acompletion`. For example:
 
 ```python
 response = completion(
@@ -438,6 +588,179 @@ assert isinstance(
 ```
 
 
+### Google Search Tool
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+os.environ["GEMINI_API_KEY"] = ".."
+
+tools = [{"googleSearch": {}}] # 👈 ADD GOOGLE SEARCH
+
+response = completion(
+    model="gemini/gemini-2.0-flash",
+    messages=[{"role": "user", "content": "What is the weather in San Francisco?"}],
+    tools=tools,
+)
+
+print(response)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: gemini-2.0-flash
+    litellm_params:
+      model: gemini/gemini-2.0-flash
+      api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start Proxy
+```bash
+$ litellm --config /path/to/config.yaml
+```
+
+3. Make Request!
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "gemini-2.0-flash",
+  "messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+  "tools": [{"googleSearch": {}}]
+}
+'
+```
+
+</TabItem>
+</Tabs>
+
+### Google Search Retrieval
+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+os.environ["GEMINI_API_KEY"] = ".."
+
+tools = [{"googleSearchRetrieval": {}}] # 👈 ADD GOOGLE SEARCH
+
+response = completion(
+    model="gemini/gemini-2.0-flash",
+    messages=[{"role": "user", "content": "What is the weather in San Francisco?"}],
+    tools=tools,
+)
+
+print(response)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: gemini-2.0-flash
+    litellm_params:
+      model: gemini/gemini-2.0-flash
+      api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start Proxy
+```bash
+$ litellm --config /path/to/config.yaml
+```
+
+3. Make Request!
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "gemini-2.0-flash",
+  "messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+  "tools": [{"googleSearchRetrieval": {}}]
+}
+'
+```
+
+</TabItem>
+</Tabs>
+
+
+### Code Execution Tool
+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+os.environ["GEMINI_API_KEY"] = ".."
+
+tools = [{"codeExecution": {}}] # 👈 ADD GOOGLE SEARCH
+
+response = completion(
+    model="gemini/gemini-2.0-flash",
+    messages=[{"role": "user", "content": "What is the weather in San Francisco?"}],
+    tools=tools,
+)
+
+print(response)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: gemini-2.0-flash
+    litellm_params:
+      model: gemini/gemini-2.0-flash
+      api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start Proxy
+```bash
+$ litellm --config /path/to/config.yaml
+```
+
+3. Make Request!
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "gemini-2.0-flash",
+  "messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+  "tools": [{"codeExecution": {}}]
+}
+'
+```
+
+</TabItem>
+</Tabs>
+
+
+
+
+
+
 ## JSON Mode
 
 <Tabs>
@@ -589,8 +912,10 @@ response = litellm.completion(
             "content": [
                 {"type": "text", "text": "Please summarize the audio."},
                 {
-                    "type": "image_url",
-                    "image_url": "data:audio/mp3;base64,{}".format(encoded_data), # 👈 SET MIME_TYPE + DATA
+                    "type": "file",
+                    "file": {
+                        "file_data": "data:audio/mp3;base64,{}".format(encoded_data), # 👈 SET MIME_TYPE + DATA
+                    }
                 },
             ],
         }
@@ -640,8 +965,11 @@ response = litellm.completion(
             "content": [
                 {"type": "text", "text": "Please summarize the file."},
                 {
-                    "type": "image_url",
-                    "image_url": "https://storage..." # 👈 SET THE IMG URL
+                    "type": "file",
+                    "file": {
+                        "file_id": "https://storage...", # 👈 SET THE IMG URL
+                        "format": "application/pdf" # OPTIONAL
+                    }
                 },
             ],
         }
@@ -668,8 +996,11 @@ response = litellm.completion(
             "content": [
                 {"type": "text", "text": "Please summarize the file."},
                 {
-                    "type": "image_url",
-                    "image_url": "gs://..." # 👈 SET THE cloud storage bucket url
+                    "type": "file",
+                    "file": {
+                        "file_id": "gs://storage...", # 👈 SET THE IMG URL
+                        "format": "application/pdf" # OPTIONAL
+                    }
                 },
             ],
         }
@@ -879,3 +1210,54 @@ response = await client.chat.completions.create(
 
 </TabItem>
 </Tabs>
+
+## Image Generation
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion 
+
+response = completion(
+    model="gemini/gemini-2.0-flash-exp-image-generation",
+    messages=[{"role": "user", "content": "Generate an image of a cat"}],
+    modalities=["image", "text"],
+)
+assert response.choices[0].message.content is not None # "data:image/png;base64,e4rr.."
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: gemini-2.0-flash-exp-image-generation
+    litellm_params:
+      model: gemini/gemini-2.0-flash-exp-image-generation
+      api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it!
+
+```bash
+curl -L -X POST 'http://localhost:4000/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "gemini-2.0-flash-exp-image-generation",
+    "messages": [{"role": "user", "content": "Generate an image of a cat"}],
+    "modalities": ["image", "text"]
+}'
+```
+
+</TabItem>
+</Tabs>
+

docs/my-website/docs/providers/google_ai_studio/files.md

@@ -0,0 +1,161 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# [BETA] Google AI Studio (Gemini) Files API
+
+Use this to upload files to Google AI Studio (Gemini).
+
+Useful to pass in large media files to Gemini's `/generateContent` endpoint.
+
+| Action | Supported | 
+|----------|-----------|
+| `create` | Yes |
+| `delete` | No |
+| `retrieve` | No |
+| `list` | No |
+
+## Usage
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import base64
+import requests
+from litellm import completion, create_file
+import os
+
+
+### UPLOAD FILE ### 
+
+# Fetch the audio file and convert it to a base64 encoded string
+url = "https://cdn.openai.com/API/docs/audio/alloy.wav"
+response = requests.get(url)
+response.raise_for_status()
+wav_data = response.content
+encoded_string = base64.b64encode(wav_data).decode('utf-8')
+
+
+file = create_file(
+    file=wav_data,
+    purpose="user_data",
+    extra_body={"custom_llm_provider": "gemini"},
+    api_key=os.getenv("GEMINI_API_KEY"),
+)
+
+print(f"file: {file}")
+
+assert file is not None
+
+
+### GENERATE CONTENT ### 
+completion = completion(
+    model="gemini-2.0-flash",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                { 
+                    "type": "text",
+                    "text": "What is in this recording?"
+                },
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                        "filename": "my-test-name",
+                        "format": "audio/wav"
+                    }
+                }
+            ]
+        },
+    ]
+)
+
+print(completion.choices[0].message)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+    - model_name: "gemini-2.0-flash"
+      litellm_params:
+        model: gemini/gemini-2.0-flash
+        api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start proxy
+
+```bash
+litellm --config config.yaml
+```
+
+3. Test it
+
+```python
+import base64
+import requests
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://0.0.0.0:4000",
+    api_key="sk-1234"
+)
+
+# Fetch the audio file and convert it to a base64 encoded string
+url = "https://cdn.openai.com/API/docs/audio/alloy.wav"
+response = requests.get(url)
+response.raise_for_status()
+wav_data = response.content
+encoded_string = base64.b64encode(wav_data).decode('utf-8')
+
+
+file = client.files.create(
+    file=wav_data,
+    purpose="user_data",
+    extra_body={"target_model_names": "gemini-2.0-flash"}
+)
+
+print(f"file: {file}")
+
+assert file is not None
+
+completion = client.chat.completions.create(
+    model="gemini-2.0-flash",
+    modalities=["text", "audio"],
+    audio={"voice": "alloy", "format": "wav"},
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                { 
+                    "type": "text",
+                    "text": "What is in this recording?"
+                },
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                        "filename": "my-test-name",
+                        "format": "audio/wav"
+                    }
+                }
+            ]
+        },
+    ],
+    extra_body={"drop_params": True}
+)
+
+print(completion.choices[0].message)
+```
+
+
+
+
+</TabItem>
+</Tabs>
+

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

@@ -2,466 +2,392 @@ import Image from '@theme/IdealImage';
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# Huggingface
+# Hugging Face
+LiteLLM supports running inference across multiple services for models hosted on the Hugging Face Hub.
 
-LiteLLM supports the following types of Hugging Face models:
+- **Serverless Inference Providers** - Hugging Face offers an easy and unified access to serverless AI inference through multiple inference providers, like [Together AI](https://together.ai) and [Sambanova](https://sambanova.ai). This is the fastest way to integrate AI in your products with a maintenance-free and scalable solution. More details in the [Inference Providers documentation](https://huggingface.co/docs/inference-providers/index).
+- **Dedicated Inference Endpoints** - which is a product to easily deploy models to production. Inference is run by Hugging Face in a dedicated, fully managed infrastructure on a cloud provider of your choice. You can deploy your model on Hugging Face Inference Endpoints by following [these steps](https://huggingface.co/docs/inference-endpoints/guides/create_endpoint).
 
-- Serverless Inference API (free) - loaded and ready to use: https://huggingface.co/models?inference=warm&pipeline_tag=text-generation
-- Dedicated Inference Endpoints (paid) - manual deployment: https://ui.endpoints.huggingface.co/
-- All LLMs served via Hugging Face's Inference use [Text-generation-inference](https://huggingface.co/docs/text-generation-inference). 
+
+## Supported Models
+
+### Serverless Inference Providers
+You can check available models for an inference provider by going to [huggingface.co/models](https://huggingface.co/models), clicking the "Other" filter tab, and selecting your desired provider:
+
+![Filter models by Inference Provider](../../img/hf_filter_inference_providers.png)
+
+For example, you can find all Fireworks supported models [here](https://huggingface.co/models?inference_provider=fireworks-ai&sort=trending).
+
+
+### Dedicated Inference Endpoints
+Refer to the [Inference Endpoints catalog](https://endpoints.huggingface.co/catalog) for a list of available models.
 
 ## Usage
 
-<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/LiteLLM_HuggingFace.ipynb">
-  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
-</a>
-
-You need to tell LiteLLM when you're calling Huggingface.
-This is done by adding the "huggingface/" prefix to `model`, example `completion(model="huggingface/<model_name>",...)`.
-
 <Tabs>
-<TabItem value="serverless" label="Serverless Inference API">
+<TabItem value="serverless" label="Serverless Inference Providers">
 
-By default, LiteLLM will assume a Hugging Face call follows the [Messages API](https://huggingface.co/docs/text-generation-inference/messages_api), which is fully compatible with the OpenAI Chat Completion API.
+### Authentication
+With a single Hugging Face token, you can access inference through multiple providers. Your calls are routed through Hugging Face and the usage is billed directly to your Hugging Face account at the standard provider API rates.
 
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-```python
-import os
-from litellm import completion
-
-# [OPTIONAL] set env var
-os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"
-
-messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}]
-
-# e.g. Call 'https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct' from Serverless Inference API
-response = completion(
-    model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
-    messages=[{ "content": "Hello, how are you?","role": "user"}],
-    stream=True
-)
-
-print(response)
-```
-
-</TabItem>
-<TabItem value="proxy" label="PROXY">
-
-1. Add models to your config.yaml
-
-```yaml
-model_list:
-  - model_name: llama-3.1-8B-instruct
-    litellm_params:
-      model: huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct
-      api_key: os.environ/HUGGINGFACE_API_KEY
-```
-
-2. Start the proxy
+Simply set the `HF_TOKEN` environment variable with your Hugging Face token, you can create one here: https://huggingface.co/settings/tokens.
 
 ```bash
-$ litellm --config /path/to/config.yaml --debug
+export HF_TOKEN="hf_xxxxxx"
+```
+or alternatively, you can pass your Hugging Face token as a parameter:
+```python
+completion(..., api_key="hf_xxxxxx")
 ```
 
-3. Test it!
+### Getting Started
 
-```shell
-curl --location 'http://0.0.0.0:4000/chat/completions' \
-    --header 'Authorization: Bearer sk-1234' \
-    --header 'Content-Type: application/json' \
-    --data '{
-    "model": "llama-3.1-8B-instruct",
-    "messages": [
-      {
-          "role": "user",
-          "content": "I like you!"
-      }
-      ],
-}'
+To use a Hugging Face model, specify both the provider and model you want to use in the following format:
 ```
+huggingface/<provider>/<hf_org_or_user>/<hf_model>
+```
+Where `<hf_org_or_user>/<hf_model>` is the Hugging Face model ID and `<provider>` is the inference provider.  
+By default, if you don't specify a provider, LiteLLM will use the [HF Inference API](https://huggingface.co/docs/api-inference/en/index).
 
-</TabItem> 
-</Tabs>
-</TabItem>
-<TabItem value="classification" label="Text Classification">
-
-Append `text-classification` to the model name
-
-e.g. `huggingface/text-classification/<model-name>`
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
+Examples:
 
 ```python
-import os
-from litellm import completion
+# Run DeepSeek-R1 inference through Together AI
+completion(model="huggingface/together/deepseek-ai/DeepSeek-R1",...)
 
-# [OPTIONAL] set env var
-os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"
+# Run Qwen2.5-72B-Instruct inference through Sambanova
+completion(model="huggingface/sambanova/Qwen/Qwen2.5-72B-Instruct",...)
 
-messages = [{ "content": "I like you, I love you!","role": "user"}]
-
-# e.g. Call 'shahrukhx01/question-vs-statement-classifier' hosted on HF Inference endpoints
-response = completion(
-  model="huggingface/text-classification/shahrukhx01/question-vs-statement-classifier",
-  messages=messages,
-  api_base="https://my-endpoint.endpoints.huggingface.cloud",
-)
-
-print(response)
+# Run Llama-3.3-70B-Instruct inference through HF Inference API
+completion(model="huggingface/meta-llama/Llama-3.3-70B-Instruct",...)
 ```
 
-</TabItem> 
-<TabItem value="proxy" label="PROXY">
-
-1. Add models to your config.yaml
-
-```yaml
-model_list:
-  - model_name: bert-classifier
-    litellm_params:
-      model: huggingface/text-classification/shahrukhx01/question-vs-statement-classifier
-      api_key: os.environ/HUGGINGFACE_API_KEY
-      api_base: "https://my-endpoint.endpoints.huggingface.cloud"
-```
-
-2. Start the proxy
-
-```bash
-$ litellm --config /path/to/config.yaml --debug
-```
-
-3. Test it!
-
-```shell
-curl --location 'http://0.0.0.0:4000/chat/completions' \
-    --header 'Authorization: Bearer sk-1234' \
-    --header 'Content-Type: application/json' \
-    --data '{
-    "model": "bert-classifier",
-    "messages": [
-      {
-          "role": "user",
-          "content": "I like you!"
-      }
-      ],
-}'
-```
-
-</TabItem> 
-</Tabs>
-</TabItem>
-<TabItem value="dedicated" label="Dedicated Inference Endpoints">
-
-Steps to use
-* Create your own Hugging Face dedicated endpoint here: https://ui.endpoints.huggingface.co/
-* Set `api_base` to your deployed api base
-* Add the `huggingface/` prefix to your model so litellm knows it's a huggingface Deployed Inference Endpoint
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-```python
-import os
-from litellm import completion
-
-os.environ["HUGGINGFACE_API_KEY"] = ""
-
-# TGI model: Call https://huggingface.co/glaiveai/glaive-coder-7b
-# add the 'huggingface/' prefix to the model to set huggingface as the provider
-# set api base to your deployed api endpoint from hugging face
-response = completion(
-    model="huggingface/glaiveai/glaive-coder-7b",
-    messages=[{ "content": "Hello, how are you?","role": "user"}],
-    api_base="https://wjiegasee9bmqke2.us-east-1.aws.endpoints.huggingface.cloud"
-)
-print(response)
-```
-
-</TabItem>
-<TabItem value="proxy" label="PROXY">
-
-1. Add models to your config.yaml
-
-```yaml
-model_list:
-  - model_name: glaive-coder
-    litellm_params:
-      model: huggingface/glaiveai/glaive-coder-7b
-      api_key: os.environ/HUGGINGFACE_API_KEY
-      api_base: "https://wjiegasee9bmqke2.us-east-1.aws.endpoints.huggingface.cloud"
-```
-
-2. Start the proxy
-
-```bash
-$ litellm --config /path/to/config.yaml --debug
-```
-
-3. Test it!
-
-```shell
-curl --location 'http://0.0.0.0:4000/chat/completions' \
-    --header 'Authorization: Bearer sk-1234' \
-    --header 'Content-Type: application/json' \
-    --data '{
-    "model": "glaive-coder",
-    "messages": [
-      {
-          "role": "user",
-          "content": "I like you!"
-      }
-      ],
-}'
-```
-
-</TabItem> 
-</Tabs>
-
-</TabItem>
-</Tabs>
-
-## Streaming
 
 <a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/LiteLLM_HuggingFace.ipynb">
   <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
 
-You need to tell LiteLLM when you're calling Huggingface.
-This is done by adding the "huggingface/" prefix to `model`, example `completion(model="huggingface/<model_name>",...)`.
+### Basic Completion
+Here's an example of chat completion using the DeepSeek-R1 model through Together AI:
 
 ```python
 import os
 from litellm import completion
 
-# [OPTIONAL] set env var
-os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
 
-messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}]
-
-# e.g. Call 'facebook/blenderbot-400M-distill' hosted on HF Inference endpoints
 response = completion(
-  model="huggingface/facebook/blenderbot-400M-distill",
-  messages=messages,
-  api_base="https://my-endpoint.huggingface.cloud",
-  stream=True
+    model="huggingface/together/deepseek-ai/DeepSeek-R1",
+    messages=[
+        {
+            "role": "user",
+            "content": "How many r's are in the word 'strawberry'?",
+        }
+    ],
+)
+print(response)
+```
+
+### Streaming
+Now, let's see what a streaming request looks like.
+
+```python
+import os
+from litellm import completion
+
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+response = completion(
+    model="huggingface/together/deepseek-ai/DeepSeek-R1",
+    messages=[
+        {
+            "role": "user",
+            "content": "How many r's are in the word `strawberry`?",
+            
+        }
+    ],
+    stream=True,
 )
 
-print(response)
 for chunk in response:
     print(chunk)
 ```
 
+### Image Input
+You can also pass images when the model supports it. Here is an example using [Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct) model through Sambanova.
+
+```python
+from litellm import completion
+
+# Set your Hugging Face Token
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What's in this image?"},
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+                    }
+                },
+            ],
+        }
+    ]
+
+response = completion(
+    model="huggingface/sambanova/meta-llama/Llama-3.2-11B-Vision-Instruct", 
+    messages=messages,
+)
+print(response.choices[0])
+```
+
+### Function Calling
+You can extend the model's capabilities by giving them access to tools. Here is an example with function calling using [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) model through Sambanova.
+
+```python
+import os
+from litellm import completion
+
+# Set your Hugging Face Token
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+tools = [
+  {
+    "type": "function",
+    "function": {
+      "name": "get_current_weather",
+      "description": "Get the current weather in a given location",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "location": {
+            "type": "string",
+            "description": "The city and state, e.g. San Francisco, CA",
+          },
+          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+        },
+        "required": ["location"],
+      },
+    }
+  }
+]
+messages = [
+    {
+        "role": "user",
+        "content": "What's the weather like in Boston today?",
+    }
+]
+
+response = completion(
+    model="huggingface/sambanova/meta-llama/Llama-3.3-70B-Instruct", 
+    messages=messages,
+    tools=tools,
+    tool_choice="auto"
+)
+print(response)
+```
+
+</TabItem>
+
+<TabItem value="endpoints" label="Inference Endpoints">
+
+<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/LiteLLM_HuggingFace.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
+### Basic Completion
+After you have [deployed your Hugging Face Inference Endpoint](https://endpoints.huggingface.co/new) on dedicated infrastructure, you can run inference on it by providing the endpoint base URL in `api_base`, and indicating `huggingface/tgi` as the model name.
+
+```python
+import os
+from litellm import completion
+
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+response = completion(
+    model="huggingface/tgi",
+    messages=[{"content": "Hello, how are you?", "role": "user"}],
+    api_base="https://my-endpoint.endpoints.huggingface.cloud/v1/"
+)
+print(response)
+```
+
+### Streaming
+
+```python
+import os
+from litellm import completion
+
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+response = completion(
+    model="huggingface/tgi",
+    messages=[{"content": "Hello, how are you?", "role": "user"}],
+    api_base="https://my-endpoint.endpoints.huggingface.cloud/v1/",
+    stream=True
+)
+
+for chunk in response:
+    print(chunk)
+```
+
+### Image Input
+
+```python
+import os
+from litellm import completion
+
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What's in this image?"},
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+                    }
+                },
+            ],
+        }
+    ]
+response = completion(
+    model="huggingface/tgi",
+    messages=messages,
+    api_base="https://my-endpoint.endpoints.huggingface.cloud/v1/""
+)
+print(response.choices[0])
+```
+
+### Function Calling
+
+```python
+import os
+from litellm import completion
+
+os.environ["HF_TOKEN"] = "hf_xxxxxx"
+
+functions = [{
+    "name": "get_weather",
+    "description": "Get the weather in a given location",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "location": {
+                "type": "string",
+                "description": "The location to get weather for"
+            }
+        },
+        "required": ["location"]
+    }
+}]
+
+response = completion(
+    model="huggingface/tgi",
+    messages=[{"content": "What's the weather like in San Francisco?", "role": "user"}],
+    api_base="https://my-endpoint.endpoints.huggingface.cloud/v1/",
+    functions=functions
+)
+print(response)
+```
+
+</TabItem>
+</Tabs>
+
+## LiteLLM Proxy Server with Hugging Face models
+You can set up a [LiteLLM Proxy Server](https://docs.litellm.ai/#litellm-proxy-server-llm-gateway) to serve Hugging Face models through any of the supported Inference Providers. Here's how to do it:
+
+### Step 1. Setup the config file
+
+In this case, we are configuring a proxy to serve `DeepSeek R1` from Hugging Face, using Together AI as the backend Inference Provider.
+
+```yaml
+model_list:
+  - model_name: my-r1-model
+    litellm_params:
+      model: huggingface/together/deepseek-ai/DeepSeek-R1
+      api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
+```
+
+### Step 2. Start the server
+```bash
+litellm --config /path/to/config.yaml
+```
+
+### Step 3. Make a request to the server
+<Tabs>
+<TabItem value="curl" label="curl">
+
+```shell
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+    --header 'Content-Type: application/json' \
+    --data '{
+    "model": "my-r1-model",
+    "messages": [
+        {
+            "role": "user",
+            "content": "Hello, how are you?"
+        }
+    ]
+}'
+```
+
+</TabItem>
+<TabItem value="python" label="python">
+
+```python
+# pip install openai
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://0.0.0.0:4000",
+    api_key="anything",
+)
+
+response = client.chat.completions.create(
+    model="my-r1-model",
+    messages=[
+        {"role": "user", "content": "Hello, how are you?"}
+    ]
+)
+print(response)
+```
+
+</TabItem>
+</Tabs>
+
+
 ## Embedding
 
-LiteLLM supports Hugging Face's [text-embedding-inference](https://github.com/huggingface/text-embeddings-inference) format.
+LiteLLM supports Hugging Face's [text-embedding-inference](https://github.com/huggingface/text-embeddings-inference) models as well.
 
 ```python
 from litellm import embedding
 import os
-os.environ['HUGGINGFACE_API_KEY'] = ""
+os.environ['HF_TOKEN'] = "hf_xxxxxx"
 response = embedding(
     model='huggingface/microsoft/codebert-base',
     input=["good morning from litellm"]
 )
 ```
 
-## Advanced
-
-### Setting API KEYS + API BASE
-
-If required, you can set the api key + api base, set it in your os environment. [Code for how it's sent](https://github.com/BerriAI/litellm/blob/0100ab2382a0e720c7978fbf662cc6e6920e7e03/litellm/llms/huggingface_restapi.py#L25)
-
-```python
-import os
-os.environ["HUGGINGFACE_API_KEY"] = ""
-os.environ["HUGGINGFACE_API_BASE"] = ""
-```
-
-### Viewing Log probs
-
-#### Using `decoder_input_details` - OpenAI `echo`
-
-The `echo` param is supported by OpenAI Completions - Use `litellm.text_completion()` for this
-
-```python
-from litellm import text_completion
-response = text_completion(
-    model="huggingface/bigcode/starcoder",
-    prompt="good morning",
-    max_tokens=10, logprobs=10,
-    echo=True
-)
-```
-
-#### Output
-
-```json
-{
-  "id": "chatcmpl-3fc71792-c442-4ba1-a611-19dd0ac371ad",
-  "object": "text_completion",
-  "created": 1698801125.936519,
-  "model": "bigcode/starcoder",
-  "choices": [
-    {
-      "text": ", I'm going to make you a sand",
-      "index": 0,
-      "logprobs": {
-        "tokens": [
-          "good",
-          " morning",
-          ",",
-          " I",
-          "'m",
-          " going",
-          " to",
-          " make",
-          " you",
-          " a",
-          " s",
-          "and"
-        ],
-        "token_logprobs": [
-          "None",
-          -14.96875,
-          -2.2285156,
-          -2.734375,
-          -2.0957031,
-          -2.0917969,
-          -0.09429932,
-          -3.1132812,
-          -1.3203125,
-          -1.2304688,
-          -1.6201172,
-          -0.010292053
-        ]
-      },
-      "finish_reason": "length"
-    }
-  ],
-  "usage": {
-    "completion_tokens": 9,
-    "prompt_tokens": 2,
-    "total_tokens": 11
-  }
-}
-```
-
-### Models with Prompt Formatting
-
-For models with special prompt templates (e.g. Llama2), we format the prompt to fit their template.
-
-#### Models with natively Supported Prompt Templates
-
-| Model Name                           | Works for Models                   | Function Call                                                                                                           | Required OS Variables               |
-| ------------------------------------ | ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | ----------------------------------- |
-| mistralai/Mistral-7B-Instruct-v0.1   | mistralai/Mistral-7B-Instruct-v0.1 | `completion(model='huggingface/mistralai/Mistral-7B-Instruct-v0.1', messages=messages, api_base="your_api_endpoint")`   | `os.environ['HUGGINGFACE_API_KEY']` |
-| meta-llama/Llama-2-7b-chat           | All meta-llama llama2 chat models  | `completion(model='huggingface/meta-llama/Llama-2-7b', messages=messages, api_base="your_api_endpoint")`                | `os.environ['HUGGINGFACE_API_KEY']` |
-| tiiuae/falcon-7b-instruct            | All falcon instruct models         | `completion(model='huggingface/tiiuae/falcon-7b-instruct', messages=messages, api_base="your_api_endpoint")`            | `os.environ['HUGGINGFACE_API_KEY']` |
-| mosaicml/mpt-7b-chat                 | All mpt chat models                | `completion(model='huggingface/mosaicml/mpt-7b-chat', messages=messages, api_base="your_api_endpoint")`                 | `os.environ['HUGGINGFACE_API_KEY']` |
-| codellama/CodeLlama-34b-Instruct-hf  | All codellama instruct models      | `completion(model='huggingface/codellama/CodeLlama-34b-Instruct-hf', messages=messages, api_base="your_api_endpoint")`  | `os.environ['HUGGINGFACE_API_KEY']` |
-| WizardLM/WizardCoder-Python-34B-V1.0 | All wizardcoder models             | `completion(model='huggingface/WizardLM/WizardCoder-Python-34B-V1.0', messages=messages, api_base="your_api_endpoint")` | `os.environ['HUGGINGFACE_API_KEY']` |
-| Phind/Phind-CodeLlama-34B-v2         | All phind-codellama models         | `completion(model='huggingface/Phind/Phind-CodeLlama-34B-v2', messages=messages, api_base="your_api_endpoint")`         | `os.environ['HUGGINGFACE_API_KEY']` |
-
-**What if we don't support a model you need?**
-You can also specify you're own custom prompt formatting, in case we don't have your model covered yet.
-
-**Does this mean you have to specify a prompt for all models?**
-No. By default we'll concatenate your message content to make a prompt.
-
-**Default Prompt Template**
-
-```python
-def default_pt(messages):
-    return " ".join(message["content"] for message in messages)
-```
-
-[Code for how prompt formats work in LiteLLM](https://github.com/BerriAI/litellm/blob/main/litellm/llms/prompt_templates/factory.py)
-
-#### Custom prompt templates
-
-```python
-import litellm
-
-# Create your own custom prompt template works
-litellm.register_prompt_template(
-	    model="togethercomputer/LLaMA-2-7B-32K",
-	    roles={
-            "system": {
-                "pre_message": "[INST] <<SYS>>\n",
-                "post_message": "\n<</SYS>>\n [/INST]\n"
-            },
-            "user": {
-                "pre_message": "[INST] ",
-                "post_message": " [/INST]\n"
-            },
-            "assistant": {
-                "post_message": "\n"
-            }
-        }
-    )
-
-def test_huggingface_custom_model():
-    model = "huggingface/togethercomputer/LLaMA-2-7B-32K"
-    response = completion(model=model, messages=messages, api_base="https://ecd4sb5n09bo4ei2.us-east-1.aws.endpoints.huggingface.cloud")
-    print(response['choices'][0]['message']['content'])
-    return response
-
-test_huggingface_custom_model()
-```
-
-[Implementation Code](https://github.com/BerriAI/litellm/blob/c0b3da2c14c791a0b755f0b1e5a9ef065951ecbf/litellm/llms/huggingface_restapi.py#L52)
-
-### Deploying a model on huggingface
-
-You can use any chat/text model from Hugging Face with the following steps:
-
-- Copy your model id/url from Huggingface Inference Endpoints
-  - [ ] Go to https://ui.endpoints.huggingface.co/
-  - [ ] Copy the url of the specific model you'd like to use
-        <Image img={require('../../img/hf_inference_endpoint.png')} alt="HF_Dashboard" style={{ maxWidth: '50%', height: 'auto' }}/>
-- Set it as your model name
-- Set your HUGGINGFACE_API_KEY as an environment variable
-
-Need help deploying a model on huggingface? [Check out this guide.](https://huggingface.co/docs/inference-endpoints/guides/create_endpoint)
-
-# output
-
-Same as the OpenAI format, but also includes logprobs. [See the code](https://github.com/BerriAI/litellm/blob/b4b2dbf005142e0a483d46a07a88a19814899403/litellm/llms/huggingface_restapi.py#L115)
-
-```json
-{
-  "choices": [
-    {
-      "finish_reason": "stop",
-      "index": 0,
-      "message": {
-        "content": "\ud83d\ude31\n\nComment: @SarahSzabo I'm",
-        "role": "assistant",
-        "logprobs": -22.697942825499993
-      }
-    }
-  ],
-  "created": 1693436637.38206,
-  "model": "https://ji16r2iys9a8rjk2.us-east-1.aws.endpoints.huggingface.cloud",
-  "usage": {
-    "prompt_tokens": 14,
-    "completion_tokens": 11,
-    "total_tokens": 25
-  }
-}
-```
-
 # FAQ
 
-**Does this support stop sequences?**
+**How does billing work with Hugging Face Inference Providers?**
 
-Yes, we support stop sequences - and you can pass as many as allowed by Hugging Face (or any provider!)
+> Billing is centralized on your Hugging Face account, no matter which providers you are using. You are billed the standard provider API rates with no additional markup - Hugging Face simply passes through the provider costs. Note that [Hugging Face PRO](https://huggingface.co/subscribe/pro) users get $2 worth of Inference credits every month that can be used across providers.
 
-**How do you deal with repetition penalty?**
+**Do I need to create an account for each Inference Provider?**
 
-We map the presence penalty parameter in openai to the repetition penalty parameter on Hugging Face. [See code](https://github.com/BerriAI/litellm/blob/b4b2dbf005142e0a483d46a07a88a19814899403/litellm/utils.py#L757).
+> No, you don't need to create separate accounts. All requests are routed through Hugging Face, so you only need your HF token. This allows you to easily benchmark different providers and choose the one that best fits your needs.
+
+**Will more inference providers be supported by Hugging Face in the future?**
+
+> Yes! New inference providers (and models) are being added gradually.
 
 We welcome any suggestions for improving our Hugging Face integration - Create an [issue](https://github.com/BerriAI/litellm/issues/new/choose)/[Join the Discord](https://discord.com/invite/wuPM9dRgDw)!

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

@@ -4,17 +4,16 @@ import TabItem from '@theme/TabItem';
 # Infinity
 
 | Property                  | Details                                                                                                    |
-|-------|-------|
-| Description | Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip|
+| ------------------------- | ---------------------------------------------------------------------------------------------------------- |
+| Description               | Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip |
 | Provider Route on LiteLLM | `infinity/`                                                                                                |
-| Supported Operations | `/rerank` |
+| Supported Operations      | `/rerank`, `/embeddings`                                                                                   |
 | Link to Provider Doc      | [Infinity ↗](https://github.com/michaelfeil/infinity)                                                      |
 
-
 ## **Usage - LiteLLM Python SDK**
 
 ```python
-from litellm import rerank
+from litellm import rerank, embedding
 import os
 
 os.environ["INFINITY_API_BASE"] = "http://localhost:8080"
@@ -39,8 +38,8 @@ model_list:
   - model_name: custom-infinity-rerank
     litellm_params:
       model: infinity/rerank
-      api_key: os.environ/INFINITY_API_KEY
       api_base: https://localhost:8080
+      api_key: os.environ/INFINITY_API_KEY
 ```
 
 Start litellm
@@ -51,7 +50,9 @@ litellm --config /path/to/config.yaml
 # RUNNING on http://0.0.0.0:4000
 ```
 
-Test request
+## Test request:
+
+### Rerank
 
 ```bash
 curl http://0.0.0.0:4000/rerank \
@@ -70,11 +71,10 @@ curl http://0.0.0.0:4000/rerank \
   }'
 ```
 
-
-## Supported Cohere Rerank API Params
+#### Supported Cohere Rerank API Params
 
 | Param              | Type        | Description                                     |
-|-------|-------|-------|
+| ------------------ | ----------- | ----------------------------------------------- |
 | `query`            | `str`       | The query to rerank the documents against       |
 | `documents`        | `list[str]` | The documents to rerank                         |
 | `top_n`            | `int`       | The number of documents to return               |
@@ -138,6 +138,7 @@ response = rerank(
     raw_scores=True, # 👈 PROVIDER-SPECIFIC PARAM
 )
 ```
+
 </TabItem>
 
 <TabItem value="proxy" label="PROXY">
@@ -179,6 +180,121 @@ curl http://0.0.0.0:4000/rerank \
     "raw_scores": True # 👈 PROVIDER-SPECIFIC PARAM
   }'
 ```
+
 </TabItem>
 
 </Tabs>
+
+## Embeddings
+
+LiteLLM provides an OpenAI api compatible `/embeddings` endpoint for embedding calls.
+
+**Setup**
+
+Add this to your litellm proxy config.yaml
+
+```yaml
+model_list:
+  - model_name: custom-infinity-embedding
+    litellm_params:
+      model: infinity/provider/custom-embedding-v1
+      api_base: http://localhost:8080
+      api_key: os.environ/INFINITY_API_KEY
+```
+
+### Test request:
+
+```bash
+curl http://0.0.0.0:4000/embeddings \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "custom-infinity-embedding",
+    "input": ["hello"]
+  }'
+```
+
+#### Supported Embedding API Params
+
+| Param             | Type        | Description                                                 |
+| ----------------- | ----------- | ----------------------------------------------------------- |
+| `model`           | `str`       | The embedding model to use                                  |
+| `input`           | `list[str]` | The text inputs to generate embeddings for                  |
+| `encoding_format` | `str`       | The format to return embeddings in (e.g. "float", "base64") |
+| `modality`        | `str`       | The type of input (e.g. "text", "image", "audio")           |
+
+### Usage - Basic Examples
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import embedding
+import os
+
+os.environ["INFINITY_API_BASE"] = "http://localhost:8080"
+
+response = embedding(
+    model="infinity/bge-small",
+    input=["good morning from litellm"]
+)
+
+print(response.data[0]['embedding'])
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/embeddings \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "custom-infinity-embedding",
+    "input": ["hello"]
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+### Usage - OpenAI Client
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+  api_key="<LITELLM_MASTER_KEY>",
+  base_url="<LITELLM_URL>"
+)
+
+response = client.embeddings.create(
+  model="bge-small",
+  input=["The food was delicious and the waiter..."],
+  encoding_format="float"
+)
+
+print(response.data[0].embedding)
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/embeddings \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "bge-small",
+    "input": ["The food was delicious and the waiter..."],
+    "encoding_format": "float"
+  }'
+```
+
+</TabItem>
+</Tabs>

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

@@ -57,7 +57,7 @@ messages = [{ "content": "Hello, how are you?","role": "user"}]
 # litellm proxy call
 response = completion(
     model="litellm_proxy/your-model-name", 
-    messages, 
+    messages=messages, 
     api_base = "your-litellm-proxy-url",
     api_key = "your-litellm-proxy-api-key"
 )
@@ -76,7 +76,7 @@ messages = [{ "content": "Hello, how are you?","role": "user"}]
 # openai call
 response = completion(
     model="litellm_proxy/your-model-name", 
-    messages, 
+    messages=messages,
     api_base = "your-litellm-proxy-url", 
     stream=True
 )

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

@@ -202,6 +202,67 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 </TabItem>
 </Tabs>
 
+
+## Using Ollama FIM on `/v1/completions`
+
+LiteLLM supports calling Ollama's `/api/generate` endpoint on `/v1/completions` requests. 
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm 
+litellm._turn_on_debug() # turn on debug to see the request
+from litellm import completion
+
+response = completion(
+    model="ollama/llama3.1",
+    prompt="Hello, world!",
+    api_base="http://localhost:11434"
+)
+print(response)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml 
+
+```yaml
+model_list:
+  - model_name: "llama3.1"             
+    litellm_params:
+      model: "ollama/llama3.1"
+      api_base: "http://localhost:11434"
+```
+
+2. Start proxy 
+
+```bash
+litellm --config /path/to/config.yaml --detailed_debug
+
+# RUNNING ON http://0.0.0.0:4000 
+```
+
+3. Test it! 
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="anything", # 👈 PROXY KEY (can be anything, if master_key not set)
+    base_url="http://0.0.0.0:4000" # 👈 PROXY BASE URL
+)
+
+response = client.completions.create(
+    model="ollama/llama3.1",
+    prompt="Hello, world!",
+    api_base="http://localhost:11434"
+)
+print(response)
+```
+</TabItem>
+</Tabs>
+
 ## Using ollama `api/chat` 
 In order to send ollama requests to `POST /api/chat` on your ollama server, set the model prefix to `ollama_chat`
 

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

@@ -163,6 +163,12 @@ os.environ["OPENAI_API_BASE"] = "openaiai-api-base"     # OPTIONAL
 
 | Model Name            | Function Call                                                   |
 |-----------------------|-----------------------------------------------------------------|
+| gpt-4.1 | `response = completion(model="gpt-4.1", messages=messages)` |
+| gpt-4.1-mini | `response = completion(model="gpt-4.1-mini", messages=messages)` |
+| gpt-4.1-nano | `response = completion(model="gpt-4.1-nano", messages=messages)` |
+| o4-mini | `response = completion(model="o4-mini", messages=messages)` |
+| o3-mini | `response = completion(model="o3-mini", messages=messages)` |
+| o3 | `response = completion(model="o3", messages=messages)` |
 | o1-mini | `response = completion(model="o1-mini", messages=messages)` |
 | o1-preview | `response = completion(model="o1-preview", messages=messages)` |
 | gpt-4o-mini  | `response = completion(model="gpt-4o-mini", messages=messages)` |
@@ -228,6 +234,92 @@ response = completion(
 
 ```
 
+## PDF File Parsing
+
+OpenAI has a new `file` message type that allows you to pass in a PDF file and have it parsed into a structured output. [Read more](https://platform.openai.com/docs/guides/pdf-files?api-mode=chat&lang=python)
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import base64
+from litellm import completion
+
+with open("draconomicon.pdf", "rb") as f:
+    data = f.read()
+
+base64_string = base64.b64encode(data).decode("utf-8")
+
+completion = completion(
+    model="gpt-4o",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "file",
+                    "file": {
+                        "filename": "draconomicon.pdf",
+                        "file_data": f"data:application/pdf;base64,{base64_string}",
+                    }
+                },
+                {
+                    "type": "text",
+                    "text": "What is the first dragon in the book?",
+                }
+            ],
+        },
+    ],
+)
+
+print(completion.choices[0].message.content)
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+  - model_name: openai-model
+    litellm_params:
+      model: gpt-4o
+      api_key: os.environ/OPENAI_API_KEY
+```
+
+2. Start the proxy
+
+```bash
+litellm --config config.yaml
+```
+
+3. Test it!
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{ 
+    "model": "openai-model",
+    "messages": [
+        {"role": "user", "content": [
+            {
+                "type": "file",
+                "file": {
+                    "filename": "draconomicon.pdf",
+                    "file_data": f"data:application/pdf;base64,{base64_string}",
+                }
+            }
+        ]}
+    ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
 ## OpenAI Fine Tuned Models
 
 | Model Name                | Function Call                                                          |
@@ -239,6 +331,74 @@ response = completion(
 | fine tuned `gpt-3.5-turbo-0613` | `response = completion(model="ft:gpt-3.5-turbo-0613", messages=messages)` |
 
 
+## OpenAI Audio Transcription
+
+LiteLLM supports OpenAI Audio Transcription endpoint.
+
+Supported models:
+
+| Model Name                | Function Call                                                          |
+|---------------------------|-----------------------------------------------------------------|
+| `whisper-1`    | `response = completion(model="whisper-1", file=audio_file)`     |
+| `gpt-4o-transcribe` | `response = completion(model="gpt-4o-transcribe", file=audio_file)` |
+| `gpt-4o-mini-transcribe` | `response = completion(model="gpt-4o-mini-transcribe", file=audio_file)` |
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import transcription
+import os 
+
+# set api keys 
+os.environ["OPENAI_API_KEY"] = ""
+audio_file = open("/path/to/audio.mp3", "rb")
+
+response = transcription(model="gpt-4o-transcribe", file=audio_file)
+
+print(f"response: {response}")
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+- model_name: gpt-4o-transcribe
+  litellm_params:
+    model: gpt-4o-transcribe
+    api_key: os.environ/OPENAI_API_KEY
+  model_info:
+    mode: audio_transcription
+    
+general_settings:
+  master_key: sk-1234
+```
+
+2. Start the proxy
+
+```bash
+litellm --config config.yaml
+```
+
+3. Test it!
+
+```bash
+curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
+--header 'Authorization: Bearer sk-1234' \
+--form 'file=@"/Users/krrishdholakia/Downloads/gettysburg.wav"' \
+--form 'model="gpt-4o-transcribe"'
+```
+
+
+
+</TabItem>
+</Tabs>
+
+
+
 ## Advanced
 
 ### Getting OpenAI API Response Headers 
@@ -449,26 +609,6 @@ response = litellm.acompletion(
 )
 ```
 
-### Using Helicone Proxy with LiteLLM
-```python
-import os 
-import litellm
-from litellm import completion
-
-os.environ["OPENAI_API_KEY"] = ""
-
-# os.environ["OPENAI_API_BASE"] = ""
-litellm.api_base = "https://oai.hconeai.com/v1"
-litellm.headers = {
-    "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}",
-    "Helicone-Cache-Enabled": "true",
-}
-
-messages = [{ "content": "Hello, how are you?","role": "user"}]
-
-# openai call
-response = completion("gpt-3.5-turbo", messages)
-```
 
 ### Using OpenAI Proxy with LiteLLM
 ```python

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

@@ -10,9 +10,11 @@ LiteLLM supports all the text / chat / vision models from [OpenRouter](https://o
 import os
 from litellm import completion
 os.environ["OPENROUTER_API_KEY"] = ""
+os.environ["OPENROUTER_API_BASE"] = "" # [OPTIONAL] defaults to https://openrouter.ai/api/v1
 
-os.environ["OR_SITE_URL"] = "" # optional
-os.environ["OR_APP_NAME"] = "" # optional
+
+os.environ["OR_SITE_URL"] = "" # [OPTIONAL]
+os.environ["OR_APP_NAME"] = "" # [OPTIONAL]
 
 response = completion(
             model="openrouter/google/palm-2-chat-bison",

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

@@ -17,7 +17,7 @@ import os
 
 os.environ['PERPLEXITYAI_API_KEY'] = ""
 response = completion(
-    model="perplexity/mistral-7b-instruct", 
+    model="perplexity/sonar-pro", 
     messages=messages
 )
 print(response)
@@ -30,7 +30,7 @@ import os
 
 os.environ['PERPLEXITYAI_API_KEY'] = ""
 response = completion(
-    model="perplexity/mistral-7b-instruct", 
+    model="perplexity/sonar-pro", 
     messages=messages,
     stream=True
 )
@@ -45,19 +45,12 @@ All models listed here https://docs.perplexity.ai/docs/model-cards are supported
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| pplx-7b-chat | `completion(model="perplexity/pplx-7b-chat", messages)` | 
-| pplx-70b-chat | `completion(model="perplexity/pplx-70b-chat", messages)` | 
-| pplx-7b-online | `completion(model="perplexity/pplx-7b-online", messages)` | 
-| pplx-70b-online | `completion(model="perplexity/pplx-70b-online", messages)` | 
-| codellama-34b-instruct | `completion(model="perplexity/codellama-34b-instruct", messages)` | 
-| llama-2-13b-chat | `completion(model="perplexity/llama-2-13b-chat", messages)` | 
-| llama-2-70b-chat | `completion(model="perplexity/llama-2-70b-chat", messages)` | 
-| mistral-7b-instruct | `completion(model="perplexity/mistral-7b-instruct", messages)` | 
-| openhermes-2-mistral-7b | `completion(model="perplexity/openhermes-2-mistral-7b", messages)` | 
-| openhermes-2.5-mistral-7b | `completion(model="perplexity/openhermes-2.5-mistral-7b", messages)` | 
-| pplx-7b-chat-alpha | `completion(model="perplexity/pplx-7b-chat-alpha", messages)` | 
-| pplx-70b-chat-alpha | `completion(model="perplexity/pplx-70b-chat-alpha", messages)` | 
-
+| sonar-deep-research | `completion(model="perplexity/sonar-deep-research", messages)` | 
+| sonar-reasoning-pro | `completion(model="perplexity/sonar-reasoning-pro", messages)` | 
+| sonar-reasoning | `completion(model="perplexity/sonar-reasoning", messages)` | 
+| sonar-pro | `completion(model="perplexity/sonar-pro", messages)` | 
+| sonar | `completion(model="perplexity/sonar", messages)` | 
+| r1-1776 | `completion(model="perplexity/r1-1776", messages)` | 
 
 
 

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

@@ -230,7 +230,7 @@ response = completion(
     model="predibase/llama-3-8b-instruct", 
     messages = [{ "content": "Hello, how are you?","role": "user"}],
     adapter_id="my_repo/3",
-    adapter_soruce="pbase",
+    adapter_source="pbase",
 )
 ```
 

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

@@ -347,7 +347,7 @@ Return a `list[Recipe]`
 completion(model="vertex_ai/gemini-1.5-flash-preview-0514", messages=messages, response_format={ "type": "json_object" })
 ```
 
-### **Grounding**
+### **Grounding - Web Search**
 
 Add Google Search Result grounding to vertex ai calls. 
 
@@ -358,7 +358,7 @@ See the grounding metadata with `response_obj._hidden_params["vertex_ai_groundin
 <Tabs>
 <TabItem value="sdk" label="SDK">
 
-```python 
+```python showLineNumbers
 from litellm import completion 
 
 ## SETUP ENVIRONMENT
@@ -377,14 +377,36 @@ print(resp)
 </TabItem>
 <TabItem value="proxy" label="PROXY">
 
-```bash
+<Tabs>
+<TabItem value="openai" label="OpenAI Python SDK">
+
+```python showLineNumbers
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-1234", # pass litellm proxy key, if you're using virtual keys
+    base_url="http://0.0.0.0:4000/v1/" # point to litellm proxy
+)
+
+response = client.chat.completions.create(
+    model="gemini-pro",
+    messages=[{"role": "user", "content": "Who won the world cup?"}],
+    tools=[{"googleSearchRetrieval": {}}],
+)
+
+print(response)
+```
+</TabItem>
+<TabItem value="curl" label="cURL">
+
+```bash showLineNumbers
 curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
     "model": "gemini-pro",
     "messages": [
-      {"role": "user", "content": "Hello, Claude!"}
+      {"role": "user", "content": "Who won the world cup?"}
     ],
    "tools": [
         {
@@ -394,10 +416,82 @@ curl http://localhost:4000/v1/chat/completions \
   }'
 
 ```
+</TabItem>
+</Tabs>
 
 </TabItem>
 </Tabs>
 
+You can also use the `enterpriseWebSearch` tool for an [enterprise compliant search](https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/web-grounding-enterprise).
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+from litellm import completion 
+
+## SETUP ENVIRONMENT
+# !gcloud auth application-default login - run this to add vertex credentials to your env
+
+tools = [{"enterpriseWebSearch": {}}] # 👈 ADD GOOGLE ENTERPRISE SEARCH
+
+resp = litellm.completion(
+                    model="vertex_ai/gemini-1.0-pro-001",
+                    messages=[{"role": "user", "content": "Who won the world cup?"}],
+                    tools=tools,
+                )
+
+print(resp)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+<Tabs>
+<TabItem value="openai" label="OpenAI Python SDK">
+
+```python showLineNumbers
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-1234", # pass litellm proxy key, if you're using virtual keys
+    base_url="http://0.0.0.0:4000/v1/" # point to litellm proxy
+)
+
+response = client.chat.completions.create(
+    model="gemini-pro",
+    messages=[{"role": "user", "content": "Who won the world cup?"}],
+    tools=[{"enterpriseWebSearch": {}}],
+)
+
+print(response)
+```
+</TabItem>
+<TabItem value="curl" label="cURL">
+
+```bash showLineNumbers
+curl http://localhost:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer sk-1234" \
+  -d '{
+    "model": "gemini-pro",
+    "messages": [
+      {"role": "user", "content": "Who won the world cup?"}
+    ],
+   "tools": [
+        {
+            "enterpriseWebSearch": {} 
+        }
+    ]
+  }'
+
+```
+</TabItem>
+</Tabs>
+
+</TabItem>
+</Tabs>
+
+
 #### **Moving from Vertex AI SDK to LiteLLM (GROUNDING)**
 
 
@@ -448,6 +542,154 @@ print(resp)
 ```
 
 
+### **Thinking / `reasoning_content`**
+
+LiteLLM translates OpenAI's `reasoning_effort` to Gemini's `thinking` parameter. [Code](https://github.com/BerriAI/litellm/blob/620664921902d7a9bfb29897a7b27c1a7ef4ddfb/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py#L362)
+
+**Mapping**
+
+| reasoning_effort | thinking |
+| ---------------- | -------- |
+| "low"            | "budget_tokens": 1024 |
+| "medium"         | "budget_tokens": 2048 |
+| "high"           | "budget_tokens": 4096 |
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+# !gcloud auth application-default login - run this to add vertex credentials to your env
+
+resp = completion(
+    model="vertex_ai/gemini-2.5-flash-preview-04-17",
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+    reasoning_effort="low",
+    vertex_project="project-id",
+    vertex_location="us-central1"
+)
+
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+- model_name: gemini-2.5-flash
+  litellm_params:
+    model: vertex_ai/gemini-2.5-flash-preview-04-17
+    vertex_credentials: {"project_id": "project-id", "location": "us-central1", "project_key": "project-key"}
+    vertex_project: "project-id"
+    vertex_location: "us-central1"
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
+  -d '{
+    "model": "gemini-2.5-flash",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "reasoning_effort": "low"
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
+**Expected Response**
+
+```python
+ModelResponse(
+    id='chatcmpl-c542d76d-f675-4e87-8e5f-05855f5d0f5e',
+    created=1740470510,
+    model='claude-3-7-sonnet-20250219',
+    object='chat.completion',
+    system_fingerprint=None,
+    choices=[
+        Choices(
+            finish_reason='stop',
+            index=0,
+            message=Message(
+                content="The capital of France is Paris.",
+                role='assistant',
+                tool_calls=None,
+                function_call=None,
+                reasoning_content='The capital of France is Paris. This is a very straightforward factual question.'
+            ),
+        )
+    ],
+    usage=Usage(
+        completion_tokens=68,
+        prompt_tokens=42,
+        total_tokens=110,
+        completion_tokens_details=None,
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            audio_tokens=None,
+            cached_tokens=0,
+            text_tokens=None,
+            image_tokens=None
+        ),
+        cache_creation_input_tokens=0,
+        cache_read_input_tokens=0
+    )
+)
+```
+
+#### Pass `thinking` to Gemini models
+
+You can also pass the `thinking` parameter to Gemini models.
+
+This is translated to Gemini's [`thinkingConfig` parameter](https://ai.google.dev/gemini-api/docs/thinking#set-budget).
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+# !gcloud auth application-default login - run this to add vertex credentials to your env
+
+response = litellm.completion(
+  model="vertex_ai/gemini-2.5-flash-preview-04-17",
+  messages=[{"role": "user", "content": "What is the capital of France?"}],
+  thinking={"type": "enabled", "budget_tokens": 1024},
+  vertex_project="project-id",
+  vertex_location="us-central1"
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "vertex_ai/gemini-2.5-flash-preview-04-17",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "thinking": {"type": "enabled", "budget_tokens": 1024}
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+
 ### **Context Caching**
 
 Use Vertex AI context caching is supported by calling provider api directly. (Unified Endpoint support comin soon.).
@@ -1369,6 +1611,103 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 </Tabs>
 
 
+## Gemini Pro
+| Model Name       | Function Call                        |
+|------------------|--------------------------------------|
+| gemini-pro   | `completion('gemini-pro', messages)`, `completion('vertex_ai/gemini-pro', messages)` |
+
+## Fine-tuned Models
+
+You can call fine-tuned Vertex AI Gemini models through LiteLLM
+
+| Property | Details |
+|----------|---------|
+| Provider Route | `vertex_ai/gemini/{MODEL_ID}` |
+| Vertex Documentation | [Vertex AI - Fine-tuned Gemini Models](https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini-use-supervised-tuning#test_the_tuned_model_with_a_prompt)|
+| Supported Operations | `/chat/completions`, `/completions`, `/embeddings`, `/images` |
+
+To use a model that follows the `/gemini` request/response format, simply set the model parameter as 
+
+```python title="Model parameter for calling fine-tuned gemini models"
+model="vertex_ai/gemini/<your-finetuned-model>"
+```
+
+<Tabs>
+<TabItem value="sdk" label="LiteLLM Python SDK">
+
+```python showLineNumbers title="Example"
+import litellm
+import os
+
+## set ENV variables
+os.environ["VERTEXAI_PROJECT"] = "hardy-device-38811"
+os.environ["VERTEXAI_LOCATION"] = "us-central1"
+
+response = litellm.completion(
+  model="vertex_ai/gemini/<your-finetuned-model>",  # e.g. vertex_ai/gemini/4965075652664360960
+  messages=[{ "content": "Hello, how are you?","role": "user"}],
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+1. Add Vertex Credentials to your env 
+
+```bash title="Authenticate to Vertex AI"
+!gcloud auth application-default login
+```
+
+2. Setup config.yaml 
+
+```yaml showLineNumbers title="Add to litellm config"
+- model_name: finetuned-gemini
+  litellm_params:
+    model: vertex_ai/gemini/<ENDPOINT_ID>
+    vertex_project: <PROJECT_ID>
+    vertex_location: <LOCATION>
+```
+
+3. Test it! 
+
+<Tabs>
+<TabItem value="openai" label="OpenAI Python SDK">
+
+```python showLineNumbers title="Example request"
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="your-litellm-key",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.chat.completions.create(
+    model="finetuned-gemini",
+    messages=[
+        {"role": "user", "content": "hi"}
+    ]
+)
+print(response)
+```
+
+</TabItem>
+<TabItem value="curl" label="curl">
+
+```bash showLineNumbers title="Example request"
+curl --location 'https://0.0.0.0:4000/v1/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: <LITELLM_KEY>' \
+--data '{"model": "finetuned-gemini" ,"messages":[{"role": "user", "content":[{"type": "text", "text": "hi"}]}]}'
+```
+
+</TabItem>
+</Tabs>
+
+</TabItem>
+</Tabs>
+
+
+
 ## Model Garden
 
 :::tip
@@ -1479,67 +1818,6 @@ response = completion(
 </Tabs>
 
 
-## Gemini Pro
-| Model Name       | Function Call                        |
-|------------------|--------------------------------------|
-| gemini-pro   | `completion('gemini-pro', messages)`, `completion('vertex_ai/gemini-pro', messages)` |
-
-## Fine-tuned Models
-
-Fine tuned models on vertex have a numerical model/endpoint id. 
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-```python
-from litellm import completion
-import os
-
-## set ENV variables
-os.environ["VERTEXAI_PROJECT"] = "hardy-device-38811"
-os.environ["VERTEXAI_LOCATION"] = "us-central1"
-
-response = completion(
-  model="vertex_ai/<your-finetuned-model>",  # e.g. vertex_ai/4965075652664360960
-  messages=[{ "content": "Hello, how are you?","role": "user"}],
-  base_model="vertex_ai/gemini-1.5-pro" # the base model - used for routing
-)
-```
-
-</TabItem>
-<TabItem value="proxy" label="PROXY">
-
-1. Add Vertex Credentials to your env 
-
-```bash
-!gcloud auth application-default login
-```
-
-2. Setup config.yaml 
-
-```yaml
-- model_name: finetuned-gemini
-  litellm_params:
-    model: vertex_ai/<ENDPOINT_ID>
-    vertex_project: <PROJECT_ID>
-    vertex_location: <LOCATION>
-  model_info:
-    base_model: vertex_ai/gemini-1.5-pro # IMPORTANT
-```
-
-3. Test it! 
-
-```bash
-curl --location 'https://0.0.0.0:4000/v1/chat/completions' \
---header 'Content-Type: application/json' \
---header 'Authorization: <LITELLM_KEY>' \
---data '{"model": "finetuned-gemini" ,"messages":[{"role": "user", "content":[{"type": "text", "text": "hi"}]}]}'
-```
-
-</TabItem>
-</Tabs>
-
-
 
 ## Gemini Pro Vision
 | Model Name       | Function Call                        |
@@ -1684,23 +1962,25 @@ assert isinstance(
 ```
 
 
-## Usage - PDF / Videos / etc. Files 
+## Usage - PDF / Videos / Audio etc. Files 
 
 Pass any file supported by Vertex AI, through LiteLLM. 
 
-LiteLLM Supports the following image types passed in url
+LiteLLM Supports the following file types passed in url. 
+
+Using `file` message type for VertexAI is live from v1.65.1+ 
 
 ```
-Images with Cloud Storage URIs - gs://cloud-samples-data/generative-ai/image/boats.jpeg
-Images with direct links - https://storage.googleapis.com/github-repo/img/gemini/intro/landmark3.jpg
+Files with Cloud Storage URIs - gs://cloud-samples-data/generative-ai/image/boats.jpeg
+Files with direct links - https://storage.googleapis.com/github-repo/img/gemini/intro/landmark3.jpg
 Videos with Cloud Storage URIs - https://storage.googleapis.com/github-repo/img/gemini/multimodality_usecases_overview/pixel8.mp4
-Base64 Encoded Local Images
+Base64 Encoded Local Files
 ```
 
 <Tabs>
 <TabItem value="sdk" label="SDK">
 
-### **Using `gs://`**
+### **Using `gs://` or any URL**
 ```python
 from litellm import completion
 
@@ -1712,8 +1992,11 @@ response = completion(
             "content": [
                 {"type": "text", "text": "You are a very professional document summarization specialist. Please summarize the given document."},
                 {
-                    "type": "image_url",
-                    "image_url": "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf", # 👈 PDF
+                    "type": "file",
+                    "file": {
+                        "file_id": "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf",
+                        "format": "application/pdf" # OPTIONAL - specify mime-type
+                    }
                 },
             ],
         }
@@ -1747,8 +2030,16 @@ response = completion(
             "content": [
                 {"type": "text", "text": "You are a very professional document summarization specialist. Please summarize the given document."},
                 {
-                    "type": "image_url",
-                    "image_url": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                    "type": "file",
+                    "file": {
+                        "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                    }  
+                },
+                {
+                    "type": "audio_input",
+                    "audio_input {
+                        "audio_input": f"data:audio/mp3;base64,{encoded_file}", # 👈 AUDIO File ('file' message works as too)
+                    }  
                 },
             ],
         }
@@ -1794,8 +2085,11 @@ curl http://0.0.0.0:4000/v1/chat/completions \
             "text": "You are a very professional document summarization specialist. Please summarize the given document"
           },
           {
-                "type": "image_url",
-                "image_url": "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf" # 👈 PDF
+                "type": "file",
+                "file": {
+                    "file_id": "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf",
+                    "format": "application/pdf" # OPTIONAL
+                }
             }
           }
         ]
@@ -1822,10 +2116,17 @@ curl http://0.0.0.0:4000/v1/chat/completions \
             "text": "You are a very professional document summarization specialist. Please summarize the given document"
           },
           {
-                "type": "image_url",
-                "image_url": "data:application/pdf;base64,{encoded_file}" # 👈 PDF
-            }
+                "type": "file",
+                "file": {
+                    "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
+                },
+            },
+            {
+                "type": "audio_input",
+                "audio_input {
+                    "audio_input": f"data:audio/mp3;base64,{encoded_file}", # 👈 AUDIO File ('file' message works as too)
                 }  
+            },
     ]
       }
     ],
@@ -1836,6 +2137,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
 </TabItem>
 </Tabs>
 
+
 ## Chat Models
 | Model Name       | Function Call                        |
 |------------------|--------------------------------------|
@@ -2044,7 +2346,12 @@ print(response)
 
 ## **Multi-Modal Embeddings**
 
-Usage
+
+Known Limitations:
+- Only supports 1 image / video / image per request
+- Only supports GCS or base64 encoded images / videos
+
+### Usage
 
 <Tabs>
 <TabItem value="sdk" label="SDK">
@@ -2260,6 +2567,115 @@ print(f"Text Embedding: {embeddings.text_embedding}")
 </Tabs>
 
 
+### Text + Image + Video Embeddings
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+Text + Image 
+
+```python
+response = await litellm.aembedding(
+    model="vertex_ai/multimodalembedding@001",
+    input=["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"] # will be sent as a gcs image
+)
+```
+
+Text + Video 
+
+```python
+response = await litellm.aembedding(
+    model="vertex_ai/multimodalembedding@001",
+    input=["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image
+)
+```
+
+Image + Video 
+
+```python
+response = await litellm.aembedding(
+    model="vertex_ai/multimodalembedding@001",
+    input=["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image
+)
+```
+
+
+</TabItem>
+<TabItem value="proxy" label="LiteLLM PROXY (Unified Endpoint)">
+
+1. Add model to config.yaml
+```yaml
+model_list:
+  - model_name: multimodalembedding@001
+    litellm_params:
+      model: vertex_ai/multimodalembedding@001
+      vertex_project: "adroit-crow-413218"
+      vertex_location: "us-central1"
+      vertex_credentials: adroit-crow-413218-a956eef1a2a8.json 
+
+litellm_settings:
+  drop_params: True
+```
+
+2. Start Proxy 
+
+```
+$ litellm --config /path/to/config.yaml
+```
+
+3. Make Request use OpenAI Python SDK, Langchain Python SDK
+
+
+Text + Image 
+
+```python
+import openai
+
+client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000")
+
+# # request sent to model set on litellm proxy, `litellm --model`
+response = client.embeddings.create(
+    model="multimodalembedding@001", 
+    input = ["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"],
+)
+
+print(response)
+```
+
+Text + Video 
+```python
+import openai
+
+client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000")
+
+# # request sent to model set on litellm proxy, `litellm --model`
+response = client.embeddings.create(
+    model="multimodalembedding@001", 
+    input = ["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"],
+)
+
+print(response)
+```
+
+Image + Video 
+```python
+import openai
+
+client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000")
+
+# # request sent to model set on litellm proxy, `litellm --model`
+response = client.embeddings.create(
+    model="multimodalembedding@001", 
+    input = ["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"],
+)
+
+print(response)
+```
+
+</TabItem>
+</Tabs>
+
+
 ## **Image Generation Models**
 
 Usage 

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

@@ -161,6 +161,120 @@ curl -L -X POST 'http://0.0.0.0:4000/embeddings' \
 
 Example Implementation from VLLM [here](https://github.com/vllm-project/vllm/pull/10020)
 
+<Tabs>
+<TabItem value="files_message" label="(Unified) Files Message">
+
+Use this to send a video url to VLLM + Gemini in the same format, using OpenAI's `files` message type.
+
+There are two ways to send a video url to VLLM:
+
+1. Pass the video url directly
+
+```
+{"type": "file", "file": {"file_id": video_url}},
+```
+
+2. Pass the video data as base64
+
+```
+{"type": "file", "file": {"file_data": f"data:video/mp4;base64,{video_data_base64}"}}
+```
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+messages=[
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "Summarize the following video"
+            },
+            {
+                "type": "file",
+                "file": {
+                    "file_id": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+                }
+            }
+        ]
+    }
+]
+
+# call vllm 
+os.environ["HOSTED_VLLM_API_BASE"] = "https://hosted-vllm-api.co"
+os.environ["HOSTED_VLLM_API_KEY"] = "" # [optional], if your VLLM server requires an API key
+response = completion(
+    model="hosted_vllm/qwen", # pass the vllm model name
+    messages=messages,
+)
+
+# call gemini 
+os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"
+response = completion(
+    model="gemini/gemini-1.5-flash", # pass the gemini model name
+    messages=messages,
+)
+
+print(response)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+    - model_name: my-model
+      litellm_params:
+        model: hosted_vllm/qwen  # add hosted_vllm/ prefix to route as OpenAI provider
+        api_base: https://hosted-vllm-api.co      # add api base for OpenAI compatible provider
+    - model_name: my-gemini-model
+      litellm_params:
+        model: gemini/gemini-1.5-flash  # add gemini/ prefix to route as Google AI Studio provider
+        api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start the proxy 
+
+```bash
+$ litellm --config /path/to/config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+3. Test it! 
+
+```bash
+curl -X POST http://0.0.0.0:4000/chat/completions \
+-H "Authorization: Bearer sk-1234" \
+-H "Content-Type: application/json" \
+-d '{
+    "model": "my-model",
+    "messages": [
+        {"role": "user", "content": 
+            [
+                {"type": "text", "text": "Summarize the following video"},
+                {"type": "file", "file": {"file_id": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}}
+            ]
+        }
+    ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+
+</TabItem>
+<TabItem value="video_url" label="(VLLM-specific) Video Message">
+
+Use this to send a video url to VLLM in it's native message format (`video_url`).
+
 There are two ways to send a video url to VLLM:
 
 1. Pass the video url directly
@@ -249,6 +363,10 @@ curl -X POST http://0.0.0.0:4000/chat/completions \
 </Tabs>
 
 
+</TabItem>
+</Tabs>
+
+
 ## (Deprecated) for `vllm pip package` 
 ### Using - `litellm.completion`
 

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

@@ -18,13 +18,14 @@ os.environ['XAI_API_KEY']
 ```
 
 ## Sample Usage
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Non-streaming"
 from litellm import completion
 import os
 
 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-2-latest",
+    model="xai/grok-3-mini-beta",
     messages=[
         {
             "role": "user",
@@ -45,13 +46,14 @@ print(response)
 ```
 
 ## Sample Usage - Streaming
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Streaming"
 from litellm import completion
 import os
 
 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-2-latest",
+    model="xai/grok-3-mini-beta",
     messages=[
         {
             "role": "user",
@@ -75,14 +77,15 @@ for chunk in response:
 ```
 
 ## Sample Usage - Vision
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Vision"
 import os 
 from litellm import completion
 
 os.environ["XAI_API_KEY"] = "your-api-key"
 
 response = completion(
-    model="xai/grok-2-latest",
+    model="xai/grok-2-vision-latest",
     messages=[
         {
             "role": "user",
@@ -110,7 +113,7 @@ Here's how to call a XAI model with the LiteLLM Proxy Server
 
 1. Modify the config.yaml 
 
-  ```yaml
+  ```yaml showLineNumbers
   model_list:
     - model_name: my-model
       litellm_params:
@@ -131,7 +134,7 @@ Here's how to call a XAI model with the LiteLLM Proxy Server
 
   <TabItem value="openai" label="OpenAI Python v1.0.0+">
 
-  ```python
+  ```python showLineNumbers
   import openai
   client = openai.OpenAI(
       api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
@@ -173,3 +176,81 @@ Here's how to call a XAI model with the LiteLLM Proxy Server
   </Tabs>
 
 
+## Reasoning Usage
+
+LiteLLM supports reasoning usage for xAI models.
+
+<Tabs>
+
+<TabItem value="python" label="LiteLLM Python SDK">
+
+```python showLineNumbers title="reasoning with xai/grok-3-mini-beta"
+import litellm
+response = litellm.completion(
+    model="xai/grok-3-mini-beta",
+    messages=[{"role": "user", "content": "What is 101*3?"}],
+    reasoning_effort="low",
+)
+
+print("Reasoning Content:")
+print(response.choices[0].message.reasoning_content)
+
+print("\nFinal Response:")
+print(completion.choices[0].message.content)
+
+print("\nNumber of completion tokens (input):")
+print(completion.usage.completion_tokens)
+
+print("\nNumber of reasoning tokens (input):")
+print(completion.usage.completion_tokens_details.reasoning_tokens)
+```
+</TabItem>
+
+<TabItem value="curl" label="LiteLLM Proxy - OpenAI SDK Usage">
+
+```python showLineNumbers title="reasoning with xai/grok-3-mini-beta"
+import openai
+client = openai.OpenAI(
+    api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
+    base_url="http://0.0.0.0:4000" # litellm-proxy-base url
+)
+
+response = client.chat.completions.create(
+    model="xai/grok-3-mini-beta",
+    messages=[{"role": "user", "content": "What is 101*3?"}],
+    reasoning_effort="low",
+)
+
+print("Reasoning Content:")
+print(response.choices[0].message.reasoning_content)
+
+print("\nFinal Response:")
+print(completion.choices[0].message.content)
+
+print("\nNumber of completion tokens (input):")
+print(completion.usage.completion_tokens)
+
+print("\nNumber of reasoning tokens (input):")
+print(completion.usage.completion_tokens_details.reasoning_tokens)
+```
+
+</TabItem>
+</Tabs>
+
+**Example Response:**
+
+```shell
+Reasoning Content:
+Let me calculate 101 multiplied by 3:
+101 * 3 = 303.
+I can double-check that: 100 * 3 is 300, and 1 * 3 is 3, so 300 + 3 = 303. Yes, that's correct.
+
+Final Response:
+The result of 101 multiplied by 3 is 303.
+
+Number of completion tokens (input):
+14
+
+Number of reasoning tokens (input):
+310
+```

docs/my-website/docs/proxy/admin_ui_sso.md

@@ -147,11 +147,16 @@ Some SSO providers require a specific redirect url for login and logout. You can
 - Login: `<your-proxy-base-url>/sso/key/generate`
 - Logout: `<your-proxy-base-url>`
 
+Here's the env var to set the logout url on the proxy
+```bash
+PROXY_LOGOUT_URL="https://www.google.com"
+```
+
 #### Step 3. Set `PROXY_BASE_URL` in your .env
 
 Set this in your .env (so the proxy can set the correct redirect url)
 ```shell
-PROXY_BASE_URL=https://litellm-api.up.railway.app/
+PROXY_BASE_URL=https://litellm-api.up.railway.app
 ```
 
 #### Step 4. Test flow

docs/my-website/docs/proxy/call_hooks.md

@@ -70,6 +70,21 @@ class MyCustomHandler(CustomLogger): # https://docs.litellm.ai/docs/observabilit
         response: str,
     ):
         pass
+
+    aasync def async_post_call_streaming_iterator_hook(
+        self,
+        user_api_key_dict: UserAPIKeyAuth,
+        response: Any,
+        request_data: dict,
+    ) -> AsyncGenerator[ModelResponseStream, None]:
+        """
+        Passes the entire stream to the guardrail
+
+        This is useful for plugins that need to see the entire stream.
+        """
+        async for item in response:
+            yield item
+
 proxy_handler_instance = MyCustomHandler()
 ```
 

docs/my-website/docs/proxy/config_settings.md

@@ -147,6 +147,7 @@ general_settings:
 |------|------|-------------|
 | completion_model | string | The default model to use for completions when `model` is not specified in the request |
 | disable_spend_logs | boolean | If true, turns off writing each transaction to the database |
+| disable_spend_updates | boolean | If true, turns off all spend updates to the DB. Including key/user/team spend updates. |
 | disable_master_key_return | boolean | If true, turns off returning master key on UI. (checked on '/user/info' endpoint) |
 | disable_retry_on_max_parallel_request_limit_error | boolean | If true, turns off retries when max parallel request limit is reached |
 | disable_reset_budget | boolean | If true, turns off reset budget scheduled task |
@@ -159,7 +160,7 @@ general_settings:
 | database_url | string | The URL for the database connection [Set up Virtual Keys](virtual_keys) |
 | database_connection_pool_limit | integer | The limit for database connection pool [Setting DB Connection Pool limit](#configure-db-pool-limits--connection-timeouts) |
 | database_connection_timeout | integer | The timeout for database connections in seconds [Setting DB Connection Pool limit, timeout](#configure-db-pool-limits--connection-timeouts) |
-| allow_requests_on_db_unavailable | boolean | If true, allows requests to succeed even if DB is unreachable. **Only use this if running LiteLLM in your VPC** This will allow requests to work even when LiteLLM cannot connect to the DB to verify a Virtual Key |
+| allow_requests_on_db_unavailable | boolean | If true, allows requests to succeed even if DB is unreachable. **Only use this if running LiteLLM in your VPC** This will allow requests to work even when LiteLLM cannot connect to the DB to verify a Virtual Key [Doc on graceful db unavailability](prod#5-if-running-litellm-on-vpc-gracefully-handle-db-unavailability) |
 | custom_auth | string | Write your own custom authentication logic [Doc Custom Auth](virtual_keys#custom-auth) |
 | max_parallel_requests | integer | The max parallel requests allowed per deployment |
 | global_max_parallel_requests | integer | The max parallel requests allowed on the proxy overall |
@@ -177,7 +178,7 @@ general_settings:
 | use_x_forwarded_for | str | If true, uses the X-Forwarded-For header to get the client IP address |
 | service_account_settings | List[Dict[str, Any]] | Set `service_account_settings` if you want to create settings that only apply to service account keys (Doc on service accounts)[./service_accounts.md] | 
 | image_generation_model | str | The default model to use for image generation - ignores model set in request |
-| store_model_in_db | boolean | If true, allows `/model/new` endpoint to store model information in db. Endpoint disabled by default. [Doc on `/model/new` endpoint](./model_management.md#create-a-new-model) |
+| store_model_in_db | boolean | If true, enables storing model + credential information in the DB. |
 | store_prompts_in_spend_logs | boolean | If true, allows prompts and responses to be stored in the spend logs table. |
 | max_request_size_mb | int | The maximum size for requests in MB. Requests above this size will be rejected. |
 | max_response_size_mb | int | The maximum size for responses in MB. LLM Responses above this size will not be sent. |
@@ -298,6 +299,9 @@ router_settings:
 |------|-------------|
 | ACTIONS_ID_TOKEN_REQUEST_TOKEN | Token for requesting ID in GitHub Actions
 | ACTIONS_ID_TOKEN_REQUEST_URL | URL for requesting ID token in GitHub Actions
+| AGENTOPS_ENVIRONMENT | Environment for AgentOps logging integration
+| AGENTOPS_API_KEY | API Key for AgentOps logging integration
+| AGENTOPS_SERVICE_NAME | Service Name for AgentOps logging integration
 | AISPEND_ACCOUNT_ID | Account ID for AI Spend
 | AISPEND_API_KEY | API Key for AI Spend
 | ALLOWED_EMAIL_DOMAINS | List of email domains allowed for access
@@ -322,6 +326,9 @@ router_settings:
 | AZURE_AUTHORITY_HOST | Azure authority host URL
 | AZURE_CLIENT_ID | Client ID for Azure services
 | AZURE_CLIENT_SECRET | Client secret for Azure services
+| AZURE_TENANT_ID | Tenant ID for Azure Active Directory
+| AZURE_USERNAME | Username for Azure services, use in conjunction with AZURE_PASSWORD for azure ad token with basic username/password workflow
+| AZURE_PASSWORD | Password for Azure services, use in conjunction with AZURE_USERNAME for azure ad token with basic username/password workflow
 | AZURE_FEDERATED_TOKEN_FILE | File path to Azure federated token
 | AZURE_KEY_VAULT_URI | URI for Azure Key Vault
 | AZURE_STORAGE_ACCOUNT_KEY | The Azure Storage Account Key to use for Authentication to Azure Blob Storage logging
@@ -330,7 +337,6 @@ router_settings:
 | AZURE_STORAGE_TENANT_ID | The Application Tenant ID to use for Authentication to Azure Blob Storage logging
 | AZURE_STORAGE_CLIENT_ID | The Application Client ID to use for Authentication to Azure Blob Storage logging
 | AZURE_STORAGE_CLIENT_SECRET | The Application Client Secret to use for Authentication to Azure Blob Storage logging
-| AZURE_TENANT_ID | Tenant ID for Azure Active Directory
 | BERRISPEND_ACCOUNT_ID | Account ID for BerriSpend service
 | BRAINTRUST_API_KEY | API key for Braintrust integration
 | CIRCLE_OIDC_TOKEN | OpenID Connect token for CircleCI
@@ -405,6 +411,7 @@ router_settings:
 | HELICONE_API_KEY | API key for Helicone service
 | HOSTNAME | Hostname for the server, this will be [emitted to `datadog` logs](https://docs.litellm.ai/docs/proxy/logging#datadog)
 | HUGGINGFACE_API_BASE | Base URL for Hugging Face API
+| HUGGINGFACE_API_KEY | API key for Hugging Face API
 | IAM_TOKEN_DB_AUTH | IAM token for database authentication
 | JSON_LOGS | Enable JSON formatted logging
 | JWT_AUDIENCE | Expected audience for JWT tokens
@@ -431,6 +438,7 @@ router_settings:
 | LITERAL_BATCH_SIZE | Batch size for Literal operations
 | LITELLM_DONT_SHOW_FEEDBACK_BOX | Flag to hide feedback box in LiteLLM UI
 | LITELLM_DROP_PARAMS | Parameters to drop in LiteLLM requests
+| LITELLM_MODIFY_PARAMS | Parameters to modify in LiteLLM requests
 | LITELLM_EMAIL | Email associated with LiteLLM account
 | LITELLM_GLOBAL_MAX_PARALLEL_REQUEST_RETRIES | Maximum retries for parallel requests in LiteLLM
 | LITELLM_GLOBAL_MAX_PARALLEL_REQUEST_RETRY_TIMEOUT | Timeout for retries of parallel requests in LiteLLM
@@ -444,9 +452,12 @@ router_settings:
 | LITELLM_TOKEN | Access token for LiteLLM integration
 | LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD | If true, prints the standard logging payload to the console - useful for debugging
 | LOGFIRE_TOKEN | Token for Logfire logging service
+| MISTRAL_API_BASE | Base URL for Mistral API
+| MISTRAL_API_KEY | API key for Mistral API
 | MICROSOFT_CLIENT_ID | Client ID for Microsoft services
 | MICROSOFT_CLIENT_SECRET | Client secret for Microsoft services
 | MICROSOFT_TENANT | Tenant ID for Microsoft Azure
+| MICROSOFT_SERVICE_PRINCIPAL_ID | Service Principal ID for Microsoft Enterprise Application. (This is an advanced feature if you want litellm to auto-assign members to Litellm Teams based on their Microsoft Entra ID Groups)
 | NO_DOCS | Flag to disable documentation generation
 | NO_PROXY | List of addresses to bypass proxy
 | OAUTH_TOKEN_INFO_ENDPOINT | Endpoint for OAuth token info retrieval
@@ -478,7 +489,7 @@ router_settings:
 | PROXY_ADMIN_ID | Admin identifier for proxy server
 | PROXY_BASE_URL | Base URL for proxy service
 | PROXY_LOGOUT_URL | URL for logging out of the proxy service
-| PROXY_MASTER_KEY | Master key for proxy authentication
+| LITELLM_MASTER_KEY | Master key for proxy authentication
 | QDRANT_API_BASE | Base URL for Qdrant API
 | QDRANT_API_KEY | API key for Qdrant service
 | QDRANT_URL | Connection URL for Qdrant database
@@ -499,9 +510,11 @@ router_settings:
 | SMTP_USERNAME | Username for SMTP authentication (do not set if SMTP does not require auth)
 | SPEND_LOGS_URL | URL for retrieving spend logs
 | SSL_CERTIFICATE | Path to the SSL certificate file
+| SSL_SECURITY_LEVEL | [BETA] Security level for SSL/TLS connections. E.g. `DEFAULT@SECLEVEL=1`
 | SSL_VERIFY | Flag to enable or disable SSL certificate verification
 | SUPABASE_KEY | API key for Supabase service
 | SUPABASE_URL | Base URL for Supabase instance
+| STORE_MODEL_IN_DB | If true, enables storing model + credential information in the DB. 
 | TEST_EMAIL_ADDRESS | Email address used for testing purposes
 | UI_LOGO_PATH | Path to the logo image used in the UI
 | UI_PASSWORD | Password for accessing the UI
@@ -512,5 +525,5 @@ router_settings:
 | UPSTREAM_LANGFUSE_RELEASE | Release version identifier for upstream Langfuse
 | UPSTREAM_LANGFUSE_SECRET_KEY | Secret key for upstream Langfuse authentication
 | USE_AWS_KMS | Flag to enable AWS Key Management Service for encryption
+| USE_PRISMA_MIGRATE | Flag to use prisma migrate instead of prisma db push. Recommended for production environments.
 | WEBHOOK_URL | URL for receiving webhooks from external services
-

docs/my-website/docs/proxy/cost_tracking.md

@@ -6,6 +6,8 @@ import Image from '@theme/IdealImage';
 
 Track spend for keys, users, and teams across 100+ LLMs.
 
+LiteLLM automatically tracks spend for all known models. See our [model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)
+
 ### How to Track Spend with LiteLLM
 
 **Step 1**
@@ -35,10 +37,10 @@ response = client.chat.completions.create(
             "content": "this is a test request, write a short poem"
         }
     ],
-    user="palantir",
+    user="palantir", # OPTIONAL: pass user to track spend by user
     extra_body={ 
         "metadata": {
-            "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"]
+            "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"] # ENTERPRISE: pass tags to track spend by tags
         }
     }
 )
@@ -63,9 +65,9 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
         "content": "what llm are you"
         }
     ],
-    "user": "palantir",
+    "user": "palantir", # OPTIONAL: pass user to track spend by user
     "metadata": {
-        "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"]
+        "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"] # ENTERPRISE: pass tags to track spend by tags
     }
 }'
 ```
@@ -90,7 +92,7 @@ chat = ChatOpenAI(
     user="palantir",
     extra_body={
         "metadata": {
-            "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"]
+            "tags": ["jobID:214590dsff09fds", "taskName:run_page_classification"] # ENTERPRISE: pass tags to track spend by tags
         }
     }
 )
@@ -150,8 +152,112 @@ Navigate to the Usage Tab on the LiteLLM UI (found on https://your-proxy-endpoin
 </TabItem>
 </Tabs>
 
-## ✨ (Enterprise) API Endpoints to get Spend
-### Getting Spend Reports - To Charge Other Teams, Customers, Users
+### Allowing Non-Proxy Admins to access `/spend` endpoints 
+
+Use this when you want non-proxy admins to access `/spend` endpoints
+
+:::info
+
+Schedule a [meeting with us to get your Enterprise License](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)
+
+:::
+
+##### Create Key 
+Create Key with with `permissions={"get_spend_routes": true}` 
+```shell
+curl --location 'http://0.0.0.0:4000/key/generate' \
+        --header 'Authorization: Bearer sk-1234' \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "permissions": {"get_spend_routes": true}
+    }'
+```
+
+##### Use generated key on `/spend` endpoints
+
+Access spend Routes with newly generate keys
+```shell
+curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end_date=2024-06-30' \
+  -H 'Authorization: Bearer sk-H16BKvrSNConSsBYLGc_7A'
+```
+
+
+
+#### Reset Team, API Key Spend - MASTER KEY ONLY
+
+Use `/global/spend/reset` if you want to:
+- Reset the Spend for all API Keys, Teams. The `spend` for ALL Teams and Keys in `LiteLLM_TeamTable` and `LiteLLM_VerificationToken` will be set to `spend=0`
+
+- LiteLLM will maintain all the logs in `LiteLLMSpendLogs` for Auditing Purposes
+
+##### Request 
+Only the `LITELLM_MASTER_KEY` you set can access this route
+```shell
+curl -X POST \
+  'http://localhost:4000/global/spend/reset' \
+  -H 'Authorization: Bearer sk-1234' \
+  -H 'Content-Type: application/json'
+```
+
+##### Expected Responses
+
+```shell
+{"message":"Spend for all API Keys and Teams reset successfully","status":"success"}
+```
+
+## Daily Spend Breakdown API
+
+Retrieve granular daily usage data for a user (by model, provider, and API key) with a single endpoint.
+
+Example Request:
+
+```shell title="Daily Spend Breakdown API" showLineNumbers
+curl -L -X GET 'http://localhost:4000/user/daily/activity?start_date=2025-03-20&end_date=2025-03-27' \
+-H 'Authorization: Bearer sk-...'
+```
+
+```json title="Daily Spend Breakdown API Response" showLineNumbers
+{
+    "results": [
+        {
+            "date": "2025-03-27",
+            "metrics": {
+                "spend": 0.0177072,
+                "prompt_tokens": 111,
+                "completion_tokens": 1711,
+                "total_tokens": 1822,
+                "api_requests": 11
+            },
+            "breakdown": {
+                "models": {
+                    "gpt-4o-mini": {
+                        "spend": 1.095e-05,
+                        "prompt_tokens": 37,
+                        "completion_tokens": 9,
+                        "total_tokens": 46,
+                        "api_requests": 1
+                },
+                "providers": { "openai": { ... }, "azure_ai": { ... } },
+                "api_keys": { "3126b6eaf1...": { ... } }
+            }
+        }
+    ],
+    "metadata": {
+        "total_spend": 0.7274667,
+        "total_prompt_tokens": 280990,
+        "total_completion_tokens": 376674,
+        "total_api_requests": 14
+    }
+}
+```
+
+### API Reference
+
+See our [Swagger API](https://litellm-api.up.railway.app/#/Budget%20%26%20Spend%20Tracking/get_user_daily_activity_user_daily_activity_get) for more details on the `/user/daily/activity` endpoint
+
+## ✨ (Enterprise) Generate Spend Reports 
+
+Use this to charge other teams, customers, users
 
 Use the `/global/spend/report` endpoint to get spend reports
 
@@ -470,105 +576,6 @@ curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end
 
 </Tabs>
 
-### Allowing Non-Proxy Admins to access `/spend` endpoints 
-
-Use this when you want non-proxy admins to access `/spend` endpoints
-
-:::info
-
-Schedule a [meeting with us to get your Enterprise License](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)
-
-:::
-
-##### Create Key 
-Create Key with with `permissions={"get_spend_routes": true}` 
-```shell
-curl --location 'http://0.0.0.0:4000/key/generate' \
-        --header 'Authorization: Bearer sk-1234' \
-        --header 'Content-Type: application/json' \
-        --data '{
-            "permissions": {"get_spend_routes": true}
-    }'
-```
-
-##### Use generated key on `/spend` endpoints
-
-Access spend Routes with newly generate keys
-```shell
-curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end_date=2024-06-30' \
-  -H 'Authorization: Bearer sk-H16BKvrSNConSsBYLGc_7A'
-```
-
-
-
-#### Reset Team, API Key Spend - MASTER KEY ONLY
-
-Use `/global/spend/reset` if you want to:
-- Reset the Spend for all API Keys, Teams. The `spend` for ALL Teams and Keys in `LiteLLM_TeamTable` and `LiteLLM_VerificationToken` will be set to `spend=0`
-
-- LiteLLM will maintain all the logs in `LiteLLMSpendLogs` for Auditing Purposes
-
-##### Request 
-Only the `LITELLM_MASTER_KEY` you set can access this route
-```shell
-curl -X POST \
-  'http://localhost:4000/global/spend/reset' \
-  -H 'Authorization: Bearer sk-1234' \
-  -H 'Content-Type: application/json'
-```
-
-##### Expected Responses
-
-```shell
-{"message":"Spend for all API Keys and Teams reset successfully","status":"success"}
-```
-
-
-
-
-## Spend Tracking for Azure OpenAI Models
-
-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
-```
-
-## Custom Input/Output Pricing
-
-👉 Head to [Custom Input/Output Pricing](https://docs.litellm.ai/docs/proxy/custom_pricing) to setup custom pricing or your models
 
 ## ✨ Custom Spend Log metadata
 
@@ -588,3 +595,4 @@ Logging specific key,value pairs in spend logs metadata is an enterprise feature
 Tracking spend with Custom tags is an enterprise feature. [See here](./enterprise.md#tracking-spend-for-custom-tags)
 
 :::
+

docs/my-website/docs/proxy/custom_pricing.md

@@ -26,10 +26,12 @@ model_list:
   - model_name: sagemaker-completion-model
     litellm_params:
       model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
+    model_info:
       input_cost_per_second: 0.000420
   - model_name: sagemaker-embedding-model
     litellm_params:
       model: sagemaker/berri-benchmarking-gpt-j-6b-fp16
+    model_info:
       input_cost_per_second: 0.000420 
 ```
 
@@ -55,11 +57,55 @@ model_list:
       api_key: os.environ/AZURE_API_KEY
       api_base: os.environ/AZURE_API_BASE
       api_version: os.envrion/AZURE_API_VERSION
+    model_info:
       input_cost_per_token: 0.000421 # 👈 ONLY to track cost per token
       output_cost_per_token: 0.000520 # 👈 ONLY to track cost per token
 ```
 
-### Debugging 
+## Override Model Cost Map
+
+You can override [our model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) with your own custom pricing for a mapped model.
+
+Just add a `model_info` key to your model in the config, and override the desired keys.
+
+Example: Override Anthropic's model cost map for the `prod/claude-3-5-sonnet-20241022` model.
+
+```yaml
+model_list:
+  - model_name: "prod/claude-3-5-sonnet-20241022"
+    litellm_params:
+      model: "anthropic/claude-3-5-sonnet-20241022"
+      api_key: os.environ/ANTHROPIC_PROD_API_KEY
+    model_info:
+      input_cost_per_token: 0.000006
+      output_cost_per_token: 0.00003
+      cache_creation_input_token_cost: 0.0000075
+      cache_read_input_token_cost: 0.0000006
+```
+
+## Set 'base_model' for Cost Tracking (e.g. Azure deployments)
+
+**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
+```
+
+
+## Debugging 
 
 If you're custom pricing is not being used or you're seeing errors, please check the following:
 

docs/my-website/docs/proxy/custom_prompt_management.md

@@ -0,0 +1,194 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Custom Prompt Management
+
+Connect LiteLLM to your prompt management system with custom hooks.
+
+## Overview
+
+
+<Image 
+  img={require('../../img/custom_prompt_management.png')}
+  style={{width: '100%', display: 'block', margin: '2rem auto'}}
+/>
+
+
+## How it works
+
+## Quick Start
+
+### 1. Create Your Custom Prompt Manager
+
+Create a class that inherits from `CustomPromptManagement` to handle prompt retrieval and formatting:
+
+**Example Implementation**
+
+Create a new file called `custom_prompt.py` and add this code. The key method here is `get_chat_completion_prompt` you can implement custom logic to retrieve and format prompts based on the `prompt_id` and `prompt_variables`.
+
+```python
+from typing import List, Tuple, Optional
+from litellm.integrations.custom_prompt_management import CustomPromptManagement
+from litellm.types.llms.openai import AllMessageValues
+from litellm.types.utils import StandardCallbackDynamicParams
+
+class MyCustomPromptManagement(CustomPromptManagement):
+    def get_chat_completion_prompt(
+        self,
+        model: str,
+        messages: List[AllMessageValues],
+        non_default_params: dict,
+        prompt_id: str,
+        prompt_variables: Optional[dict],
+        dynamic_callback_params: StandardCallbackDynamicParams,
+    ) -> Tuple[str, List[AllMessageValues], dict]:
+        """
+        Retrieve and format prompts based on prompt_id.
+        
+        Returns:
+            - model: The model to use
+            - messages: The formatted messages
+            - non_default_params: Optional parameters like temperature
+        """
+        # Example matching the diagram: Add system message for prompt_id "1234"
+        if prompt_id == "1234":
+            # Prepend system message while preserving existing messages
+            new_messages = [
+                {"role": "system", "content": "Be a good Bot!"},
+            ] + messages
+            return model, new_messages, non_default_params
+        
+        # Default: Return original messages if no prompt_id match
+        return model, messages, non_default_params
+
+prompt_management = MyCustomPromptManagement()
+```
+
+### 2. Configure Your Prompt Manager in LiteLLM `config.yaml`
+
+```yaml
+model_list:
+  - model_name: gpt-4
+    litellm_params:
+      model: openai/gpt-4
+      api_key: os.environ/OPENAI_API_KEY
+
+litellm_settings:
+  callbacks: custom_prompt.prompt_management  # sets litellm.callbacks = [prompt_management]
+```
+
+### 3. Start LiteLLM Gateway
+
+<Tabs>
+<TabItem value="docker" label="Docker Run">
+
+Mount your `custom_logger.py` on the LiteLLM Docker container.
+
+```shell
+docker run -d \
+  -p 4000:4000 \
+  -e OPENAI_API_KEY=$OPENAI_API_KEY \
+  --name my-app \
+  -v $(pwd)/my_config.yaml:/app/config.yaml \
+  -v $(pwd)/custom_logger.py:/app/custom_logger.py \
+  my-app:latest \
+  --config /app/config.yaml \
+  --port 4000 \
+  --detailed_debug \
+```
+
+</TabItem>
+
+<TabItem value="py" label="litellm pip">
+
+```shell
+litellm --config config.yaml --detailed_debug
+```
+
+</TabItem>
+</Tabs>
+
+### 4. Test Your Custom Prompt Manager
+
+When you pass `prompt_id="1234"`, the custom prompt manager will add a system message "Be a good Bot!" to your conversation:
+
+<Tabs>
+<TabItem value="openai" label="OpenAI Python v1.0.0+">
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.chat.completions.create(
+    model="gemini-1.5-pro",
+    messages=[{"role": "user", "content": "hi"}],
+    prompt_id="1234"
+)
+
+print(response.choices[0].message.content)
+```
+</TabItem>
+
+<TabItem value="langchain" label="Langchain">
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import HumanMessage
+
+chat = ChatOpenAI(
+    model="gpt-4",
+    openai_api_key="sk-1234",
+    openai_api_base="http://0.0.0.0:4000",
+    extra_body={
+        "prompt_id": "1234"
+    }
+)
+
+messages = []
+response = chat(messages)
+
+print(response.content)
+```
+</TabItem>
+
+<TabItem value="curl" label="Curl">
+
+```shell
+curl -X POST http://0.0.0.0:4000/v1/chat/completions \
+-H "Content-Type: application/json" \
+-H "Authorization: Bearer sk-1234" \
+-d '{
+    "model": "gemini-1.5-pro",
+    "messages": [{"role": "user", "content": "hi"}],
+    "prompt_id": "1234"
+}'
+```
+</TabItem>
+</Tabs>
+
+The request will be transformed from:
+```json
+{
+    "model": "gemini-1.5-pro",
+    "messages": [{"role": "user", "content": "hi"}],
+    "prompt_id": "1234"
+}
+```
+
+To:
+```json
+{
+    "model": "gemini-1.5-pro",
+    "messages": [
+        {"role": "system", "content": "Be a good Bot!"},
+        {"role": "user", "content": "hi"}
+    ]
+}
+```
+
+

docs/my-website/docs/proxy/db_deadlocks.md

@@ -0,0 +1,86 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# High Availability Setup (Resolve DB Deadlocks)
+
+Resolve any Database Deadlocks you see in high traffic by using this setup
+
+## What causes the problem?
+
+LiteLLM writes `UPDATE` and `UPSERT` queries to the DB. When using 10+ instances of LiteLLM, these queries can cause deadlocks since each instance could simultaneously attempt to update the same `user_id`, `team_id`, `key` etc. 
+
+## How the high availability setup fixes the problem
+- All instances will write to a Redis queue instead of the DB. 
+- A single instance will acquire a lock on the DB and flush the redis queue to the DB. 
+
+
+## How it works 
+
+### Stage 1. Each instance writes updates to redis
+
+Each instance will accumlate the spend updates for a key, user, team, etc and write the updates to a redis queue. 
+
+<Image img={require('../../img/deadlock_fix_1.png')}  style={{ width: '900px', height: 'auto' }} />
+<p style={{textAlign: 'left', color: '#666'}}>
+Each instance writes updates to redis
+</p>
+
+
+### Stage 2. A single instance flushes the redis queue to the DB
+
+A single instance will acquire a lock on the DB and flush all elements in the redis queue to the DB. 
+
+- 1 instance will attempt to acquire the lock for the DB update job 
+- The status of the lock is stored in redis
+- If the instance acquires the lock to write to DB
+    - It will read all updates from redis
+    - Aggregate all updates into 1 transaction
+    - Write updates to DB
+    - Release the lock
+- Note: Only 1 instance can acquire the lock at a time, this limits the number of instances that can write to the DB at once
+
+
+<Image img={require('../../img/deadlock_fix_2.png')}  style={{ width: '900px', height: 'auto' }} />
+<p style={{textAlign: 'left', color: '#666'}}>
+A single instance flushes the redis queue to the DB
+</p>
+
+
+## Usage
+
+### Required components
+
+- Redis
+- Postgres
+
+### Setup on LiteLLM config
+
+You can enable using the redis buffer by setting `use_redis_transaction_buffer: true` in the `general_settings` section of your `proxy_config.yaml` file. 
+
+Note: This setup requires litellm to be connected to a redis instance. 
+
+```yaml showLineNumbers title="litellm proxy_config.yaml"
+general_settings:
+  use_redis_transaction_buffer: true
+
+litellm_settings:
+  cache: True
+  cache_params:
+    type: redis
+    supported_call_types: [] # Optional: Set cache for proxy, but not on the actual llm api call
+```
+
+## Monitoring
+
+LiteLLM emits the following prometheus metrics to monitor the health/status of the in memory buffer and redis buffer. 
+
+
+| Metric Name                                         | Description                                                                 | Storage Type |
+|-----------------------------------------------------|-----------------------------------------------------------------------------|--------------|
+| `litellm_pod_lock_manager_size`                     | Indicates which pod has the lock to write updates to the database.         | Redis    |
+| `litellm_in_memory_daily_spend_update_queue_size`   | Number of items in the in-memory daily spend update queue. These are the aggregate spend logs for each user.                 | In-Memory    |
+| `litellm_redis_daily_spend_update_queue_size`       | Number of items in the Redis daily spend update queue.  These are the aggregate spend logs for each user.                    | Redis        |
+| `litellm_in_memory_spend_update_queue_size`         | In-memory aggregate spend values for keys, users, teams, team members, etc.| In-Memory    |
+| `litellm_redis_spend_update_queue_size`             | Redis aggregate spend values for keys, users, teams, etc.                  | Redis        |
+

docs/my-website/docs/proxy/guardrails/aim_security.md

@@ -23,6 +23,12 @@ In the newly created guard's page, you can find a reference to the prompt policy
 
 You can decide which detections will be enabled, and set the threshold for each detection.
 
+:::info 
+When using LiteLLM with virtual keys, key-specific policies can be set directly in Aim's guards page by specifying the virtual key alias when creating the guard.
+
+Only the aliases of your virtual keys (and not the actual key secrets) will be sent to Aim.
+:::
+
 ### 3. Add Aim Guardrail on your LiteLLM config.yaml 
 
 Define your guardrails under the `guardrails` section
@@ -134,7 +140,7 @@ The above request should not be blocked, and you should receive a regular LLM re
 
 </Tabs>
 
-# Advanced
+## Advanced
 
 Aim Guard provides user-specific Guardrail policies, enabling you to apply tailored policies to individual users.
 To utilize this feature, include the end-user's email in the request payload by setting the `x-aim-user-email` header of your request.

docs/my-website/docs/proxy/guardrails/custom_guardrail.md

@@ -10,10 +10,12 @@ Use this is you want to write code to run a custom guardrail
 
 ### 1. Write a `CustomGuardrail` Class
 
-A CustomGuardrail has 3 methods to enforce guardrails 
+A CustomGuardrail has 4 methods to enforce guardrails 
 - `async_pre_call_hook` - (Optional) modify input or reject request before making LLM API call
 - `async_moderation_hook` - (Optional) reject request, runs while making LLM API call (help to lower latency)
 - `async_post_call_success_hook`- (Optional) apply guardrail on input/output, runs after making LLM API call
+- `async_post_call_streaming_iterator_hook` - (Optional) pass the entire stream to the guardrail
+
 
 **[See detailed spec of methods here](#customguardrail-methods)**
 
@@ -128,6 +130,23 @@ class myCustomGuardrail(CustomGuardrail):
                     ):
                         raise ValueError("Guardrail failed Coffee Detected")
 
+    async def async_post_call_streaming_iterator_hook(
+        self,
+        user_api_key_dict: UserAPIKeyAuth,
+        response: Any,
+        request_data: dict,
+    ) -> AsyncGenerator[ModelResponseStream, None]:
+        """
+        Passes the entire stream to the guardrail
+
+        This is useful for guardrails that need to see the entire response, such as PII masking.
+
+        See Aim guardrail implementation for an example - https://github.com/BerriAI/litellm/blob/d0e022cfacb8e9ebc5409bb652059b6fd97b45c0/litellm/proxy/guardrails/guardrail_hooks/aim.py#L168
+
+        Triggered by mode: 'post_call'
+        """
+        async for item in response:
+            yield item
 
 ```
 

docs/my-website/docs/proxy/guardrails/quick_start.md

@@ -17,6 +17,14 @@ model_list:
       api_key: os.environ/OPENAI_API_KEY
 
 guardrails:
+  - guardrail_name: general-guard
+    litellm_params:
+      guardrail: aim
+      mode: [pre_call, post_call]
+      api_key: os.environ/AIM_API_KEY
+      api_base: os.environ/AIM_API_BASE
+      default_on: true # Optional
+  
   - guardrail_name: "aporia-pre-guard"
     litellm_params:
       guardrail: aporia  # supported values: "aporia", "lakera"
@@ -45,6 +53,7 @@ guardrails:
 - `pre_call` Run **before** LLM call, on **input**
 - `post_call` Run **after** LLM call, on **input & output**
 - `during_call` Run **during** LLM call, on **input** Same as `pre_call` but runs in parallel as LLM call.  Response not returned until guardrail check completes
+- A list of the above values to run multiple modes, e.g. `mode: [pre_call, post_call]`
 
 
 ## 2. Start LiteLLM Gateway 

docs/my-website/docs/proxy/image_handling.md

@@ -0,0 +1,21 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Image URL Handling 
+
+<Image img={require('../../img/image_handling.png')}  style={{ width: '900px', height: 'auto' }} />
+
+Some LLM API's don't support url's for images, but do support base-64 strings. 
+
+For those, LiteLLM will:
+
+1. Detect a URL being passed
+2. Check if the LLM API supports a URL
+3. Else, will download the base64 
+4. Send the provider a base64 string. 
+
+
+LiteLLM also caches this result, in-memory to reduce latency for subsequent calls. 
+
+The limit for an in-memory cache is 1MB. 

docs/my-website/docs/proxy/litellm_managed_files.md

@@ -0,0 +1,279 @@
+import TabItem from '@theme/TabItem';
+import Tabs from '@theme/Tabs';
+import Image from '@theme/IdealImage';
+
+# [BETA] Unified File ID
+
+Reuse the same 'file id' across different providers.
+
+| Feature | Description | Comments |
+| --- | --- | --- |
+| Proxy | ✅ |  |
+| SDK | ❌ | Requires postgres DB for storing file ids |
+| Available across all providers | ✅ |  |
+
+
+
+Limitations of LiteLLM Managed Files:
+- Only works for `/chat/completions` requests. 
+- Assumes just 1 model configured per model_name.
+
+Follow [here](https://github.com/BerriAI/litellm/discussions/9632) for multiple models, batches support.
+
+### 1. Setup config.yaml
+
+```
+model_list:
+    - model_name: "gemini-2.0-flash"
+      litellm_params:
+        model: vertex_ai/gemini-2.0-flash
+        vertex_project: my-project-id
+        vertex_location: us-central1
+    - model_name: "gpt-4o-mini-openai"
+      litellm_params:
+        model: gpt-4o-mini
+        api_key: os.environ/OPENAI_API_KEY
+```
+
+### 2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+### 3. Test it!
+
+Specify `target_model_names` to use the same file id across different providers. This is the list of model_names set via config.yaml (or 'public_model_names' on UI). 
+
+```python
+target_model_names="gpt-4o-mini-openai, gemini-2.0-flash" # 👈 Specify model_names
+```
+
+Check `/v1/models` to see the list of available model names for a key.
+
+#### **Store a PDF file**
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://0.0.0.0:4000", api_key="sk-1234", max_retries=0)
+
+
+# Download and save the PDF locally 
+url = (
+    "https://storage.googleapis.com/cloud-samples-data/generative-ai/pdf/2403.05530.pdf"
+)
+response = requests.get(url)
+response.raise_for_status()
+
+# Save the PDF locally
+with open("2403.05530.pdf", "wb") as f:
+    f.write(response.content)
+
+file = client.files.create(
+    file=open("2403.05530.pdf", "rb"),
+    purpose="user_data", # can be any openai 'purpose' value
+    extra_body={"target_model_names": "gpt-4o-mini-openai, gemini-2.0-flash"}, # 👈 Specify model_names
+)
+
+print(f"file id={file.id}")
+```
+
+#### **Use the same file id across different providers**
+
+<Tabs>
+<TabItem value="openai" label="OpenAI">
+
+```python
+completion = client.chat.completions.create(
+    model="gpt-4o-mini-openai",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this recording?"},
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                    },
+                },
+            ],
+        },
+    ]
+)
+
+print(completion.choices[0].message)
+```
+
+
+</TabItem>
+<TabItem value="vertex" label="Vertex AI">
+
+```python
+completion = client.chat.completions.create(
+    model="gemini-2.0-flash",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this recording?"},
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                    },
+                },
+            ],
+        },
+    ]
+)
+
+print(completion.choices[0].message)
+
+```
+
+</TabItem>
+</Tabs>
+
+### Complete Example
+
+```python   
+import base64
+import requests
+from openai import OpenAI
+
+client = OpenAI(base_url="http://0.0.0.0:4000", api_key="sk-1234", max_retries=0)
+
+
+# Download and save the PDF locally
+url = (
+    "https://storage.googleapis.com/cloud-samples-data/generative-ai/pdf/2403.05530.pdf"
+)
+response = requests.get(url)
+response.raise_for_status()
+
+# Save the PDF locally
+with open("2403.05530.pdf", "wb") as f:
+    f.write(response.content)
+
+# Read the local PDF file
+file = client.files.create(
+    file=open("2403.05530.pdf", "rb"),
+    purpose="user_data", # can be any openai 'purpose' value
+    extra_body={"target_model_names": "gpt-4o-mini-openai, vertex_ai/gemini-2.0-flash"},
+)
+
+print(f"file.id: {file.id}") # 👈 Unified file id
+
+## GEMINI CALL ### 
+completion = client.chat.completions.create(
+    model="gemini-2.0-flash",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this recording?"},
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                    },
+                },
+            ],
+        },
+    ]
+)
+
+print(completion.choices[0].message)
+
+
+### OPENAI CALL ### 
+completion = client.chat.completions.create(
+    model="gpt-4o-mini-openai",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this recording?"},
+                {
+                    "type": "file",
+                    "file": {
+                        "file_id": file.id,
+                    },
+                },
+            ],
+        },
+    ],
+)
+
+print(completion.choices[0].message)
+
+```
+
+
+### Supported Endpoints
+
+#### Create a file - `/files`
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://0.0.0.0:4000", api_key="sk-1234", max_retries=0)
+
+# Download and save the PDF locally
+url = (
+    "https://storage.googleapis.com/cloud-samples-data/generative-ai/pdf/2403.05530.pdf"
+)
+response = requests.get(url)
+response.raise_for_status()
+
+# Save the PDF locally
+with open("2403.05530.pdf", "wb") as f:
+    f.write(response.content)
+
+# Read the local PDF file
+file = client.files.create(
+    file=open("2403.05530.pdf", "rb"),
+    purpose="user_data", # can be any openai 'purpose' value
+    extra_body={"target_model_names": "gpt-4o-mini-openai, vertex_ai/gemini-2.0-flash"},
+)
+```
+
+#### Retrieve a file - `/files/{file_id}`
+
+```python
+client = OpenAI(base_url="http://0.0.0.0:4000", api_key="sk-1234", max_retries=0)
+
+file = client.files.retrieve(file_id=file.id)
+```
+
+#### Delete a file - `/files/{file_id}/delete`
+
+```python
+client = OpenAI(base_url="http://0.0.0.0:4000", api_key="sk-1234", max_retries=0)
+
+file = client.files.delete(file_id=file.id)
+```
+
+### FAQ
+
+**1. Does LiteLLM store the file?**
+
+No, LiteLLM does not store the file. It only stores the file id's in the postgres DB.
+
+**2. How does LiteLLM know which file to use for a given file id?**
+
+LiteLLM stores a mapping of the litellm file id to the model-specific file id in the postgres DB. When a request comes in, LiteLLM looks up the model-specific file id and uses it in the request to the provider.
+
+**3. How do file deletions work?**
+
+When a file is deleted, LiteLLM deletes the mapping from the postgres DB, and the files on each provider.
+
+### Architecture
+
+
+
+
+
+<Image img={require('../../img/managed_files_arch.png')}  style={{ width: '800px', height: 'auto' }} />

docs/my-website/docs/proxy/logging.md

@@ -862,7 +862,7 @@ Add the following to your env
 
 ```shell
 OTEL_EXPORTER="otlp_http"
-OTEL_ENDPOINT="http:/0.0.0.0:4317"
+OTEL_ENDPOINT="http://0.0.0.0:4317"
 OTEL_HEADERS="x-honeycomb-team=<your-api-key>" # Optional
 ```
 

docs/my-website/docs/proxy/logging_spec.md

@@ -79,6 +79,7 @@ Inherits from `StandardLoggingUserAPIKeyMetadata` and adds:
 | `response_cost` | `Optional[str]` | Optional response cost |
 | `additional_headers` | `Optional[StandardLoggingAdditionalHeaders]` | Additional headers |
 | `batch_models` | `Optional[List[str]]` | Only set for Batches API. Lists the models used for cost calculation |
+| `litellm_model_name` | `Optional[str]` | Model name sent in request |
 
 ## StandardLoggingModelInformation
 

docs/my-website/docs/proxy/model_discovery.md

@@ -0,0 +1,108 @@
+# Model Discovery
+
+Use this to give users an accurate list of models available behind provider endpoint, when calling `/v1/models` for wildcard models.
+
+## Supported Models
+
+- Fireworks AI
+- OpenAI
+- Gemini
+- LiteLLM Proxy
+- Topaz
+- Anthropic
+- XAI
+- VLLM
+- Vertex AI
+
+### Usage
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+    - model_name: xai/*
+      litellm_params:
+        model: xai/*
+        api_key: os.environ/XAI_API_KEY
+
+litellm_settings:
+    check_provider_endpoint: true # 👈 Enable checking provider endpoint for wildcard models
+```
+
+**2. Start proxy**
+
+```bash
+litellm --config /path/to/config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+**3. Call `/v1/models`**
+
+```bash
+curl -X GET "http://localhost:4000/v1/models" -H "Authorization: Bearer $LITELLM_KEY"
+```
+
+Expected response
+
+```json
+{
+    "data": [
+        {
+            "id": "xai/grok-2-1212",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-2-vision-1212",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-3-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-3-fast-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-3-mini-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-3-mini-fast-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-vision-beta",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        },
+        {
+            "id": "xai/grok-2-image-1212",
+            "object": "model",
+            "created": 1677610602,
+            "owned_by": "openai"
+        }
+    ],
+    "object": "list"
+}
+```

docs/my-website/docs/proxy/prod.md

@@ -94,15 +94,31 @@ This disables the load_dotenv() functionality, which will automatically load you
 
 ## 5. If running LiteLLM on VPC, gracefully handle DB unavailability
 
-This will allow LiteLLM to continue to process requests even if the DB is unavailable. This is better handling for DB unavailability.
+When running LiteLLM on a VPC (and inaccessible from the public internet), you can enable graceful degradation so that request processing continues even if the database is temporarily unavailable.
+
 
 **WARNING: Only do this if you're running LiteLLM on VPC, that cannot be accessed from the public internet.**
 
-```yaml
+#### Configuration
+
+```yaml showLineNumbers title="litellm config.yaml"
 general_settings:
   allow_requests_on_db_unavailable: True
 ```
 
+#### Expected Behavior
+
+When `allow_requests_on_db_unavailable` is set to `true`, LiteLLM will handle errors as follows:
+
+| Type of Error | Expected Behavior | Details |
+|---------------|-------------------|----------------|
+| Prisma Errors | ✅ Request will be allowed | Covers issues like DB connection resets or rejections from the DB via Prisma, the ORM used by LiteLLM. |
+| Httpx Errors | ✅ Request will be allowed | Occurs when the database is unreachable, allowing the request to proceed despite the DB outage. |
+| Pod Startup Behavior | ✅ Pods start regardless | LiteLLM Pods will start even if the database is down or unreachable, ensuring higher uptime guarantees for deployments. |
+| Health/Readiness Check | ✅ Always returns 200 OK | The /health/readiness endpoint returns a 200 OK status to ensure that pods remain operational even when the database is unavailable.
+| LiteLLM Budget Errors or Model Errors | ❌ Request will be blocked | Triggered when the DB is reachable but the authentication token is invalid, lacks access, or exceeds budget limits. |
+
+
 ## 6. Disable spend_logs & error_logs if not using the LiteLLM UI
 
 By default, LiteLLM writes several types of logs to the database:
@@ -161,6 +177,50 @@ export LITELLM_SALT_KEY="sk-1234"
 
 [**See Code**](https://github.com/BerriAI/litellm/blob/036a6821d588bd36d170713dcf5a72791a694178/litellm/proxy/common_utils/encrypt_decrypt_utils.py#L15)
 
+
+## 9. Use `prisma migrate deploy`
+
+Use this to handle db migrations across LiteLLM versions in production
+
+<Tabs>
+<TabItem value="env" label="ENV">
+
+```bash
+USE_PRISMA_MIGRATE="True"
+```
+
+</TabItem>
+
+<TabItem value="cli" label="CLI">
+
+```bash
+litellm --use_prisma_migrate
+```
+
+</TabItem>
+</Tabs>
+
+Benefits:
+
+The migrate deploy command:
+
+- **Does not** issue a warning if an already applied migration is missing from migration history
+- **Does not** detect drift (production database schema differs from migration history end state - for example, due to a hotfix)
+- **Does not** reset the database or generate artifacts (such as Prisma Client)
+- **Does not** rely on a shadow database
+
+
+### How does LiteLLM handle DB migrations in production?
+
+1. A new migration file is written to our `litellm-proxy-extras` package. [See all](https://github.com/BerriAI/litellm/tree/main/litellm-proxy-extras/litellm_proxy_extras/migrations)
+
+2. The core litellm pip package is bumped to point to the new `litellm-proxy-extras` package. This ensures, older versions of LiteLLM will continue to use the old migrations. [See code](https://github.com/BerriAI/litellm/blob/52b35cd8093b9ad833987b24f494586a1e923209/pyproject.toml#L58)
+
+3. When you upgrade to a new version of LiteLLM, the migration file is applied to the database. [See code](https://github.com/BerriAI/litellm/blob/52b35cd8093b9ad833987b24f494586a1e923209/litellm-proxy-extras/litellm_proxy_extras/utils.py#L42)
+
+
+
+
 ## Extras
 ### Expected Performance in Production
 
@@ -183,93 +243,3 @@ You should only see the following level of details in logs on the proxy server
 # INFO:     192.168.2.205:34717 - "POST /chat/completions HTTP/1.1" 200 OK
 # INFO:     192.168.2.205:29734 - "POST /chat/completions HTTP/1.1" 200 OK
 ```
-
-
-### Machine Specifications to Deploy LiteLLM
-
-| Service | Spec | CPUs | Memory | Architecture | Version|
-| --- | --- | --- | --- | --- | --- | 
-| Server | `t2.small`. | `1vCPUs` | `8GB` | `x86` |
-| Redis Cache | - | - | - | - | 7.0+ Redis Engine|
-
-
-### Reference Kubernetes Deployment YAML
-
-Reference Kubernetes `deployment.yaml` that was load tested by us
-
-```yaml
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: litellm-deployment
-spec:
-  replicas: 3
-  selector:
-    matchLabels:
-      app: litellm
-  template:
-    metadata:
-      labels:
-        app: litellm
-    spec:
-      containers:
-        - name: litellm-container
-          image: ghcr.io/berriai/litellm:main-latest
-          imagePullPolicy: Always
-          env:
-            - name: AZURE_API_KEY
-              value: "d6******"
-            - name: AZURE_API_BASE
-              value: "https://ope******"
-            - name: LITELLM_MASTER_KEY
-              value: "sk-1234"
-            - name: DATABASE_URL
-              value: "po**********"
-          args:
-            - "--config"
-            - "/app/proxy_config.yaml"  # Update the path to mount the config file
-          volumeMounts:                 # Define volume mount for proxy_config.yaml
-            - name: config-volume
-              mountPath: /app
-              readOnly: true
-          livenessProbe:
-            httpGet:
-              path: /health/liveliness
-              port: 4000
-            initialDelaySeconds: 120
-            periodSeconds: 15
-            successThreshold: 1
-            failureThreshold: 3
-            timeoutSeconds: 10
-          readinessProbe:
-            httpGet:
-              path: /health/readiness
-              port: 4000
-            initialDelaySeconds: 120
-            periodSeconds: 15
-            successThreshold: 1
-            failureThreshold: 3
-            timeoutSeconds: 10
-      volumes:  # Define volume to mount proxy_config.yaml
-        - name: config-volume
-          configMap:
-            name: litellm-config  
-
-```
-
-
-Reference Kubernetes `service.yaml` that was load tested by us
-```yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: litellm-service
-spec:
-  selector:
-    app: litellm
-  ports:
-    - protocol: TCP
-      port: 4000
-      targetPort: 4000
-  type: LoadBalancer
-```

docs/my-website/docs/proxy/prometheus.md

@@ -95,7 +95,14 @@ Use this for for tracking per [user, key, team, etc.](virtual_keys)
 
 ### Initialize Budget Metrics on Startup
 
-If you want to initialize the key/team budget metrics on startup, you can set the `prometheus_initialize_budget_metrics` to `true` in the `config.yaml`
+If you want litellm to emit the budget metrics for all keys, teams irrespective of whether they are getting requests or not, set `prometheus_initialize_budget_metrics` to `true` in the `config.yaml`
+
+**How this works:**
+
+- If the `prometheus_initialize_budget_metrics` is set to `true`
+  - Every 5 minutes litellm runs a cron job to read all keys, teams from the database
+  - It then emits the budget metrics for each key, team
+  - This is used to populate the budget metrics on the `/metrics` endpoint
 
 ```yaml
 litellm_settings:
@@ -242,6 +249,19 @@ litellm_settings:
 | `litellm_redis_fails`         | Number of failed redis calls    |
 | `litellm_self_latency`         | Histogram latency for successful litellm api call    |
 
+#### DB Transaction Queue Health Metrics
+
+Use these metrics to monitor the health of the DB Transaction Queue. Eg. Monitoring the size of the in-memory and redis buffers. 
+
+| Metric Name                                         | Description                                                                 | Storage Type |
+|-----------------------------------------------------|-----------------------------------------------------------------------------|--------------|
+| `litellm_pod_lock_manager_size`                     | Indicates which pod has the lock to write updates to the database.         | Redis    |
+| `litellm_in_memory_daily_spend_update_queue_size`   | Number of items in the in-memory daily spend update queue. These are the aggregate spend logs for each user.                 | In-Memory    |
+| `litellm_redis_daily_spend_update_queue_size`       | Number of items in the Redis daily spend update queue.  These are the aggregate spend logs for each user.                    | Redis        |
+| `litellm_in_memory_spend_update_queue_size`         | In-memory aggregate spend values for keys, users, teams, team members, etc.| In-Memory    |
+| `litellm_redis_spend_update_queue_size`             | Redis aggregate spend values for keys, users, teams, etc.                  | Redis        |
+
+
 
 ## **🔥 LiteLLM Maintained Grafana Dashboards **
 
@@ -268,6 +288,17 @@ Here is a screenshot of the metrics you can monitor with the LiteLLM Grafana Das
 
 
 
+## Add authentication on /metrics endpoint
+
+**By default /metrics endpoint is unauthenticated.** 
+
+You can opt into running litellm authentication on the /metrics endpoint by setting the following on the config 
+
+```yaml
+litellm_settings:
+  require_auth_for_metrics_endpoint: true
+```
+
 ## FAQ 
 
 ### What are `_created` vs. `_total` metrics?

docs/my-website/docs/proxy/prompt_management.md

@@ -2,7 +2,7 @@ import Image from '@theme/IdealImage';
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# [BETA] Prompt Management
+# Prompt Management
 
 :::info
 
@@ -12,9 +12,10 @@ This feature is currently in beta, and might change unexpectedly. We expect this
 
 Run experiments or change the specific model (e.g. from gpt-4o to gpt4o-mini finetune) from your prompt management tool (e.g. Langfuse) instead of making changes in the application. 
 
-Supported Integrations:
-- [Langfuse](https://langfuse.com/docs/prompts/get-started)
-- [Humanloop](../observability/humanloop)
+| Supported Integrations | Link |
+|------------------------|------|
+| Langfuse               | [Get Started](https://langfuse.com/docs/prompts/get-started) |
+| Humanloop              | [Get Started](../observability/humanloop) |
 
 ## Quick Start
 

docs/my-website/docs/proxy/release_cycle.md

@@ -4,9 +4,17 @@ Litellm Proxy has the following release cycle:
 
 - `v1.x.x-nightly`: These are releases which pass ci/cd. 
 - `v1.x.x.rc`: These are releases which pass ci/cd + [manual review](https://github.com/BerriAI/litellm/discussions/8495#discussioncomment-12180711).
-- `v1.x.x` OR `v1.x.x-stable`: These are releases which pass ci/cd + manual review + 3 days of production testing.
+- `v1.x.x:main-stable`: These are releases which pass ci/cd + manual review + 3 days of production testing.
 
-In production, we recommend using the latest `v1.x.x` release.
+In production, we recommend using the latest `v1.x.x:main-stable` release.
 
 
 Follow our release notes [here](https://github.com/BerriAI/litellm/releases).
+
+
+## FAQ
+
+### Is there a release schedule for LiteLLM stable release?
+
+Stable releases come out every week (typically Sunday)
+

docs/my-website/docs/proxy/response_headers.md

@@ -43,19 +43,19 @@ These headers are useful for clients to understand the current rate limit status
 | `x-litellm-max-fallbacks` | int | Maximum number of fallback attempts allowed |
 
 ## Cost Tracking Headers
-| Header | Type | Description |
-|--------|------|-------------|
-| `x-litellm-response-cost` | float | Cost of the API call |
-| `x-litellm-key-spend` | float | Total spend for the API key |
+| Header | Type | Description | Available on Pass-Through Endpoints |
+|--------|------|-------------|-------------|
+| `x-litellm-response-cost` | float | Cost of the API call | |
+| `x-litellm-key-spend` | float | Total spend for the API key | ✅ |
 
 ## LiteLLM Specific Headers
-| Header | Type | Description |
-|--------|------|-------------|
-| `x-litellm-call-id` | string | Unique identifier for the API call |
-| `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 |
+| Header | Type | Description | Available on Pass-Through Endpoints |
+|--------|------|-------------|-------------|
+| `x-litellm-call-id` | string | Unique identifier for the API call | ✅ |
+| `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 | |
 
 ## Response headers from LLM providers
 

docs/my-website/docs/proxy/self_serve.md

@@ -161,6 +161,83 @@ Here's the available UI roles for a LiteLLM Internal User:
   - `internal_user`: can login, view/create/delete their own keys, view their spend. **Cannot** add new users.
   - `internal_user_viewer`: can login, view their own keys, view their own spend. **Cannot** create/delete keys, add new users.
 
+## Auto-add SSO users to teams
+
+This walks through setting up sso auto-add for **Okta, Google SSO**
+
+### Okta, Google SSO 
+
+1. Specify the JWT field that contains the team ids, that the user belongs to. 
+
+```yaml
+general_settings:
+  master_key: sk-1234
+  litellm_jwtauth:
+    team_ids_jwt_field: "groups" # 👈 CAN BE ANY FIELD
+```
+
+This is assuming your SSO token looks like this. **If you need to inspect the JWT fields received from your SSO provider by LiteLLM, follow these instructions [here](#debugging-sso-jwt-fields)**
+
+```
+{
+  ...,
+  "groups": ["team_id_1", "team_id_2"]
+}
+```
+
+2. Create the teams on LiteLLM 
+
+```bash
+curl -X POST '<PROXY_BASE_URL>/team/new' \
+-H 'Authorization: Bearer <PROXY_MASTER_KEY>' \
+-H 'Content-Type: application/json' \
+-D '{
+    "team_alias": "team_1",
+    "team_id": "team_id_1" # 👈 MUST BE THE SAME AS THE SSO GROUP ID
+}'
+```
+
+3. Test the SSO flow
+
+Here's a walkthrough of [how it works](https://www.loom.com/share/8959be458edf41fd85937452c29a33f3?sid=7ebd6d37-569a-4023-866e-e0cde67cb23e)
+
+### Microsoft Entra ID SSO group assignment
+
+Follow this [tutorial for auto-adding sso users to teams with Microsoft Entra ID](https://docs.litellm.ai/docs/tutorials/msft_sso)
+
+### Debugging SSO JWT fields 
+
+If you need to inspect the JWT fields received from your SSO provider by LiteLLM, follow these instructions. This guide walks you through setting up a debug callback to view the JWT data during the SSO process.
+
+
+<Image img={require('../../img/debug_sso.png')}  style={{ width: '500px', height: 'auto' }} />
+<br />
+
+1. Add `/sso/debug/callback` as a redirect URL in your SSO provider 
+
+  In your SSO provider's settings, add the following URL as a new redirect (callback) URL:
+
+  ```bash showLineNumbers title="Redirect URL"
+  http://<proxy_base_url>/sso/debug/callback
+  ```
+
+
+2. Navigate to the debug login page on your browser 
+
+    Navigate to the following URL on your browser:
+
+    ```bash showLineNumbers title="URL to navigate to"
+    https://<proxy_base_url>/sso/debug/login
+    ```
+
+    This will initiate the standard SSO flow. You will be redirected to your SSO provider's login screen, and after successful authentication, you will be redirected back to LiteLLM's debug callback route.
+
+
+3. View the JWT fields 
+
+Once redirected, you should see a page called "SSO Debug Information". This page displays the JWT fields received from your SSO provider (as shown in the image above)
+
+
 ## Advanced
 ### Setting custom logout URLs
 
@@ -196,40 +273,26 @@ This budget does not apply to keys created under non-default teams.
 
 [**Go Here**](./team_budgets.md)
 
-### Auto-add SSO users to teams
+### Set default params for new teams
 
-1. Specify the JWT field that contains the team ids, that the user belongs to. 
+When you connect litellm to your SSO provider, litellm can auto-create teams. Use this to set the default `models`, `max_budget`, `budget_duration` for these auto-created teams. 
 
-```yaml
-general_settings:
-  master_key: sk-1234
-  litellm_jwtauth:
-    team_ids_jwt_field: "groups" # 👈 CAN BE ANY FIELD
+**How it works**
+
+1. When litellm fetches `groups` from your SSO provider, it will check if the corresponding group_id exists as a `team_id` in litellm. 
+2. If the team_id does not exist, litellm will auto-create a team with the default params you've set. 
+3. If the team_id already exist, litellm will not apply any settings on the team. 
+
+**Usage**
+
+```yaml showLineNumbers title="Default Params for new teams"
+litellm_settings:
+  default_team_params:             # Default Params to apply when litellm auto creates a team from SSO IDP provider
+    max_budget: 100                # Optional[float], optional): $100 budget for the team
+    budget_duration: 30d           # Optional[str], optional): 30 days budget_duration for the team
+    models: ["gpt-3.5-turbo"]      # Optional[List[str]], optional): models to be used by the team
 ```
 
-This is assuming your SSO token looks like this:
-```
-{
-  ...,
-  "groups": ["team_id_1", "team_id_2"]
-}
-```
-
-2. Create the teams on LiteLLM 
-
-```bash
-curl -X POST '<PROXY_BASE_URL>/team/new' \
--H 'Authorization: Bearer <PROXY_MASTER_KEY>' \
--H 'Content-Type: application/json' \
--D '{
-    "team_alias": "team_1",
-    "team_id": "team_id_1" # 👈 MUST BE THE SAME AS THE SSO GROUP ID
-}'
-```
-
-3. Test the SSO flow
-
-Here's a walkthrough of [how it works](https://www.loom.com/share/8959be458edf41fd85937452c29a33f3?sid=7ebd6d37-569a-4023-866e-e0cde67cb23e)
 
 ### Restrict Users from creating personal keys 
 
@@ -241,7 +304,7 @@ This will also prevent users from using their session tokens on the test keys ch
 
 ## **All Settings for Self Serve / SSO Flow**
 
-```yaml
+```yaml showLineNumbers title="All Settings for Self Serve / SSO Flow"
 litellm_settings:
   max_internal_user_budget: 10        # max budget for internal users
   internal_user_budget_duration: "1mo" # reset every month
@@ -252,6 +315,11 @@ litellm_settings:
     budget_duration: 30d           # Optional[str], optional): 30 days budget_duration for a new SSO sign in user
     models: ["gpt-3.5-turbo"]      # Optional[List[str]], optional): models to be used by a new SSO sign in user
   
+  default_team_params:             # Default Params to apply when litellm auto creates a team from SSO IDP provider
+    max_budget: 100                # Optional[float], optional): $100 budget for the team
+    budget_duration: 30d           # Optional[str], optional): 30 days budget_duration for the team
+    models: ["gpt-3.5-turbo"]      # Optional[List[str]], optional): models to be used by the team
+
 
   upperbound_key_generate_params:    # Upperbound for /key/generate requests when self-serve flow is on
     max_budget: 100 # Optional[float], optional): upperbound of $100, for all /key/generate requests

docs/my-website/docs/reasoning_content.md

@@ -15,14 +15,17 @@ Supported Providers:
 - Bedrock (Anthropic + Deepseek) (`bedrock/`)
 - Vertex AI (Anthropic) (`vertexai/`)
 - OpenRouter (`openrouter/`)
+- XAI (`xai/`)
+- Google AI Studio (`google/`)
+- Vertex AI (`vertex_ai/`)
 
 LiteLLM will standardize the `reasoning_content` in the response and `thinking_blocks` in the assistant message.
 
-```python
+```python title="Example response from litellm"
 "message": {
     ...
     "reasoning_content": "The capital of France is Paris.",
-    "thinking_blocks": [
+    "thinking_blocks": [ # only returned for Anthropic models
         {
             "type": "thinking",
             "thinking": "The capital of France is Paris.",
@@ -37,7 +40,7 @@ LiteLLM will standardize the `reasoning_content` in the response and `thinking_b
 <Tabs>
 <TabItem value="sdk" label="SDK">
 
-```python
+```python showLineNumbers
 from litellm import completion
 import os 
 
@@ -48,7 +51,7 @@ response = completion(
   messages=[
     {"role": "user", "content": "What is the capital of France?"},
   ],
-  thinking={"type": "enabled", "budget_tokens": 1024} # 👈 REQUIRED FOR ANTHROPIC models (on `anthropic/`, `bedrock/`, `vertexai/`)
+  reasoning_effort="low", 
 )
 print(response.choices[0].message.content)
 ```
@@ -68,7 +71,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
         "content": "What is the capital of France?"
       }
     ],
-    "thinking": {"type": "enabled", "budget_tokens": 1024}
+    "reasoning_effort": "low"
 }'
 ```
 </TabItem>
@@ -111,7 +114,7 @@ Here's how to use `thinking` blocks by Anthropic with tool calling.
 <Tabs>
 <TabItem value="sdk" label="SDK">
 
-```python
+```python showLineNumbers
 litellm._turn_on_debug()
 litellm.modify_params = True
 model = "anthropic/claude-3-7-sonnet-20250219" # works across Anthropic, Bedrock, Vertex AI
@@ -150,7 +153,7 @@ response = litellm.completion(
     messages=messages,
     tools=tools,
     tool_choice="auto",  # auto is default, but we'll be explicit
-    thinking={"type": "enabled", "budget_tokens": 1024},
+    reasoning_effort="low",
 )
 print("Response\n", response)
 response_message = response.choices[0].message
@@ -198,9 +201,9 @@ if tool_calls:
         model=model,
         messages=messages,
         seed=22,
+        reasoning_effort="low",
         # tools=tools,
         drop_params=True,
-        thinking={"type": "enabled", "budget_tokens": 1024},
     )  # get a new response from the model where it can see the function response
     print("second response\n", second_response)
 ```
@@ -210,7 +213,7 @@ if tool_calls:
 
 1. Setup config.yaml
 
-```yaml
+```yaml showLineNumbers
 model_list:
   - model_name: claude-3-7-sonnet-thinking
     litellm_params:
@@ -224,7 +227,7 @@ model_list:
 
 2. Run proxy
 
-```bash
+```bash showLineNumbers
 litellm --config config.yaml
 
 # RUNNING on http://0.0.0.0:4000
@@ -332,7 +335,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
 
 Set `drop_params=True` to drop the 'thinking' blocks when swapping from Anthropic to Deepseek models. Suggest improvements to this approach [here](https://github.com/BerriAI/litellm/discussions/8927).
 
-```python
+```python showLineNumbers
 litellm.drop_params = True # 👈 EITHER GLOBALLY or per request
 
 # or per request
@@ -340,7 +343,7 @@ litellm.drop_params = True # 👈 EITHER GLOBALLY or per request
 response = litellm.completion(
   model="anthropic/claude-3-7-sonnet-20250219",
   messages=[{"role": "user", "content": "What is the capital of France?"}],
-  thinking={"type": "enabled", "budget_tokens": 1024},
+  reasoning_effort="low",
   drop_params=True,
 )
 
@@ -348,7 +351,7 @@ response = litellm.completion(
 response = litellm.completion(
   model="deepseek/deepseek-chat",
   messages=[{"role": "user", "content": "What is the capital of France?"}],
-  thinking={"type": "enabled", "budget_tokens": 1024},
+  reasoning_effort="low",
   drop_params=True,
 )
 ```
@@ -364,3 +367,123 @@ These fields can be accessed via `response.choices[0].message.reasoning_content`
   - `thinking` - str: The thinking from the model.
   - `signature` - str: The signature delta from the model.
 
+
+
+## Pass `thinking` to Anthropic models
+
+You can also pass the `thinking` parameter to Anthropic models.
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python showLineNumbers
+response = litellm.completion(
+  model="anthropic/claude-3-7-sonnet-20250219",
+  messages=[{"role": "user", "content": "What is the capital of France?"}],
+  thinking={"type": "enabled", "budget_tokens": 1024},
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```bash
+curl http://0.0.0.0:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "anthropic/claude-3-7-sonnet-20250219",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "thinking": {"type": "enabled", "budget_tokens": 1024}
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+## Checking if a model supports reasoning
+
+<Tabs>
+<TabItem label="LiteLLM Python SDK" value="Python">
+
+Use `litellm.supports_reasoning(model="")` -> returns `True` if model supports reasoning and `False` if not.
+
+```python showLineNumbers title="litellm.supports_reasoning() usage"
+import litellm 
+
+# Example models that support reasoning
+assert litellm.supports_reasoning(model="anthropic/claude-3-7-sonnet-20250219") == True
+assert litellm.supports_reasoning(model="deepseek/deepseek-chat") == True 
+
+# Example models that do not support reasoning
+assert litellm.supports_reasoning(model="openai/gpt-3.5-turbo") == False 
+```
+</TabItem>
+
+<TabItem label="LiteLLM Proxy Server" value="proxy">
+
+1. Define models that support reasoning in your `config.yaml`. You can optionally add `supports_reasoning: True` to the `model_info` if LiteLLM does not automatically detect it for your custom model.
+
+```yaml showLineNumbers title="litellm proxy config.yaml"
+model_list:
+  - model_name: claude-3-sonnet-reasoning
+    litellm_params:
+      model: anthropic/claude-3-7-sonnet-20250219
+      api_key: os.environ/ANTHROPIC_API_KEY
+  - model_name: deepseek-reasoning
+    litellm_params:
+      model: deepseek/deepseek-chat
+      api_key: os.environ/DEEPSEEK_API_KEY
+  # Example for a custom model where detection might be needed
+  - model_name: my-custom-reasoning-model 
+    litellm_params:
+      model: openai/my-custom-model # Assuming it's OpenAI compatible
+      api_base: http://localhost:8000
+      api_key: fake-key
+    model_info:
+      supports_reasoning: True # Explicitly mark as supporting reasoning
+```
+
+2. Run the proxy server:
+
+```bash showLineNumbers title="litellm --config config.yaml"
+litellm --config config.yaml
+```
+
+3. Call `/model_group/info` to check if your model supports `reasoning`
+
+```shell showLineNumbers title="curl /model_group/info"
+curl -X 'GET' \
+  'http://localhost:4000/model_group/info' \
+  -H 'accept: application/json' \
+  -H 'x-api-key: sk-1234'
+```
+
+Expected Response 
+
+```json showLineNumbers title="response from /model_group/info"
+{
+  "data": [
+    {
+      "model_group": "claude-3-sonnet-reasoning",
+      "providers": ["anthropic"],
+      "mode": "chat",
+      "supports_reasoning": true,
+    },
+    {
+      "model_group": "deepseek-reasoning",
+      "providers": ["deepseek"],
+      "supports_reasoning": true,
+    },
+    {
+      "model_group": "my-custom-reasoning-model",
+      "providers": ["openai"],
+      "supports_reasoning": true,
+    }
+  ]
+}
+````
+
+
+</TabItem>
+</Tabs>

docs/my-website/docs/response_api.md

@@ -14,22 +14,22 @@ LiteLLM provides a BETA endpoint in the spec of [OpenAI's `/responses` API](http
 | Fallbacks | ✅ | Works between supported models |
 | Loadbalancing | ✅ | Works between supported models |
 | Supported LiteLLM Versions | 1.63.8+ | |
-| Supported LLM providers | `openai` | |
+| Supported LLM providers | **All LiteLLM supported providers** | `openai`, `anthropic`, `bedrock`, `vertex_ai`, `gemini`, `azure`, `azure_ai` etc. |
 
 ## Usage
 
-## Create a model response
+### LiteLLM Python SDK
 
 <Tabs>
-<TabItem value="litellm-sdk" label="LiteLLM SDK">
+<TabItem value="openai" label="OpenAI">
 
 #### Non-streaming
-```python
+```python showLineNumbers title="OpenAI Non-streaming Response"
 import litellm
 
 # Non-streaming response
 response = litellm.responses(
-    model="gpt-4o",
+    model="openai/o1-pro",
     input="Tell me a three sentence bedtime story about a unicorn.",
     max_output_tokens=100
 )
@@ -38,12 +38,12 @@ print(response)
 ```
 
 #### Streaming
-```python
+```python showLineNumbers title="OpenAI Streaming Response"
 import litellm
 
 # Streaming response
 response = litellm.responses(
-    model="gpt-4o",
+    model="openai/o1-pro",
     input="Tell me a three sentence bedtime story about a unicorn.",
     stream=True
 )
@@ -53,58 +53,169 @@ for event in response:
 ```
 
 </TabItem>
-<TabItem value="proxy" label="OpenAI SDK with LiteLLM Proxy">
 
-First, add this to your litellm proxy config.yaml:
-```yaml
-model_list:
-  - model_name: gpt-4o
-    litellm_params:
-      model: openai/gpt-4o
-      api_key: os.environ/OPENAI_API_KEY
-```
-
-Start your LiteLLM proxy:
-```bash
-litellm --config /path/to/config.yaml
-
-# RUNNING on http://0.0.0.0:4000
-```
-
-Then use the OpenAI SDK pointed to your proxy:
+<TabItem value="anthropic" label="Anthropic">
 
 #### Non-streaming
-```python
-from openai import OpenAI
+```python showLineNumbers title="Anthropic Non-streaming Response"
+import litellm
+import os
 
-# Initialize client with your proxy URL
-client = OpenAI(
-    base_url="http://localhost:4000",  # Your proxy URL
-    api_key="your-api-key"             # Your proxy API key
-)
+# Set API key
+os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-api-key"
 
 # Non-streaming response
-response = client.responses.create(
-    model="gpt-4o",
-    input="Tell me a three sentence bedtime story about a unicorn."
+response = litellm.responses(
+    model="anthropic/claude-3-5-sonnet-20240620",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    max_output_tokens=100
 )
 
 print(response)
 ```
 
 #### Streaming
-```python
-from openai import OpenAI
+```python showLineNumbers title="Anthropic Streaming Response"
+import litellm
+import os
 
-# Initialize client with your proxy URL
-client = OpenAI(
-    base_url="http://localhost:4000",  # Your proxy URL
-    api_key="your-api-key"             # Your proxy API key
-)
+# Set API key
+os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-api-key"
 
 # Streaming response
-response = client.responses.create(
-    model="gpt-4o",
+response = litellm.responses(
+    model="anthropic/claude-3-5-sonnet-20240620",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="vertex" label="Vertex AI">
+
+#### Non-streaming
+```python showLineNumbers title="Vertex AI Non-streaming Response"
+import litellm
+import os
+
+# Set credentials - Vertex AI uses application default credentials
+# Run 'gcloud auth application-default login' to authenticate
+os.environ["VERTEXAI_PROJECT"] = "your-gcp-project-id"
+os.environ["VERTEXAI_LOCATION"] = "us-central1"
+
+# Non-streaming response
+response = litellm.responses(
+    model="vertex_ai/gemini-1.5-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    max_output_tokens=100
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="Vertex AI Streaming Response"
+import litellm
+import os
+
+# Set credentials - Vertex AI uses application default credentials
+# Run 'gcloud auth application-default login' to authenticate
+os.environ["VERTEXAI_PROJECT"] = "your-gcp-project-id"
+os.environ["VERTEXAI_LOCATION"] = "us-central1"
+
+# Streaming response
+response = litellm.responses(
+    model="vertex_ai/gemini-1.5-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="bedrock" label="AWS Bedrock">
+
+#### Non-streaming
+```python showLineNumbers title="AWS Bedrock Non-streaming Response"
+import litellm
+import os
+
+# Set AWS credentials
+os.environ["AWS_ACCESS_KEY_ID"] = "your-access-key-id"
+os.environ["AWS_SECRET_ACCESS_KEY"] = "your-secret-access-key"
+os.environ["AWS_REGION_NAME"] = "us-west-2"  # or your AWS region
+
+# Non-streaming response
+response = litellm.responses(
+    model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    max_output_tokens=100
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="AWS Bedrock Streaming Response"
+import litellm
+import os
+
+# Set AWS credentials
+os.environ["AWS_ACCESS_KEY_ID"] = "your-access-key-id"
+os.environ["AWS_SECRET_ACCESS_KEY"] = "your-secret-access-key"
+os.environ["AWS_REGION_NAME"] = "us-west-2"  # or your AWS region
+
+# Streaming response
+response = litellm.responses(
+    model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="gemini" label="Google AI Studio">
+
+#### Non-streaming
+```python showLineNumbers title="Google AI Studio Non-streaming Response"
+import litellm
+import os
+
+# Set API key for Google AI Studio
+os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"
+
+# Non-streaming response
+response = litellm.responses(
+    model="gemini/gemini-1.5-flash",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    max_output_tokens=100
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="Google AI Studio Streaming Response"
+import litellm
+import os
+
+# Set API key for Google AI Studio
+os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"
+
+# Streaming response
+response = litellm.responses(
+    model="gemini/gemini-1.5-flash",
     input="Tell me a three sentence bedtime story about a unicorn.",
     stream=True
 )
@@ -115,3 +226,408 @@ for event in response:
 
 </TabItem>
 </Tabs>
+
+### LiteLLM Proxy with OpenAI SDK
+
+First, set up and start your LiteLLM proxy server.
+
+```bash title="Start LiteLLM Proxy Server"
+litellm --config /path/to/config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+<Tabs>
+<TabItem value="openai" label="OpenAI">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="OpenAI Proxy Configuration"
+model_list:
+  - model_name: openai/o1-pro
+    litellm_params:
+      model: openai/o1-pro
+      api_key: os.environ/OPENAI_API_KEY
+```
+
+#### Non-streaming
+```python showLineNumbers title="OpenAI Proxy Non-streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="openai/o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="OpenAI Proxy Streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="openai/o1-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="anthropic" label="Anthropic">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="Anthropic Proxy Configuration"
+model_list:
+  - model_name: anthropic/claude-3-5-sonnet-20240620
+    litellm_params:
+      model: anthropic/claude-3-5-sonnet-20240620
+      api_key: os.environ/ANTHROPIC_API_KEY
+```
+
+#### Non-streaming
+```python showLineNumbers title="Anthropic Proxy Non-streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="anthropic/claude-3-5-sonnet-20240620",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="Anthropic Proxy Streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="anthropic/claude-3-5-sonnet-20240620",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="vertex" label="Vertex AI">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="Vertex AI Proxy Configuration"
+model_list:
+  - model_name: vertex_ai/gemini-1.5-pro
+    litellm_params:
+      model: vertex_ai/gemini-1.5-pro
+      vertex_project: your-gcp-project-id
+      vertex_location: us-central1
+```
+
+#### Non-streaming
+```python showLineNumbers title="Vertex AI Proxy Non-streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="vertex_ai/gemini-1.5-pro",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="Vertex AI Proxy Streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="vertex_ai/gemini-1.5-pro",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="bedrock" label="AWS Bedrock">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="AWS Bedrock Proxy Configuration"
+model_list:
+  - model_name: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
+    litellm_params:
+      model: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
+      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
+      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
+      aws_region_name: us-west-2
+```
+
+#### Non-streaming
+```python showLineNumbers title="AWS Bedrock Proxy Non-streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="AWS Bedrock Proxy Streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+
+<TabItem value="gemini" label="Google AI Studio">
+
+First, add this to your litellm proxy config.yaml:
+```yaml showLineNumbers title="Google AI Studio Proxy Configuration"
+model_list:
+  - model_name: gemini/gemini-1.5-flash
+    litellm_params:
+      model: gemini/gemini-1.5-flash
+      api_key: os.environ/GEMINI_API_KEY
+```
+
+#### Non-streaming
+```python showLineNumbers title="Google AI Studio Proxy Non-streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Non-streaming response
+response = client.responses.create(
+    model="gemini/gemini-1.5-flash",
+    input="Tell me a three sentence bedtime story about a unicorn."
+)
+
+print(response)
+```
+
+#### Streaming
+```python showLineNumbers title="Google AI Studio Proxy Streaming Response"
+from openai import OpenAI
+
+# Initialize client with your proxy URL
+client = OpenAI(
+    base_url="http://localhost:4000",  # Your proxy URL
+    api_key="your-api-key"             # Your proxy API key
+)
+
+# Streaming response
+response = client.responses.create(
+    model="gemini/gemini-1.5-flash",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+    stream=True
+)
+
+for event in response:
+    print(event)
+```
+
+</TabItem>
+</Tabs>
+
+## Supported Responses API Parameters
+
+| Provider | Supported Parameters |
+|----------|---------------------|
+| `openai` | [All Responses API parameters are supported](https://github.com/BerriAI/litellm/blob/7c3df984da8e4dff9201e4c5353fdc7a2b441831/litellm/llms/openai/responses/transformation.py#L23) |
+| `azure` | [All Responses API parameters are supported](https://github.com/BerriAI/litellm/blob/7c3df984da8e4dff9201e4c5353fdc7a2b441831/litellm/llms/openai/responses/transformation.py#L23) |
+| `anthropic` | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+| `bedrock` | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+| `gemini` | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+| `vertex_ai` | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+| `azure_ai` | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+| All other llm api providers | [See supported parameters here](https://github.com/BerriAI/litellm/blob/f39d9178868662746f159d5ef642c7f34f9bfe5f/litellm/responses/litellm_completion_transformation/transformation.py#L57) |
+
+## Load Balancing with Routing Affinity
+
+When using the Responses API with multiple deployments of the same model (e.g., multiple Azure OpenAI endpoints), LiteLLM provides routing affinity for conversations. This ensures that follow-up requests using a `previous_response_id` are routed to the same deployment that generated the original response.
+
+
+#### Example Usage
+
+<Tabs>
+<TabItem value="python-sdk" label="Python SDK">
+
+```python showLineNumbers title="Python SDK with Routing Affinity"
+import litellm
+
+# Set up router with multiple deployments of the same model
+router = litellm.Router(
+    model_list=[
+        {
+            "model_name": "azure-gpt4-turbo",
+            "litellm_params": {
+                "model": "azure/gpt-4-turbo",
+                "api_key": "your-api-key-1",
+                "api_version": "2024-06-01",
+                "api_base": "https://endpoint1.openai.azure.com",
+            },
+        },
+        {
+            "model_name": "azure-gpt4-turbo",
+            "litellm_params": {
+                "model": "azure/gpt-4-turbo",
+                "api_key": "your-api-key-2",
+                "api_version": "2024-06-01",
+                "api_base": "https://endpoint2.openai.azure.com",
+            },
+        },
+    ],
+    optional_pre_call_checks=["responses_api_deployment_check"],
+)
+
+# Initial request
+response = await router.aresponses(
+    model="azure-gpt4-turbo",
+    input="Hello, who are you?",
+    truncation="auto",
+)
+
+# Store the response ID
+response_id = response.id
+
+# Follow-up request - will be automatically routed to the same deployment
+follow_up = await router.aresponses(
+    model="azure-gpt4-turbo",
+    input="Tell me more about yourself",
+    truncation="auto",
+    previous_response_id=response_id  # This ensures routing to the same deployment
+)
+```
+
+</TabItem>
+<TabItem value="proxy-server" label="Proxy Server">
+
+#### 1. Setup routing affinity on proxy config.yaml
+
+To enable routing affinity for Responses API in your LiteLLM proxy, set `optional_pre_call_checks: ["responses_api_deployment_check"]` in your proxy config.yaml.
+
+```yaml showLineNumbers title="config.yaml with Responses API Routing Affinity"
+model_list:
+  - model_name: azure-gpt4-turbo
+    litellm_params:
+      model: azure/gpt-4-turbo
+      api_key: your-api-key-1
+      api_version: 2024-06-01
+      api_base: https://endpoint1.openai.azure.com
+  - model_name: azure-gpt4-turbo
+    litellm_params:
+      model: azure/gpt-4-turbo
+      api_key: your-api-key-2
+      api_version: 2024-06-01
+      api_base: https://endpoint2.openai.azure.com
+
+router_settings:
+  optional_pre_call_checks: ["responses_api_deployment_check"]
+```
+
+#### 2. Use the OpenAI Python SDK to make requests to LiteLLM Proxy
+
+```python showLineNumbers title="OpenAI Client with Proxy Server"
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://localhost:4000",
+    api_key="your-api-key"
+)
+
+# Initial request
+response = client.responses.create(
+    model="azure-gpt4-turbo",
+    input="Hello, who are you?"
+)
+
+response_id = response.id
+
+# Follow-up request - will be automatically routed to the same deployment
+follow_up = client.responses.create(
+    model="azure-gpt4-turbo",
+    input="Tell me more about yourself",
+    previous_response_id=response_id  # This ensures routing to the same deployment
+)
+```
+
+</TabItem>
+</Tabs>

docs/my-website/docs/set_keys.md

@@ -188,7 +188,13 @@ Currently implemented for:
 - OpenAI (if OPENAI_API_KEY is set)
 - Fireworks AI (if FIREWORKS_AI_API_KEY is set)
 - LiteLLM Proxy (if LITELLM_PROXY_API_KEY is set)
+- Gemini (if GEMINI_API_KEY is set)
+- XAI (if XAI_API_KEY is set)   
+- Anthropic (if ANTHROPIC_API_KEY is set)
 
+You can also specify a custom provider to check:
+
+**All providers**:
 ```python
 from litellm import get_valid_models
 
@@ -196,6 +202,14 @@ valid_models = get_valid_models(check_provider_endpoint=True)
 print(valid_models)
 ```
 
+**Specific provider**:
+```python
+from litellm import get_valid_models
+
+valid_models = get_valid_models(check_provider_endpoint=True, custom_llm_provider="openai")
+print(valid_models)
+```
+
 ### `validate_environment(model: str)`
 
 This helper tells you if you have all the required environment variables for a model, and if not - what's missing. 

docs/my-website/docs/tutorials/msft_sso.md

@@ -0,0 +1,162 @@
+import Image from '@theme/IdealImage';
+
+# Microsoft SSO: Sync Groups, Members with LiteLLM
+
+Sync Microsoft SSO Groups, Members with LiteLLM Teams. 
+
+<Image img={require('../../img/litellm_entra_id.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+<br />
+
+
+## Prerequisites
+
+- An Azure Entra ID account with administrative access
+- A LiteLLM Enterprise App set up in your Azure Portal
+- Access to Microsoft Entra ID (Azure AD)
+
+
+## Overview of this tutorial
+
+1. Auto-Create Entra ID Groups on LiteLLM Teams 
+2. Sync Entra ID Team Memberships
+3. Set default params for new teams and users auto-created on LiteLLM
+
+## 1. Auto-Create Entra ID Groups on LiteLLM Teams 
+
+In this step, our goal is to have LiteLLM automatically create a new team on the LiteLLM DB when there is a new Group Added to the LiteLLM Enterprise App on Azure Entra ID.
+
+### 1.1 Create a new group in Entra ID
+
+
+Navigate to [your Azure Portal](https://portal.azure.com/) > Groups > New Group. Create a new group. 
+
+<Image img={require('../../img/entra_create_team.png')}  style={{ width: '800px', height: 'auto' }} />
+
+### 1.2 Assign the group to your LiteLLM Enterprise App
+
+On your Azure Portal, navigate to `Enterprise Applications` > Select your litellm app 
+
+<Image img={require('../../img/msft_enterprise_app.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+<br />
+
+Once you've selected your litellm app, click on `Users and Groups` > `Add user/group` 
+
+<Image img={require('../../img/msft_enterprise_assign_group.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+
+Now select the group you created in step 1.1. And add it to the LiteLLM Enterprise App. At this point we have added `Production LLM Evals Group` to the LiteLLM Enterprise App. The next steps is having LiteLLM automatically create the `Production LLM Evals Group` on the LiteLLM DB when a new user signs in.
+
+<Image img={require('../../img/msft_enterprise_select_group.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+### 1.3 Sign in to LiteLLM UI via SSO
+
+Sign into the LiteLLM UI via SSO. You should be redirected to the Entra ID SSO page. This SSO sign in flow will trigger LiteLLM to fetch the latest Groups and Members from Azure Entra ID.
+
+<Image img={require('../../img/msft_sso_sign_in.png')}  style={{ width: '800px', height: 'auto' }} />
+
+### 1.4 Check the new team on LiteLLM UI
+
+On the LiteLLM UI, Navigate to `Teams`, You should see the new team `Production LLM Evals Group` auto-created on LiteLLM. 
+
+<Image img={require('../../img/msft_auto_team.png')}  style={{ width: '900px', height: 'auto' }} />
+
+#### How this works
+
+When a SSO user signs in to LiteLLM:
+- LiteLLM automatically fetches the Groups under the LiteLLM Enterprise App
+- It finds the Production LLM Evals Group assigned to the LiteLLM Enterprise App
+- LiteLLM checks if this group's ID exists in the LiteLLM Teams Table
+- Since the ID doesn't exist, LiteLLM automatically creates a new team with:
+  - Name: Production LLM Evals Group
+  - ID: Same as the Entra ID group's ID
+
+## 2. Sync Entra ID Team Memberships
+
+In this step, we will have LiteLLM automatically add a user to the `Production LLM Evals` Team on the LiteLLM DB when a new user is added to the `Production LLM Evals` Group in Entra ID.
+
+### 2.1 Navigate to the `Production LLM Evals` Group in Entra ID
+
+Navigate to the `Production LLM Evals` Group in Entra ID.
+
+<Image img={require('../../img/msft_member_1.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+### 2.2 Add a member to the group in Entra ID
+
+Select `Members` > `Add members`
+
+In this stage you should add the user you want to add to the `Production LLM Evals` Team.
+
+<Image img={require('../../img/msft_member_2.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+
+### 2.3 Sign in as the new user on LiteLLM UI
+
+Sign in as the new user on LiteLLM UI. You should be redirected to the Entra ID SSO page. This SSO sign in flow will trigger LiteLLM to fetch the latest Groups and Members from Azure Entra ID. During this step LiteLLM sync it's teams, team members with what is available from Entra ID
+
+<Image img={require('../../img/msft_sso_sign_in.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+
+### 2.4 Check the team membership on LiteLLM UI
+
+On the LiteLLM UI, Navigate to `Teams`, You should see the new team `Production LLM Evals Group`. Since your are now a member of the `Production LLM Evals Group` in Entra ID, you should see the new team `Production LLM Evals Group` on the LiteLLM UI.
+
+<Image img={require('../../img/msft_member_3.png')}  style={{ width: '900px', height: 'auto' }} />
+
+## 3. Set default params for new teams auto-created on LiteLLM
+
+Since litellm auto creates a new team on the LiteLLM DB when there is a new Group Added to the LiteLLM Enterprise App on Azure Entra ID, we can set default params for new teams created. 
+
+This allows you to set a default budget, models, etc for new teams created. 
+
+### 3.1 Set `default_team_params` on litellm 
+
+Navigate to your litellm config file and set the following params 
+
+```yaml showLineNumbers title="litellm config with default_team_params"
+litellm_settings:
+  default_team_params:             # Default Params to apply when litellm auto creates a team from SSO IDP provider
+    max_budget: 100                # Optional[float], optional): $100 budget for the team
+    budget_duration: 30d           # Optional[str], optional): 30 days budget_duration for the team
+    models: ["gpt-3.5-turbo"]      # Optional[List[str]], optional): models to be used by the team
+```
+
+### 3.2 Auto-create a new team on LiteLLM
+
+- In this step you should add a new group to the LiteLLM Enterprise App on Azure Entra ID (like we did in step 1.1). We will call this group `Default LiteLLM Prod Team` on Azure Entra ID.
+- Start litellm proxy server with your config
+- Sign into LiteLLM UI via SSO
+- Navigate to `Teams` and you should see the new team `Default LiteLLM Prod Team` auto-created on LiteLLM
+- Note LiteLLM will set the default params for this new team. 
+
+<Image img={require('../../img/msft_default_settings.png')}  style={{ width: '900px', height: 'auto' }} />
+
+
+## Video Walkthrough
+
+This walks through setting up sso auto-add for **Microsoft Entra ID**
+
+Follow along this video for a walkthrough of how to set this up with Microsoft Entra ID
+
+<iframe width="840" height="500" src="https://www.loom.com/embed/ea711323aa9a496d84a01fd7b2a12f54?sid=c53e238c-5bfd-4135-b8fb-b5b1a08632cf" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>
+
+
+
+
+
+
+
+
+
+
+
+
+

docs/my-website/docs/tutorials/openai_codex.md

@@ -0,0 +1,146 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Using LiteLLM with OpenAI Codex
+
+This guide walks you through connecting OpenAI Codex to LiteLLM. Using LiteLLM with Codex allows teams to:
+- Access 100+ LLMs through the Codex interface
+- Use powerful models like Gemini through a familiar interface
+- Track spend and usage with LiteLLM's built-in analytics
+- Control model access with virtual keys
+
+<Image img={require('../../img/litellm_codex.gif')} />
+
+## Quickstart
+
+:::info
+
+Requires LiteLLM v1.66.3.dev5 and higher
+
+:::
+
+
+Make sure to set up LiteLLM with the [LiteLLM Getting Started Guide](../proxy/docker_quick_start.md).
+
+## 1. Install OpenAI Codex
+
+Install the OpenAI Codex CLI tool globally using npm:
+
+<Tabs>
+<TabItem value="npm" label="npm">
+
+```bash showLineNumbers
+npm i -g @openai/codex
+```
+
+</TabItem>
+<TabItem value="yarn" label="yarn">
+
+```bash showLineNumbers
+yarn global add @openai/codex
+```
+
+</TabItem>
+</Tabs>
+
+## 2. Start LiteLLM Proxy
+
+<Tabs>
+<TabItem value="docker" label="Docker">
+
+```bash showLineNumbers
+docker run \
+    -v $(pwd)/litellm_config.yaml:/app/config.yaml \
+    -p 4000:4000 \
+    ghcr.io/berriai/litellm:main-latest \
+    --config /app/config.yaml
+```
+
+</TabItem>
+<TabItem value="pip" label="LiteLLM CLI">
+
+```bash showLineNumbers
+litellm --config /path/to/config.yaml
+```
+
+</TabItem>
+</Tabs>
+
+LiteLLM should now be running on [http://localhost:4000](http://localhost:4000)
+
+## 3. Configure LiteLLM for Model Routing
+
+Ensure your LiteLLM Proxy is properly configured to route to your desired models. Create a `litellm_config.yaml` file with the following content:
+
+```yaml showLineNumbers
+model_list:
+  - model_name: o3-mini
+    litellm_params:
+      model: openai/o3-mini
+      api_key: os.environ/OPENAI_API_KEY
+  - model_name: claude-3-7-sonnet-latest
+    litellm_params:
+      model: anthropic/claude-3-7-sonnet-latest
+      api_key: os.environ/ANTHROPIC_API_KEY
+  - model_name: gemini-2.0-flash
+    litellm_params:
+      model: gemini/gemini-2.0-flash
+      api_key: os.environ/GEMINI_API_KEY
+
+litellm_settings:
+  drop_params: true
+```
+
+This configuration enables routing to specific OpenAI, Anthropic, and Gemini models with explicit names.
+
+## 4. Configure Codex to Use LiteLLM Proxy
+
+Set the required environment variables to point Codex to your LiteLLM Proxy:
+
+```bash
+# Point to your LiteLLM Proxy server
+export OPENAI_BASE_URL=http://0.0.0.0:4000 
+
+# Use your LiteLLM API key (if you've set up authentication)
+export OPENAI_API_KEY="sk-1234"
+```
+
+## 5. Run Codex with Gemini
+
+With everything configured, you can now run Codex with Gemini:
+
+```bash showLineNumbers
+codex --model gemini-2.0-flash --full-auto
+```
+
+<Image img={require('../../img/litellm_codex.gif')} />
+
+The `--full-auto` flag allows Codex to automatically generate code without additional prompting.
+
+## 6. Advanced Options
+
+### Using Different Models
+
+You can use any model configured in your LiteLLM proxy:
+
+```bash
+# Use Claude models
+codex --model claude-3-7-sonnet-latest
+
+# Use Google AI Studio Gemini models
+codex --model gemini/gemini-2.0-flash
+```
+
+## Troubleshooting
+
+- If you encounter connection issues, ensure your LiteLLM Proxy is running and accessible at the specified URL
+- Verify your LiteLLM API key is valid if you're using authentication
+- Check that your model routing configuration is correct
+- For model-specific errors, ensure the model is properly configured in your LiteLLM setup
+
+## Additional Resources
+
+- [LiteLLM Docker Quick Start Guide](../proxy/docker_quick_start.md)
+- [OpenAI Codex GitHub Repository](https://github.com/openai/codex)
+- [LiteLLM Virtual Keys and Authentication](../proxy/virtual_keys.md)

docs/my-website/docs/tutorials/openweb_ui.md

@@ -98,6 +98,5 @@ On the models dropdown select `thinking-anthropic-claude-3-7-sonnet`
 
 <Image img={require('../../img/litellm_thinking_openweb.gif')} />
 
-
-
-
+## Additional Resources
+- Running LiteLLM and OpenWebUI on Windows Localhost: A Comprehensive Guide [https://www.tanyongsheng.com/note/running-litellm-and-openwebui-on-windows-localhost-a-comprehensive-guide/](https://www.tanyongsheng.com/note/running-litellm-and-openwebui-on-windows-localhost-a-comprehensive-guide/)

docs/my-website/docs/tutorials/prompt_caching.md

@@ -0,0 +1,128 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Auto-Inject Prompt Caching Checkpoints
+
+Reduce costs by up to 90% by using LiteLLM to auto-inject prompt caching checkpoints.
+
+<Image img={require('../../img/auto_prompt_caching.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+## How it works
+
+LiteLLM can automatically inject prompt caching checkpoints into your requests to LLM providers. This allows:
+
+- **Cost Reduction**: Long, static parts of your prompts can be cached to avoid repeated processing
+- **No need to modify your application code**: You can configure the auto-caching behavior in the LiteLLM UI or in the `litellm config.yaml` file.
+
+## Configuration
+
+You need to specify `cache_control_injection_points` in your model configuration. This tells LiteLLM:
+1. Where to add the caching directive (`location`)
+2. Which message to target (`role`)
+
+LiteLLM will then automatically add a `cache_control` directive to the specified messages in your requests:
+
+```json
+"cache_control": {
+    "type": "ephemeral"
+}
+```
+
+## Usage Example 
+
+In this example, we'll configure caching for system messages by adding the directive to all messages with `role: system`.
+
+<Tabs>
+<TabItem value="litellm config.yaml" label="litellm config.yaml">
+
+```yaml showLineNumbers title="litellm config.yaml"
+model_list:
+  - model_name: anthropic-auto-inject-cache-system-message
+    litellm_params:
+      model: anthropic/claude-3-5-sonnet-20240620
+      api_key: os.environ/ANTHROPIC_API_KEY
+      cache_control_injection_points:
+        - location: message
+          role: system
+```
+</TabItem>
+
+<TabItem value="UI" label="LiteLLM UI">
+
+On the LiteLLM UI, you can specify the `cache_control_injection_points` in the `Advanced Settings` tab when adding a model.
+<Image img={require('../../img/ui_auto_prompt_caching.png')}/>
+
+</TabItem>
+</Tabs>
+
+
+## Detailed Example
+
+### 1. Original Request to LiteLLM 
+
+In this example, we have a very long, static system message and a varying user message. It's efficient to cache the system message since it rarely changes.
+
+```json
+{
+    "messages": [
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are a helpful assistant. This is a set of very long instructions that you will follow. Here is a legal document that you will use to answer the user's question."
+                }
+            ]
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "What is the main topic of this legal document?"
+                }
+            ]
+        }
+    ]
+}
+```
+
+### 2. LiteLLM's Modified Request
+
+LiteLLM auto-injects the caching directive into the system message based on our configuration:
+
+```json
+{
+    "messages": [
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are a helpful assistant. This is a set of very long instructions that you will follow. Here is a legal document that you will use to answer the user's question.",
+                    "cache_control": {"type": "ephemeral"}
+                }
+            ]
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "What is the main topic of this legal document?"
+                }
+            ]
+        }
+    ]
+}
+```
+
+When the model provider processes this request, it will recognize the caching directive and only process the system message once, caching it for subsequent requests.
+
+
+    
+
+
+

docs/my-website/docs/tutorials/scim_litellm.md

@@ -0,0 +1,74 @@
+
+import Image from '@theme/IdealImage';
+
+# SCIM with LiteLLM
+
+Enables identity providers (Okta, Azure AD, OneLogin, etc.) to automate user and team (group) provisioning, updates, and deprovisioning on LiteLLM.
+
+
+This tutorial will walk you through the steps to connect your IDP to LiteLLM SCIM Endpoints.
+
+### Supported SSO Providers for SCIM
+Below is a list of supported SSO providers for connecting to LiteLLM SCIM Endpoints.
+- Microsoft Entra ID (Azure AD)
+- Okta
+- Google Workspace
+- OneLogin
+- Keycloak
+- Auth0
+
+
+## 1. Get your SCIM Tenant URL and Bearer Token
+
+On LiteLLM, navigate to the Settings > Admin Settings > SCIM. On this page you will create a SCIM Token, this allows your IDP to authenticate to litellm `/scim` endpoints.
+
+<Image img={require('../../img/scim_2.png')}  style={{ width: '800px', height: 'auto' }} />
+
+## 2. Connect your IDP to LiteLLM SCIM Endpoints
+
+On your IDP provider, navigate to your SSO application and select `Provisioning` > `New provisioning configuration`.
+
+On this page, paste in your litellm scim tenant url and bearer token.
+
+Once this is pasted in, click on `Test Connection` to ensure your IDP can authenticate to the LiteLLM SCIM endpoints.
+
+<Image img={require('../../img/scim_4.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+## 3. Test SCIM Connection
+
+### 3.1 Assign the group to your LiteLLM Enterprise App
+
+On your IDP Portal, navigate to `Enterprise Applications` > Select your litellm app 
+
+<Image img={require('../../img/msft_enterprise_app.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+<br />
+
+Once you've selected your litellm app, click on `Users and Groups` > `Add user/group` 
+
+<Image img={require('../../img/msft_enterprise_assign_group.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+
+Now select the group you created in step 1.1. And add it to the LiteLLM Enterprise App. At this point we have added `Production LLM Evals Group` to the LiteLLM Enterprise App. The next step is having LiteLLM automatically create the `Production LLM Evals Group` on the LiteLLM DB when a new user signs in.
+
+<Image img={require('../../img/msft_enterprise_select_group.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+### 3.2 Sign in to LiteLLM UI via SSO
+
+Sign into the LiteLLM UI via SSO. You should be redirected to the Entra ID SSO page. This SSO sign in flow will trigger LiteLLM to fetch the latest Groups and Members from Azure Entra ID.
+
+<Image img={require('../../img/msft_sso_sign_in.png')}  style={{ width: '800px', height: 'auto' }} />
+
+### 3.3 Check the new team on LiteLLM UI
+
+On the LiteLLM UI, Navigate to `Teams`, You should see the new team `Production LLM Evals Group` auto-created on LiteLLM. 
+
+<Image img={require('../../img/msft_auto_team.png')}  style={{ width: '900px', height: 'auto' }} />
+
+
+
+

docs/my-website/docs/tutorials/tag_management.md

@@ -0,0 +1,145 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# [Beta] Routing based on request metadata
+
+Create routing rules based on request metadata.
+
+## Setup
+
+Add the following to your litellm proxy config yaml file.
+
+```yaml showLineNumbers title="litellm proxy config.yaml"
+router_settings:
+  enable_tag_filtering: True # 👈 Key Change
+```
+
+## 1. Create a tag
+
+On the LiteLLM UI, navigate to Experimental > Tag Management > Create Tag.
+
+Create a tag called `private-data` and only select the allowed models for requests with this tag. Once created, you will see the tag in the Tag Management page.
+
+<Image img={require('../../img/tag_create.png')}  style={{ width: '800px', height: 'auto' }} />
+
+
+## 2. Test Tag Routing
+
+Now we will test the tag based routing rules.
+
+### 2.1 Invalid model
+
+This request will fail since we send `tags=private-data` but the model `gpt-4o` is not in the allowed models for the `private-data` tag.
+
+<Image img={require('../../img/tag_invalid.png')}  style={{ width: '800px', height: 'auto' }} />
+
+<br />
+
+Here is an example sending the same request using the OpenAI Python SDK.
+<Tabs>
+<TabItem value="python" label="OpenAI Python SDK">
+
+```python showLineNumbers
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000/v1/"
+)
+
+response = client.chat.completions.create(
+    model="gpt-4o",
+    messages=[
+        {"role": "user", "content": "Hello, how are you?"}
+    ],
+    extra_body={
+        "tags": "private-data"
+    }
+)
+```
+
+</TabItem>
+<TabItem value="curl" label="cURL">
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "gpt-4o",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello, how are you?"
+    }
+  ],
+  "tags": "private-data"
+}'
+```
+
+</TabItem>
+</Tabs>
+
+<br />
+
+### 2.2 Valid model
+
+This request will succeed since we send `tags=private-data` and the model `us.anthropic.claude-3-7-sonnet-20250219-v1:0` is in the allowed models for the `private-data` tag.
+
+<Image img={require('../../img/tag_valid.png')}  style={{ width: '800px', height: 'auto' }} />
+
+Here is an example sending the same request using the OpenAI Python SDK.
+
+<Tabs>
+<TabItem value="python" label="OpenAI Python SDK">
+
+```python showLineNumbers
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-1234",
+    base_url="http://0.0.0.0:4000/v1/"
+)
+
+response = client.chat.completions.create(
+    model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+    messages=[
+        {"role": "user", "content": "Hello, how are you?"}
+    ],
+    extra_body={
+        "tags": "private-data"
+    }
+)
+```
+
+</TabItem>
+<TabItem value="curl" label="cURL">
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+  "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello, how are you?"
+    }
+  ],
+  "tags": "private-data"
+}'
+```
+
+</TabItem>
+</Tabs>
+
+
+
+## Additional Tag Features
+- [Sending tags in request headers](https://docs.litellm.ai/docs/proxy/tag_routing#calling-via-request-header)
+- [Tag based routing](https://docs.litellm.ai/docs/proxy/tag_routing)
+- [Track spend per tag](cost_tracking#-custom-tags)
+- [Setup Budgets per Virtual Key, Team](users)
+