Merge branch 'main' into newrelic

.circleci/config.yml

@@ -42,7 +42,7 @@ commands:
               "pydantic==2.11.0" "mcp==1.25.0" "requests-mock>=1.12.1" \
               "responses==0.25.7" "pytest-xdist==3.6.1" "pytest-timeout==2.2.0" \
               "pytest-cov==5.0.0" "semantic_router==0.1.10" "fastapi-offline==1.7.3" \
-              "a2a"
+              "a2a" "parameterized>=0.9.0"
       - setup_litellm_enterprise_pip
       - save_cache:
           paths:
@@ -1115,7 +1115,7 @@ jobs:
             for dir in "${IGNORE_DIRS[@]}"; do
               IGNORE_ARGS="$IGNORE_ARGS --ignore=$dir"
             done
-            python -m pytest -v tests/llm_translation $IGNORE_ARGS --junitxml=test-results/junit.xml --durations=20 -n 8 --timeout=120 --timeout_method=thread
+            python -m pytest -v tests/llm_translation $IGNORE_ARGS --junitxml=test-results/junit.xml --durations=20 -n 8 --timeout=120 --timeout_method=thread --retries 2 --retry-delay 5
           no_output_timeout: 15m
 
       # Store test results
@@ -1331,7 +1331,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/unified_google_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/unified_google_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5 --retries 3 --retry-delay 5
           no_output_timeout: 15m
       - run:
           name: Rename the coverage files

.github/workflows/codeql.yml

@@ -15,6 +15,7 @@ concurrency:
 
 jobs:
   analyze:
+    if: github.event_name != 'schedule' || github.repository == 'BerriAI/litellm'
     name: Analyze (${{ matrix.language }})
     runs-on: ubuntu-latest
     timeout-minutes: 30

.github/workflows/create_daily_staging_branch.yml

@@ -7,6 +7,7 @@ on:
 
 jobs:
   create-staging-branch:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
 
     steps:
@@ -43,6 +44,7 @@ jobs:
           fi
 
   create-internal-dev-branch:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/ghcr_deploy.yml

@@ -369,7 +369,8 @@ jobs:
   release:
     name: "New LiteLLM Release"
     needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
-
+    permissions:
+      contents: write
     runs-on: "ubuntu-latest"
    
     steps:

.github/workflows/stale.yml

@@ -7,6 +7,7 @@ on:
 
 jobs:
   stale:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/stale@v8

.github/workflows/test-linting.yml

@@ -28,9 +28,12 @@ jobs:
         find . -type d -name "__pycache__" -exec rm -rf {} + || true
         find . -name "*.pyc" -delete || true
 
+    - name: Check poetry.lock is up to date
+      run: |
+        poetry check --lock || (echo "❌ poetry.lock is out of sync with pyproject.toml. Run 'poetry lock' locally and commit the result." && exit 1)
+
     - name: Install dependencies
       run: |
-        poetry lock
         poetry install --with dev
 
     - name: Check Black formatting

.pre-commit-config.yaml

@@ -14,12 +14,12 @@ repos:
         types: [python]
         files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
         exclude: ^litellm/__init__.py$
-    # -   id: black
-    #     name: black
-    #     entry: poetry run black
-    #     language: system
-    #     types: [python]
-    #     files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
+    -   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:

CLAUDE.md

@@ -140,6 +140,11 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 - **Check index coverage.** For new or modified queries, check `schema.prisma` for a supporting index. Prefer extending an existing index (e.g. `@@index([a])` → `@@index([a, b])`) over adding a new one, unless it's a `@@unique`. Only add indexes for large/frequent queries.
 - **Keep schema files in sync.** Apply schema changes to all `schema.prisma` copies (`schema.prisma`, `litellm/proxy/`, `litellm-proxy-extras/`, `litellm-js/spend-logs/` for SpendLogs) with a migration under `litellm-proxy-extras/litellm_proxy_extras/migrations/`.
 
+### Setup Wizard (`litellm/setup_wizard.py`)
+- The wizard is implemented as a single `SetupWizard` class with `@staticmethod` methods — keep it that way. No module-level functions except `run_setup_wizard()` (the public entrypoint) and pure helpers (color, ANSI).
+- Use `litellm.utils.check_valid_key(model, api_key)` for credential validation — never roll a custom completion call.
+- Do not hardcode provider env-key names or model lists that already exist in the codebase. Add a `test_model` field to each provider entry to drive `check_valid_key`; set it to `None` for providers that can't be validated with a single API key (Azure, Bedrock, Ollama).
+
 ### Enterprise Features
 - Enterprise-specific code in `enterprise/` directory
 - Optional features enabled via environment variables

ci_cd/security_scans.sh

@@ -163,6 +163,9 @@ run_grype_scans() {
         "CVE-2026-25639" # axios - full fix requires 1.x major version bump; pinned to >=0.30.2 to clear other axios CVEs, upgrade to 1.x in follow-up
         "CVE-2026-2297" # Python 3.13 SourcelessFileLoader audit hook bypass - no fix available in base image
         "GHSA-qffp-2rhf-9h96" # tar hardlink path traversal - from nodejs_wheel bundled npm, not used in application runtime code
+        "CVE-2026-2673" # OpenSSL 3.6.1 TLS 1.3 key exchange group negotiation issue - no fix available yet
+        "CVE-2026-3644" # Python 3.13 vulnerability - no fix available in base image
+        "CVE-2026-4224" # Python 3.13 Expat parser stack overflow in ElementDeclHandler - no fix available in base image
     )
 
     # Build JSON array of allowlisted CVE IDs for jq

docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md

@@ -3,18 +3,9 @@ slug: anthropic_advanced_features
 title: "Day 0 Support: Claude 4.5 Opus (+Advanced Features)"
 date: 2025-11-25T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Guide to Claude Opus 4.5 and advanced features in LiteLLM: Tool Search, Programmatic Tool Calling, and Effort Parameter."
 tags: [anthropic, claude, tool search, programmatic tool calling, effort, advanced features]
 hide_table_of_contents: false
@@ -25,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 This guide covers Anthropic's latest model (Claude Opus 4.5) and its advanced features now available in LiteLLM: Tool Search, Programmatic Tool Calling, Tool Input Examples, and the Effort Parameter.
 
+{/* truncate */}
+
 ---
 
 | Feature | Supported Models |

docs/my-website/blog/anthropic_wildcard_model_access_incident/index.md

@@ -3,18 +3,9 @@ slug: anthropic-wildcard-model-access-incident
 title: "Incident Report: Wildcard Blocking New Models After Cost Map Reload"
 date: 2026-02-23T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 tags: [incident-report, proxy, auth, model-access]
 hide_table_of_contents: false
 ---

docs/my-website/blog/authors.yml

@@ -4,6 +4,12 @@ litellm:
   url: https://github.com/BerriAI/litellm
   image_url: https://github.com/BerriAI.png
 
+sameer:
+  name: Sameer Kankute
+  title: SWE @ LiteLLM (LLM Translation)
+  url: https://www.linkedin.com/in/sameer-kankute/
+  image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
+
 krrish:
   name: Krrish Dholakia
   title: CEO, LiteLLM
@@ -22,3 +28,21 @@ ishaan-alt:
   title: CTO, LiteLLM
   url: https://www.linkedin.com/in/reffajnaahsi/
   image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+
+ryan:
+  name: Ryan Crabbe
+  title: Performance Engineer, LiteLLM
+  url: https://www.linkedin.com/in/ryan-crabbe-0b9687214
+  image_url: https://media.licdn.com/dms/image/v2/D5603AQHt1t9Z4BJ6Gw/profile-displayphoto-shrink_400_400/profile-displayphoto-shrink_400_400/0/1724453682340?e=1772064000&v=beta&t=VXdmr13rsNB05wyA2F1TENOB5UuDHUZ0FCHTolNyR5M
+
+alexsander:
+  name: Alexsander Hamir
+  title: Performance Engineer, LiteLLM
+  url: https://www.linkedin.com/in/alexsander-baptista/
+  image_url: https://github.com/AlexsanderHamir.png
+
+yuneng:
+  name: Yuneng Jiang
+  title: SWE @ LiteLLM (Full Stack)
+  url: https://www.linkedin.com/in/yuneng-david-jiang-455676139/
+  image_url: https://avatars.githubusercontent.com/u/171294688?v=4

docs/my-website/blog/claude_code_beta_headers/index.md

@@ -3,18 +3,9 @@ slug: claude-code-beta-headers-incident
 title: "Incident Report: Invalid beta headers with Claude Code"
 date: 2026-02-16T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - sameer
+  - ishaan-alt
+  - krrish
 tags: [incident-report, anthropic, stability]
 hide_table_of_contents: false
 ---
@@ -173,5 +164,5 @@ curl -X POST "https://your-proxy-url/reload/anthropic_beta_headers" \
 
 ## Related documentation
 
-- [Managing Anthropic Beta Headers](../proxy/sync_anthropic_beta_headers.md) - Complete configuration guide
+- [Managing Anthropic Beta Headers](../../docs/proxy/sync_anthropic_beta_headers) - Complete configuration guide
 - [`anthropic_beta_headers_config.json`](https://github.com/BerriAI/litellm/blob/main/litellm/anthropic_beta_headers_config.json) - Current configuration file

docs/my-website/blog/claude_opus_4_6/index.md

@@ -3,18 +3,9 @@ slug: claude_opus_4_6
 title: "Day 0 Support: Claude Opus 4.6"
 date: 2026-02-05T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - sameer
+  - ishaan-alt
+  - krrish
 description: "Day 0 support for Claude Opus 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock."
 tags: [anthropic, claude, opus 4.6]
 hide_table_of_contents: false
@@ -25,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports Claude Opus 4.6 on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway.
 
+{/* truncate */}
+
 ## Docker Image
 
 ```bash

docs/my-website/blog/claude_sonnet_4_6/index.md

@@ -3,14 +3,8 @@ slug: claude_sonnet_4_6
 title: "Day 0 Support: Claude Sonnet 4.6"
 date: 2026-02-17T10:00:00
 authors:
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - ishaan-alt
+  - krrish
 description: "Day 0 support for Claude Sonnet 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock."
 tags: [anthropic, claude, sonnet 4.6]
 hide_table_of_contents: false
@@ -21,6 +15,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports Claude Sonnet 4.6 on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway.
 
+{/* truncate */}
+
 ## Docker Image
 
 ```bash

docs/my-website/blog/fastapi_middleware_performance/index.mdx

@@ -3,18 +3,9 @@ slug: fastapi-middleware-performance
 title: "Your Middleware Could Be a Bottleneck"
 date: 2026-02-07T10:00:00
 authors:
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Ryan Crabbe
-    title: "Performance Engineer, LiteLLM"
-    url: https://www.linkedin.com/in/ryan-crabbe-0b9687214
-    image_url: https://media.licdn.com/dms/image/v2/D5603AQHt1t9Z4BJ6Gw/profile-displayphoto-shrink_400_400/profile-displayphoto-shrink_400_400/0/1724453682340?e=1772064000&v=beta&t=VXdmr13rsNB05wyA2F1TENOB5UuDHUZ0FCHTolNyR5M
+  - krrish
+  - ishaan-alt
+  - ryan
 description: "How we improved LiteLLM proxy latency and throughput by replacing a single middleware base class"
 tags: [performance, fastapi, middleware]
 hide_table_of_contents: false

docs/my-website/blog/gemin_3.1/index.md

@@ -3,18 +3,9 @@ slug: gemini_3_1_pro
 title: "DAY 0 Support: Gemini 3.1 Pro on LiteLLM"
 date: 2026-02-19T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Guide to using Gemini 3.1 Pro on LiteLLM Proxy and SDK with day 0 support."
 tags: [gemini, day 0 support, llms]
 hide_table_of_contents: false
@@ -28,6 +19,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports `gemini-3.1-pro-preview` and all the new API changes along with it.
 
+{/* truncate */}
+
 ## Deploy this version
 
 <Tabs>
@@ -67,7 +60,7 @@ LiteLLM provides **full end-to-end support** for Gemini 3.1 Pro on:
 - ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
 - ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
 - ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent.md) compatible endpoint 
+- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
 
 All endpoints support:
 - Streaming and non-streaming responses
@@ -147,4 +140,3 @@ curl -X POST http://localhost:4000/v1/chat/completions \
 | `high` | `high` |
 | `disable` | `minimal` |
 | `none` | `minimal` |
-

docs/my-website/blog/gemini_3/index.md

@@ -3,18 +3,9 @@ slug: gemini_3
 title: "DAY 0 Support: Gemini 3 on LiteLLM"
 date: 2025-11-19T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Common questions and best practices for using gemini-3-pro-preview with LiteLLM Proxy and SDK."
 tags: [gemini, day 0 support, llms]
 hide_table_of_contents: false
@@ -29,6 +20,8 @@ This guide covers common questions and best practices for using `gemini-3-pro-pr
 
 :::
 
+{/* truncate */}
+
 ## Quick Start
 
 <Tabs>
@@ -976,8 +969,7 @@ messages.append(response.choices[0].message)  # ✅ Includes thought signatures
 
 ## Additional Resources
 
-- [Gemini Provider Documentation](../gemini.md)
-- [Thought Signatures Guide](../gemini.md#thought-signatures)
-- [Reasoning Content Documentation](../../reasoning_content.md)
-- [Function Calling Guide](../../function_calling.md)
-
+- [Gemini Provider Documentation](../../docs/providers/gemini)
+- [Thought Signatures Guide](../../docs/providers/gemini#thought-signatures)
+- [Reasoning Content Documentation](../../docs/reasoning_content)
+- [Function Calling Guide](../../docs/completion/function_call)

docs/my-website/blog/gemini_3_1_flash_lite/index.md

@@ -3,18 +3,9 @@ slug: gemini_3_1_flash_lite_preview
 title: "DAY 0 Support: Gemini 3.1 Flash Lite Preview on LiteLLM"
 date: 2026-03-03T08:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Guide to using Gemini 3.1 Flash Lite Preview on LiteLLM Proxy and SDK with day 0 support."
 tags: [gemini, day 0 support, llms, supernova]
 hide_table_of_contents: false
@@ -32,6 +23,8 @@ LiteLLM now supports `gemini-3.1-flash-lite-preview` with full day 0 support!
 If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above.
 :::
 
+{/* truncate */}
+
 ## Deploy this version
 
 <Tabs>
@@ -150,7 +143,7 @@ LiteLLM provides **full end-to-end support** for Gemini 3.1 Flash Lite Preview o
 - ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
 - ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
 - ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent.md) compatible endpoint 
+- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
 
 All endpoints support:
 - Streaming and non-streaming responses
@@ -172,4 +165,4 @@ LiteLLM automatically maps OpenAI's `reasoning_effort` parameter to Gemini's `th
 | `medium` | `medium` | Balanced reasoning for moderate complexity |
 | `high` | `high` | Maximum reasoning depth, complex problems |
 | `disable` | `minimal` | Disable extended reasoning |
-| `none` | `minimal` | No extended reasoning |
+| `none` | `minimal` | No extended reasoning |

docs/my-website/blog/gemini_3_flash/index.md

@@ -3,18 +3,9 @@ slug: gemini_3_flash
 title: "DAY 0 Support: Gemini 3 Flash on LiteLLM"
 date: 2025-12-17T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Guide to using Gemini 3 Flash on LiteLLM Proxy and SDK with day 0 support."
 tags: [gemini, day 0 support, llms]
 hide_table_of_contents: false
@@ -32,6 +23,8 @@ LiteLLM now supports `gemini-3-flash-preview` and all the new API changes along
 If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above.
 :::
 
+{/* truncate */}
+
 ## Deploy this version
 
 <Tabs>
@@ -80,7 +73,7 @@ LiteLLM provides **full end-to-end support** for Gemini 3 Flash on:
 - ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
 - ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
 - ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent.md) compatible endpoint 
+- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
 All endpoints support:
 - Streaming and non-streaming responses
 - Function calling with thought signatures
@@ -252,4 +245,3 @@ If using this model via vertex_ai, keep the location as global as this is the on
 | `high` | `high` |
 | `disable` | `minimal` |
 | `none` | `minimal` |
-

docs/my-website/blog/gemini_embedding_2_multimodal/index.md

@@ -3,10 +3,7 @@ slug: gemini_embedding_2_multimodal
 title: "Gemini Embedding 2 Preview: Multimodal Embeddings on LiteLLM"
 date: 2025-03-11T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
+  - sameer
 description: "Generate embeddings from text, images, audio, video, and PDFs with gemini-embedding-2-preview on LiteLLM via Gemini API and Vertex AI."
 tags: [gemini, embeddings, multimodal, vertex ai]
 hide_table_of_contents: false
@@ -19,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports **multimodal embeddings** with `gemini-embedding-2-preview`—generating a single embedding from a mix of text, images, audio, video, and PDF content. Available via both the **Gemini API** (API key) and **Vertex AI** (GCP credentials).
 
+{/* truncate */}
+
 ## Supported Input Types
 
 | Modality | Supported Formats | 

docs/my-website/blog/gpt_5_3_codex/index.md

@@ -3,18 +3,9 @@ slug: gpt_5_3_codex
 title: "Day 0 Support: GPT-5.3-Codex"
 date: 2026-02-24T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Day 0 support for GPT-5.3-Codex on LiteLLM, including phase parameter handling for Responses API."
 tags: [openai, gpt-5.3-codex, codex, day 0 support]
 hide_table_of_contents: false
@@ -25,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports GPT-5.3-Codex on Day 0, including support for the new assistant `phase` metadata on Responses API output items.
 
+{/* truncate */}
+
 ## Why `phase` matters for GPT-5.3-Codex
 
 `phase` appears on assistant output items and helps distinguish preamble/commentary turns from final closeout responses.

docs/my-website/blog/gpt_5_4/index.md

@@ -3,18 +3,9 @@ slug: gpt_5_4
 title: "Day 0 Support: GPT-5.4"
 date: 2026-03-05T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "GPT-5.4 model support in LiteLLM"
 tags: [openai, gpt-5.4, completion]
 hide_table_of_contents: false
@@ -25,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports fully GPT-5.4!
 
+{/* truncate */}
+
 ## Docker Image
 
 ```bash

docs/my-website/blog/gpt_5_4_mini_nano/index.md

@@ -0,0 +1,106 @@
+---
+slug: gpt_5_4_mini_nano
+title: "Day 0 Support: GPT-5.4-mini and GPT-5.4-nano"
+date: 2026-03-17T10:00:00
+authors:
+  - name: Sameer Kankute
+    title: SWE @ LiteLLM (LLM Translation)
+    url: https://www.linkedin.com/in/sameer-kankute/
+    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
+  - name: Krrish Dholakia
+    title: "CEO, LiteLLM"
+    url: https://www.linkedin.com/in/krish-d/
+    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - name: Ishaan Jaff
+    title: "CTO, LiteLLM"
+    url: https://www.linkedin.com/in/reffajnaahsi/
+    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+description: "GPT-5.4-mini and GPT-5.4-nano model support in LiteLLM"
+tags: [openai, gpt-5.4-mini, gpt-5.4-nano, completion]
+hide_table_of_contents: false
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+LiteLLM now supports GPT-5.4-mini and GPT-5.4-nano — cost-effective models for simple completions and high-throughput workloads.
+
+:::note
+If you're on **v1.82.3-stable** or above, you don't need any update to use these models.
+:::
+
+## Usage
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+  - model_name: gpt-5.4-mini
+    litellm_params:
+      model: openai/gpt-5.4-mini
+      api_key: os.environ/OPENAI_API_KEY
+  - model_name: gpt-5.4-nano
+    litellm_params:
+      model: openai/gpt-5.4-nano
+      api_key: os.environ/OPENAI_API_KEY
+```
+
+**2. Start the proxy**
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+**3. Test it**
+
+```bash
+# GPT-5.4-mini
+curl -X POST "http://localhost:4000/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "gpt-5.4-mini",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}]
+  }'
+
+# GPT-5.4-nano
+curl -X POST "http://localhost:4000/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $LITELLM_KEY" \
+  -d '{
+    "model": "gpt-5.4-nano",
+    "messages": [{"role": "user", "content": "What is 2 + 2?"}]
+  }'
+```
+
+</TabItem>
+<TabItem value="sdk" label="LiteLLM SDK">
+
+```python
+from litellm import completion
+
+# GPT-5.4-mini
+response = completion(
+    model="openai/gpt-5.4-mini",
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+)
+print(response.choices[0].message.content)
+
+# GPT-5.4-nano
+response = completion(
+    model="openai/gpt-5.4-nano",
+    messages=[{"role": "user", "content": "What is 2 + 2?"}],
+)
+print(response.choices[0].message.content)
+```
+
+</TabItem>
+</Tabs>
+
+## Notes
+
+- Both models support function calling, vision, and tool-use — see the [OpenAI provider docs](../../docs/providers/openai) for advanced usage.
+- GPT-5.4-nano is the most cost-effective option for simple tasks; GPT-5.4-mini offers a balance of speed and capability.

docs/my-website/blog/guardrail_logging_secret_exposure_incident/index.md

@@ -0,0 +1,78 @@
+---
+slug: guardrail-logging-secret-exposure-incident
+title: "Incident Report: Guardrail logging exposed secret headers in spend logs and traces"
+date: 2026-03-18T10:00:00
+authors:
+  - litellm
+tags: [incident-report, security, guardrails]
+hide_table_of_contents: false
+---
+
+**Date:** March 18, 2026
+**Duration:** Unknown
+**Severity:** High
+**Status:** Resolved
+
+## Summary
+
+When a custom guardrail returned the full LiteLLM request/data dictionary, the guardrail response logged by LiteLLM could include `secret_fields.raw_headers`, including plaintext `Authorization` headers containing API keys or other credentials.
+
+This information could then propagate to logging and observability surfaces that consume guardrail metadata, including:
+
+- **Spend logs in the LiteLLM UI:** visible to admins with access to spend-log data
+- **OpenTelemetry traces:** visible to anyone with access to the relevant telemetry backend
+
+LLM calls, proxy routing, and provider execution were not blocked by this bug. The impact was exposure of sensitive request headers in observability and logging paths.
+
+{/* truncate */}
+
+---
+
+## Background
+
+LiteLLM keeps internal request data (including request headers) for use during the call. That data is not meant to be written to logs or telemetry.
+
+When custom guardrails run, their outcomes are logged so they can appear in spend logs, OpenTelemetry traces, and other observability backends. If a guardrail returned the full request payload instead of a minimal result, that internal request data could be included in what was logged. Before the fix, the guardrail logging path did not strip that data before sending it to those systems.
+
+```mermaid
+flowchart TD
+    inboundRequest["1. Incoming proxy request"] --> storeSecrets["2. Store internal request data"]
+    storeSecrets --> guardrailRuns["3. Custom guardrail runs"]
+    guardrailRuns --> fullDataReturn["4. Guardrail returns full request payload"]
+    fullDataReturn --> loggingBuild["5. Build guardrail log payload"]
+    loggingBuild --> spendLogs["6a. Persist to spend logs / UI"]
+    loggingBuild --> otelTraces["6b. Attach to OTEL guardrail spans"]
+```
+
+---
+
+## Root Cause
+
+The root cause was incomplete sanitization in the guardrail logging path. When building the payload that gets sent to spend logs and traces, LiteLLM prepared guardrail responses for logging but did not strip internal request data (such as headers) from them. If a guardrail returned a response that included that data, it was passed through to the logging and observability systems unchanged.
+
+---
+
+## Impact
+
+This issue required all of the following:
+
+1. A custom guardrail returned the full LiteLLM request/data dictionary, or another response object containing `secret_fields`.
+2. LiteLLM logged that guardrail response through the standard guardrail logging path.
+3. An operator, admin, or telemetry consumer had access to the resulting logs or traces.
+
+When those conditions were met, sensitive values could become visible through:
+
+- **Spend logs / UI responses:** guardrail metadata could be included in spend-log payloads rendered in the admin UI.
+- **OpenTelemetry traces:** `guardrail_response` could be written as a span attribute on guardrail spans.
+- **Other downstream observability backends:** any integration consuming the same guardrail metadata could receive the leaked values.
+
+This was a logging and telemetry exposure bug. It did not let callers bypass auth, access other tenants directly, or change model behavior, but it could expose plaintext credentials to people with access to those observability systems.
+
+---
+
+## Guidance For Users
+
+- Upgrade to LiteLLM 1.82.3+.
+- If you operated custom guardrails that return the full request/data dict, review whether spend logs or telemetry traces were retained during the affected period.
+- Rotate any credentials that may have appeared in `Authorization` or other forwarded request headers in those systems.
+- Apply least-privilege access controls to spend-log views and telemetry backends that may contain request-derived metadata.

docs/my-website/blog/httpx_cache_eviction_incident/index.md

@@ -3,17 +3,9 @@ slug: httpx-cache-eviction-incident
 title: "Incident Report: Cache Eviction Closes In-Use httpx Clients"
 date: 2026-02-27T10:00:00
 authors:
-  - name: Ryan Crabbe
-    title: Performance Engineer, LiteLLM
-    url: https://www.linkedin.com/in/ryan-crabbe-0b9687214
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - ryan
+  - ishaan-alt
+  - krrish
 tags: [incident-report, caching, stability]
 hide_table_of_contents: false
 ---
@@ -31,6 +23,8 @@ A change to improve Redis connection pool cleanup introduced a regression that c
 
 **Impact:** Any proxy instance that hit the cache TTL (default 10 minutes) or capacity limit (200 entries) would have its httpx clients closed out from under it, causing requests to LLM providers to fail with connection errors.
 
+{/* truncate */}
+
 ---
 
 ## Background

docs/my-website/blog/litellm_observatory/index.md

@@ -3,18 +3,9 @@ slug: litellm-observatory
 title: "Improve release stability with 24 hour load tests"
 date: 2026-02-06T10:00:00
 authors:
-  - name: Alexsander Hamir
-    title: "Performance Engineer, LiteLLM"
-    url: https://www.linkedin.com/in/alexsander-baptista/
-    image_url: https://github.com/AlexsanderHamir.png
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - alexsander
+  - krrish
+  - ishaan-alt
 description: "How we built a long-running, release-validation system to catch regressions before they reach users."
 tags: [testing, observability, reliability, releases]
 hide_table_of_contents: false
@@ -28,6 +19,8 @@ As LiteLLM adoption has grown, so have expectations around reliability, performa
 
 This post introduces **LiteLLM Observatory**, a long-running release-validation system we built to catch regressions before they reach users.
 
+{/* truncate */}
+
 ---
 
 ## Why We Built the Observatory
@@ -133,4 +126,3 @@ Reliability is an ongoing investment.
 LiteLLM Observatory is one of several systems we’re building to continuously raise the bar on release quality and operational safety. As LiteLLM evolves, so will our validation tooling, informed by real-world usage and lessons learned.
 
 We’ll continue to share those improvements openly as we go.
-

docs/my-website/blog/minimax_m2_5/index.md

@@ -3,18 +3,9 @@ slug: minimax_m2_5
 title: "Day 0 Support: MiniMax-M2.5"
 date: 2026-02-12T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Day 0 support for MiniMax-M2.5 on LiteLLM"
 tags: [minimax, M2.5, llm]
 hide_table_of_contents: false
@@ -25,6 +16,8 @@ import TabItem from '@theme/TabItem';
 
 LiteLLM now supports MiniMax-M2.5 on Day 0. Use it across OpenAI-compatible and Anthropic-compatible APIs through the LiteLLM AI Gateway.
 
+{/* truncate */}
+
 ## Supported Models
 
 LiteLLM supports the following MiniMax models:

docs/my-website/blog/model_cost_map_incident/index.md

@@ -3,10 +3,7 @@ slug: model-cost-map-incident
 title: "Incident Report: Invalid model cost map on main"
 date: 2026-02-10T10:00:00
 authors:
-  - name: Ishaan Jaffer
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/ishaanjaffer/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - ishaan
 tags: [incident-report, stability]
 hide_table_of_contents: false
 ---

docs/my-website/blog/realtime_webrtc_http_endpoints/index.md

@@ -3,18 +3,9 @@ slug: realtime_webrtc_http_endpoints
 title: "Realtime WebRTC HTTP Endpoints"
 date: 2026-03-12T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "Use the LiteLLM proxy to route OpenAI-style WebRTC realtime via HTTP: client_secrets and SDP exchange."
 tags: [realtime, webrtc, proxy, openai]
 hide_table_of_contents: false
@@ -24,6 +15,8 @@ import WebRTCTester from '@site/src/components/WebRTCTester';
 
 Connect to the Realtime API via WebRTC from browser/mobile clients. LiteLLM handles auth and key management.
 
+{/* truncate */}
+
 ## How it works
 
 ![WebRTC flow: Browser, LiteLLM Proxy, and OpenAI/Azure](../../img/webrtc_flow.png)
@@ -116,4 +109,3 @@ A: Set the correct `api_version` in `litellm_params` (or via the `AZURE_API_VERS
 
 **Q: What if I get no audio?**  
 A: Make sure you grant microphone permission, ensure `pc.ontrack` assigns the audio element with `autoplay` enabled, check your network/firewall for WebRTC traffic, and inspect the browser console for ICE or SDP errors.
-

docs/my-website/blog/responses_api_encrypted_content_incident/index.md

@@ -3,18 +3,9 @@ slug: responses-api-encrypted-content-incident
 title: "Incident Report: Encrypted Content Failures in Multi-Region Responses API Load Balancing"
 date: 2026-02-24T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 tags: [incident-report, proxy, responses-api, load-balancing]
 hide_table_of_contents: false
 ---

docs/my-website/blog/server_root_path/index.md

@@ -3,17 +3,9 @@ slug: server-root-path-incident
 title: "Incident Report: SERVER_ROOT_PATH regression broke UI routing"
 date: 2026-02-21T10:00:00
 authors:
-  - name: Yuneng Jiang
-    title: SWE @ LiteLLM (Full Stack)
-    url: https://www.linkedin.com/in/yunengjiang/
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - yuneng
+  - ishaan-alt
+  - krrish
 tags: [incident-report, ui, stability]
 hide_table_of_contents: false
 ---

docs/my-website/blog/sub_millisecond_proxy_overhead/index.md

@@ -3,18 +3,9 @@ slug: sub-millisecond-proxy-overhead
 title: "Achieving Sub-Millisecond Proxy Overhead"
 date: 2026-02-02T10:00:00
 authors:
-  - name: Alexsander Hamir
-    title: "Performance Engineer, LiteLLM"
-    url: https://www.linkedin.com/in/alexsander-baptista/
-    image_url: https://github.com/AlexsanderHamir.png
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - alexsander
+  - krrish
+  - ishaan-alt
 description: "Our Q1 performance target and architectural direction for achieving sub-millisecond proxy overhead on modest hardware."
 tags: [performance, architecture]
 hide_table_of_contents: false
@@ -32,6 +23,8 @@ Proxy overhead refers to the latency introduced by LiteLLM itself, independent o
 
 To measure it, we run the same workload directly against the provider and through LiteLLM at identical QPS (for example, 1,000 QPS) and compare the latency delta. To reduce noise, the load generator, LiteLLM, and a mock LLM endpoint all run on the same machine, ensuring the difference reflects proxy overhead rather than network latency.
 
+{/* truncate */}
+
 ---
 
 ## Where We're Coming From

docs/my-website/blog/video_characters_litellm/index.md

@@ -3,18 +3,9 @@ slug: video_characters_api
 title: "New Video Characters, Edit and Extension API support"
 date: 2026-03-16T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 description: "LiteLLM now supports creating, retrieving, and managing reusable video characters across multiple video generations."
 tags: [videos, characters, proxy, routing]
 hide_table_of_contents: false
@@ -22,6 +13,8 @@ hide_table_of_contents: false
 
 LiteLLM now supoports videos character, edit and extension apis.
 
+{/* truncate */}
+
 ## What's New
 
 Four new endpoints for video character operations:
@@ -125,4 +118,4 @@ Router knows exactly which deployment to use
 **Behind the scenes:**
 - Character ID format: `character_<base64_encoded_metadata>`
 - Metadata includes: provider, model_id, original_character_id
-- Transparent to you - just use the ID, LiteLLM handles routing
+- Transparent to you - just use the ID, LiteLLM handles routing

docs/my-website/blog/vllm_embeddings_incident/index.md

@@ -3,18 +3,9 @@ slug: vllm-embeddings-incident
 title: "Incident Report: vLLM Embeddings Broken by encoding_format Parameter"
 date: 2026-02-18T10:00:00
 authors:
-  - name: Sameer Kankute
-    title: SWE @ LiteLLM (LLM Translation)
-    url: https://www.linkedin.com/in/sameer-kankute/
-    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-  - name: Krrish Dholakia
-    title: "CEO, LiteLLM"
-    url: https://www.linkedin.com/in/krish-d/
-    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-  - name: Ishaan Jaff
-    title: "CTO, LiteLLM"
-    url: https://www.linkedin.com/in/reffajnaahsi/
-    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - sameer
+  - krrish
+  - ishaan-alt
 tags: [incident-report, embeddings, vllm]
 hide_table_of_contents: false
 ---

docs/my-website/docs/anthropic_unified/index.md

@@ -506,12 +506,15 @@ Request body will be in the Anthropic messages API format. **litellm follows the
   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):  
+- **thinking** (object):
   Configuration for enabling extended thinking. If enabled, it includes:
-  - **budget_tokens** (integer):  
+  - **budget_tokens** (integer):
     Minimum of 1024 tokens (and less than `max_tokens`).
-  - **type** (enum):  
+  - **type** (enum):
     E.g., `"enabled"`.
+  - **summary** (string, optional):
+    Enables the summary style for thinking blocks. Possible values: `"auto"`, `"concise"`, `"detailed"`, `"disabled"`.
+    When routing to non-Anthropic providers (e.g., `openai/gpt-5.1`), the `summary` value is preserved and forwarded to the downstream API.
 - **tool_choice** (object):  
   Instructs how the model should utilize any provided tools.
 - **tools** (array of objects):  

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

@@ -6,6 +6,8 @@ import TabItem from '@theme/TabItem';
 Supported Providers:
 - OpenAI (`openai/`)
 - Anthropic API (`anthropic/`)
+- Google AI Studio (`gemini/`)
+- Vertex AI (`vertex_ai/`, `vertex_ai_beta/`)
 - 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/`)
 
@@ -257,7 +259,7 @@ Anthropic charges for cache writes.
 
 Specify the content to cache with `"cache_control": {"type": "ephemeral"}`.
 
-If you pass that in for any other llm provider, it will be ignored. 
+This same format also works for [Gemini / Vertex AI](#google-ai-studio--vertex-ai-gemini-example). For other providers, it will be ignored.
 
 <Tabs>
 <TabItem value="sdk" label="SDK">
@@ -356,6 +358,208 @@ print(response.usage)
 </TabItem>
 </Tabs>
 
+### Google AI Studio / Vertex AI (Gemini) Example
+
+Use the same Anthropic-style `cache_control` format — LiteLLM automatically translates it to Google's [context caching API](https://ai.google.dev/api/caching).
+
+**How it works under the hood:**
+1. Messages with `cache_control` are separated and sent to Google's `cachedContents` API
+2. The cached content ID is then passed as `cachedContent` in the Gemini request body
+3. Works across all three providers: `gemini/` (Google AI Studio), `vertex_ai/`, and `vertex_ai_beta/`
+4. Requires a minimum of **1024 tokens** in the cached content — below that, caching is silently skipped
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+import os
+
+os.environ["GEMINI_API_KEY"] = ""
+
+response = completion(
+    model="gemini/gemini-2.5-flash",
+    messages=[
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are an AI assistant tasked with analyzing legal documents.",
+                },
+                {
+                    "type": "text",
+                    "text": "Here is the full text of a complex legal agreement" * 400,
+                    "cache_control": {"type": "ephemeral"},
+                },
+            ],
+        },
+        {
+            "role": "user",
+            "content": "what are the key terms and conditions in this agreement?",
+        },
+    ],
+)
+
+print(response.usage)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+    - model_name: gemini-2.5-flash
+      litellm_params:
+        model: gemini/gemini-2.5-flash
+        api_key: os.environ/GEMINI_API_KEY
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it!
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="LITELLM_PROXY_KEY",  # sk-1234
+    base_url="LITELLM_PROXY_BASE",  # http://0.0.0.0:4000
+)
+
+response = client.chat.completions.create(
+    model="gemini-2.5-flash",
+    messages=[
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are an AI assistant tasked with analyzing legal documents.",
+                },
+                {
+                    "type": "text",
+                    "text": "Here is the full text of a complex legal agreement" * 400,
+                    "cache_control": {"type": "ephemeral"},
+                },
+            ],
+        },
+        {
+            "role": "user",
+            "content": "what are the key terms and conditions in this agreement?",
+        },
+    ],
+)
+
+print(response.usage)
+```
+
+</TabItem>
+</Tabs>
+
+#### Vertex AI
+
+For Vertex AI, use `vertex_ai/` prefix:
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+response = completion(
+    model="vertex_ai/gemini-2.5-flash",
+    vertex_project="my-gcp-project",
+    vertex_location="us-central1",
+    messages=[
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are an AI assistant tasked with analyzing legal documents.",
+                },
+                {
+                    "type": "text",
+                    "text": "Here is the full text of a complex legal agreement" * 400,
+                    "cache_control": {"type": "ephemeral"},
+                },
+            ],
+        },
+        {
+            "role": "user",
+            "content": "what are the key terms and conditions in this agreement?",
+        },
+    ],
+)
+
+print(response.usage)
+```
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+    - model_name: gemini-2.5-flash
+      litellm_params:
+        model: vertex_ai/gemini-2.5-flash
+        vertex_project: my-gcp-project
+        vertex_location: us-central1
+```
+
+2. Start proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it!
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="LITELLM_PROXY_KEY",  # sk-1234
+    base_url="LITELLM_PROXY_BASE",  # http://0.0.0.0:4000
+)
+
+response = client.chat.completions.create(
+    model="gemini-2.5-flash",
+    messages=[
+        {
+            "role": "system",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "You are an AI assistant tasked with analyzing legal documents.",
+                },
+                {
+                    "type": "text",
+                    "text": "Here is the full text of a complex legal agreement" * 400,
+                    "cache_control": {"type": "ephemeral"},
+                },
+            ],
+        },
+        {
+            "role": "user",
+            "content": "what are the key terms and conditions in this agreement?",
+        },
+    ],
+)
+
+print(response.usage)
+```
+
+</TabItem>
+</Tabs>
+
 ### Deepeek Example 
 
 Works the same as OpenAI. 

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

@@ -0,0 +1,78 @@
+---
+title: Guides
+sidebar_label: Overview
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+**Guides** are focused references organized by the job you are trying to do with LiteLLM: make requests, use tools, handle media, manage context, or operate the gateway safely.
+
+> New to LiteLLM or not sure whether you need the SDK or Gateway path first? Start at [Learn →](/docs/learn)
+
+---
+
+## Build With LiteLLM
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "⚡",
+    title: "Core Requests",
+    description: "Streaming, batching, structured outputs, and reasoning behavior.",
+    to: "/docs/guides/core_request_response_patterns",
+  },
+  {
+    icon: "🛠️",
+    title: "Tool Calling",
+    description: "Function calling, web tools, interception patterns, computer use, code interpreter, and tool-call hygiene.",
+    to: "/docs/guides/tools_integrations",
+  },
+  {
+    icon: "🖼️",
+    title: "Multimodal I/O",
+    description: "Vision, audio, PDFs, image generation, and video generation.",
+    to: "/docs/guides/multimodal_io",
+  },
+  {
+    icon: "📚",
+    title: "Retrieval & Knowledge",
+    description: "Vector stores, file search, citations, and knowledge-base routing.",
+    to: "/docs/guides/retrieval_knowledge",
+  },
+  {
+    icon: "🧠",
+    title: "Prompts & Context",
+    description: "Prompt caching, trimming, formatting, assistant prefill, and predicted outputs.",
+    to: "/docs/guides/prompts_context",
+  },
+]}
+/>
+
+---
+
+## Operate & Extend
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "🎛️",
+    title: "Compatibility & Extensibility",
+    description: "Provider-specific params, model aliases, fine-tuned models, and adapters.",
+    to: "/docs/guides/compatibility_extensibility",
+  },
+  {
+    icon: "🧪",
+    title: "Reliability, Testing & Spend",
+    description: "Retries, fallbacks, mock responses, and budget controls.",
+    to: "/docs/guides/reliability_testing_spend",
+  },
+  {
+    icon: "🔒",
+    title: "Security & Network",
+    description: "SSL, custom CA bundles, HTTP proxy settings, and per-service verification.",
+    to: "/docs/guides/security_network",
+  },
+]}
+/>

docs/my-website/docs/integrations/index.md

@@ -1,18 +1,336 @@
-# Integrations
+---
+title: Integrations
+sidebar_label: Overview
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
 
 This section covers integrations with various tools and services that can be used with LiteLLM (either Proxy or SDK).
 
-## AI Agent Frameworks
-- **[Letta](./letta.md)** - Build stateful LLM agents with persistent memory using LiteLLM Proxy
+---
 
-## Development Tools
-- **[OpenWebUI](../tutorials/openweb_ui.md)** - Self-hosted ChatGPT-style interface
+## Observability
 
-## Observability & Monitoring
-- **[Langfuse](../observability/langfuse_integration.md)** - LLM observability and analytics
-- **[Prometheus](../proxy/prometheus.md)** - Metrics collection and monitoring
-- **[PagerDuty](../proxy/pagerduty.md)** - Incident response and alerting
-- **[Datadog](../observability/datadog.md)**
+Track, debug, and analyze LLM calls with observability platforms.
 
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "🪢",
+    title: "Langfuse",
+    description: "LLM observability and analytics.",
+    to: "/docs/observability/langfuse_integration",
+  },
+  {
+    icon: "🐶",
+    title: "Datadog",
+    description: "Metrics, traces, and dashboards.",
+    to: "/docs/observability/datadog",
+  },
+  {
+    icon: "📡",
+    title: "OpenTelemetry",
+    description: "Vendor-neutral tracing.",
+    to: "/docs/observability/opentelemetry_integration",
+  },
+  {
+    icon: "🔗",
+    title: "LangSmith",
+    description: "LLM debugging and evaluation.",
+    to: "/docs/observability/langsmith_integration",
+  },
+  {
+    icon: "🔥",
+    title: "Arize / Phoenix",
+    description: "ML observability and evaluation.",
+    to: "/docs/observability/arize_integration",
+  },
+  {
+    icon: "🌀",
+    title: "Helicone",
+    description: "LLM request logging and analytics.",
+    to: "/docs/observability/helicone_integration",
+  },
+  {
+    icon: "📊",
+    title: "MLflow",
+    description: "Experiment tracking.",
+    to: "/docs/observability/mlflow",
+  },
+  {
+    icon: "🏋️",
+    title: "Weights & Biases",
+    description: "ML experiment tracking.",
+    to: "/docs/observability/wandb_integration",
+  },
+  {
+    icon: "📉",
+    title: "PostHog",
+    description: "Product analytics.",
+    to: "/docs/observability/posthog_integration",
+  },
+]}
+/>
 
-Click into each section to learn more about the integrations.
+[View all observability integrations →](/docs/integrations/observability_integrations)
+
+---
+
+## Alerting & Monitoring
+
+Set up alerts, metrics collection, and infrastructure monitoring.
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "📈",
+    title: "Prometheus",
+    description: "Metrics collection and monitoring.",
+    to: "../proxy/prometheus",
+  },
+  {
+    icon: "🚨",
+    title: "PagerDuty",
+    description: "Incident response and alerting.",
+    to: "../proxy/pagerduty",
+  },
+  {
+    icon: "🔔",
+    title: "Alerting",
+    description: "Slack, Teams, and webhook alerts.",
+    to: "../proxy/alerting",
+  },
+  {
+    icon: "🔍",
+    title: "Pyroscope",
+    description: "Continuous profiling.",
+    to: "../proxy/pyroscope_profiling",
+  },
+]}
+/>
+
+---
+
+## Guardrail Providers
+
+Add safety and content filtering to LLM calls.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "🛡️",
+    title: "Lakera AI",
+    description: "Prompt injection detection.",
+    to: "/docs/proxy/guardrails/lakera_ai",
+  },
+  {
+    icon: "☁️",
+    title: "Azure Content Safety",
+    description: "Content moderation.",
+    to: "/docs/proxy/guardrails/azure_content_guardrail",
+  },
+  {
+    icon: "🛏️",
+    title: "Bedrock Guardrails",
+    description: "AWS Bedrock safety.",
+    to: "/docs/proxy/guardrails/bedrock",
+  },
+  {
+    icon: "🤖",
+    title: "OpenAI Moderation",
+    description: "OpenAI content policy.",
+    to: "/docs/proxy/guardrails/openai_moderation",
+  },
+  {
+    icon: "🔐",
+    title: "Secret Detection",
+    description: "Prevent credential leaks.",
+    to: "/docs/proxy/guardrails/secret_detection",
+  },
+  {
+    icon: "🕵️",
+    title: "PII Masking",
+    description: "Mask sensitive data.",
+    to: "/docs/proxy/guardrails/pii_masking_v2",
+  },
+]}
+/>
+
+[View all guardrail providers →](/docs/guardrail_providers)
+
+---
+
+## Policies
+
+Define and enforce usage policies across your LLM deployment.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "📋",
+    title: "Guardrail Policies",
+    description: "Policy-based guardrail rules.",
+    to: "../proxy/guardrails/guardrail_policies",
+  },
+  {
+    icon: "🔀",
+    title: "Policy Flow Builder",
+    description: "Visual policy configuration.",
+    to: "../proxy/guardrails/policy_flow_builder",
+  },
+  {
+    icon: "📄",
+    title: "Policy Templates",
+    description: "Pre-built policy templates.",
+    to: "../proxy/guardrails/policy_templates",
+  },
+]}
+/>
+
+---
+
+## AI Tools
+
+Connect LiteLLM to AI-powered coding and productivity tools.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "💬",
+    title: "OpenWebUI",
+    description: "Self-hosted ChatGPT-style interface.",
+    to: "../tutorials/openweb_ui",
+  },
+  {
+    icon: "🤖",
+    title: "Claude Code",
+    description: "Use LiteLLM with Claude Code.",
+    to: "../tutorials/claude_responses_api",
+  },
+  {
+    icon: "🖱️",
+    title: "Cursor",
+    description: "AI code editor integration.",
+    to: "../tutorials/cursor_integration",
+  },
+  {
+    icon: "🐙",
+    title: "GitHub Copilot",
+    description: "GitHub Copilot integration.",
+    to: "../tutorials/github_copilot_integration",
+  },
+  {
+    icon: "💻",
+    title: "OpenCode",
+    description: "Open source coding assistant.",
+    to: "../tutorials/opencode_integration",
+  },
+  {
+    icon: "🔧",
+    title: "Retool Assist",
+    description: "Retool AI assistant.",
+    to: "../tutorials/retool_assist",
+  },
+]}
+/>
+
+---
+
+## Agent SDKs
+
+Use LiteLLM with agent frameworks and SDKs.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "🤖",
+    title: "OpenAI Agents SDK",
+    description: "Build agents with OpenAI's SDK.",
+    to: "../tutorials/openai_agents_sdk",
+  },
+  {
+    icon: "🧠",
+    title: "Claude Agent SDK",
+    description: "Build agents with Anthropic's SDK.",
+    to: "../tutorials/claude_agent_sdk",
+  },
+  {
+    icon: "🌐",
+    title: "Google ADK",
+    description: "Google Agent Development Kit.",
+    to: "../tutorials/google_adk",
+  },
+  {
+    icon: "🚀",
+    title: "CopilotKit",
+    description: "In-app AI copilots.",
+    to: "../tutorials/copilotkit_sdk",
+  },
+  {
+    icon: "🧬",
+    title: "Letta",
+    description: "Build stateful LLM agents with persistent memory.",
+    to: "./letta",
+  },
+  {
+    icon: "🎙️",
+    title: "LiveKit",
+    description: "Real-time voice and video AI agents.",
+    to: "../tutorials/livekit_xai_realtime",
+  },
+]}
+/>
+
+---
+
+## Prompt Management
+
+Manage, version, and deploy prompts.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "📝",
+    title: "LiteLLM Prompt Management",
+    description: "Built-in prompt management.",
+    to: "../proxy/litellm_prompt_management",
+  },
+  {
+    icon: "🔌",
+    title: "Custom Prompt Management",
+    description: "Bring your own prompt store.",
+    to: "../proxy/custom_prompt_management",
+  },
+  {
+    icon: "🔥",
+    title: "Arize Phoenix Prompts",
+    description: "Prompt management with Phoenix.",
+    to: "../proxy/arize_phoenix_prompts",
+  },
+]}
+/>
+
+---
+
+## Manage with AI Agents
+
+Use AI agents to manage your LiteLLM deployment — create users, teams, keys, models, and more via natural language.
+
+<NavigationCards
+columns={1}
+items={[
+  {
+    icon: "🤖",
+    title: "LiteLLM Skills",
+    description: "Manage LiteLLM via Claude Code — create keys, teams, models, and more using natural language commands.",
+    to: "../tutorials/claude_code_skills",
+  },
+]}
+/>

docs/my-website/docs/integrations/letta.md

@@ -920,9 +920,9 @@ for model in models:
 
 ## Resources
 
-- [Letta Documentation](https://docs.letta.ai/)
-- [LiteLLM Proxy Documentation](../proxy/quick_start.md)
-- [LiteLLM SDK Documentation](../completion/input.md)
-- [Function Calling Guide](../completion/function_call.md)
-- [Observability Setup](../observability/langfuse_integration.md)
-- [Router Configuration](../routing.md)
+- [Letta Documentation](https://docs.letta.com/)
+- [LiteLLM Proxy Documentation](/docs/simple_proxy)
+- [LiteLLM SDK Documentation](/docs/#litellm-python-sdk)
+- [Function Calling Guide](/docs/completion/function_call)
+- [Observability Setup](/docs/integrations/observability_integrations)
+- [Router Configuration](/docs/routing)

docs/my-website/docs/integrations/observability_index.md

@@ -0,0 +1,28 @@
+---
+title: Observability
+sidebar_label: Overview
+slug: observability_integrations
+---
+
+Track, debug, and analyze LLM calls with observability platforms.
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+## Observability Integrations
+
+<NavigationCards
+columns={3}
+items={[
+  { icon: "🪢", title: "Langfuse", description: "LLM observability and analytics.", to: "/docs/observability/langfuse_integration" },
+  { icon: "🐶", title: "Datadog", description: "Metrics, traces, and dashboards.", to: "/docs/observability/datadog" },
+  { icon: "📡", title: "OpenTelemetry", description: "Vendor-neutral tracing.", to: "/docs/observability/opentelemetry_integration" },
+  { icon: "🔗", title: "LangSmith", description: "LLM debugging and evaluation.", to: "/docs/observability/langsmith_integration" },
+  { icon: "🔥", title: "Arize / Phoenix", description: "ML observability and evaluation.", to: "/docs/observability/arize_integration" },
+  { icon: "🌀", title: "Helicone", description: "LLM request logging and analytics.", to: "/docs/observability/helicone_integration" },
+  { icon: "📊", title: "MLflow", description: "Experiment tracking.", to: "/docs/observability/mlflow" },
+  { icon: "🏋️", title: "Weights & Biases", description: "ML experiment tracking.", to: "/docs/observability/wandb_integration" },
+  { icon: "📉", title: "PostHog", description: "Product analytics.", to: "/docs/observability/posthog_integration" },
+]}
+/>
+
+[View all observability integrations →](/docs/observability/callbacks)

docs/my-website/docs/integrations/websearch_interception.md

@@ -375,7 +375,7 @@ search_tools:
 - [Search Providers](../search/index.md) - Detailed search provider setup
 - [Claude Code WebSearch](../tutorials/claude_code_websearch.md) - Using with Claude Code
 - [Tool Calling](../completion/function_call.md) - General tool calling documentation
-- [Callbacks](./custom_callback.md) - Custom callback documentation
+- [Callbacks](../observability/custom_callback.md) - Custom callback documentation
 
 ## Technical Details
 

docs/my-website/docs/learn/gateway_quickstart.md

@@ -0,0 +1,174 @@
+---
+title: Gateway Quickstart
+sidebar_label: Gateway Quickstart
+description: Start LiteLLM Gateway, add models and keys, then connect applications and SDKs to one shared endpoint.
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+Use this path if you need one shared OpenAI-compatible endpoint for a team or platform.
+
+If you need a Docker or database-first setup, use the [Docker + Database tutorial](/docs/proxy/docker_quick_start). Otherwise, use the steps below to get to a working request fast.
+
+## 1. Install The Gateway
+
+```bash
+pip install 'litellm[proxy]'
+```
+
+## 2. Set One Provider Key
+
+```bash
+export OPENAI_API_KEY="your-api-key"
+```
+
+## 3. Create `config.yaml`
+
+```yaml
+model_list:
+  - model_name: gpt-4o-mini
+    litellm_params:
+      model: openai/gpt-4o-mini
+      api_key: os.environ/OPENAI_API_KEY
+
+general_settings:
+  master_key: sk-1234
+```
+
+## 4. Start The Gateway
+
+```bash
+litellm --config config.yaml
+```
+
+You should see the proxy start on `http://0.0.0.0:4000`.
+
+## 5. Send Your First 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": "gpt-4o-mini",
+    "messages": [
+      {"role": "user", "content": "Hello from LiteLLM Gateway"}
+    ]
+  }'
+```
+
+## 6. Check The Response
+
+If the request succeeds, the proxy returns `200 OK` with an OpenAI-style response.
+
+The assistant text will be in:
+
+```json
+choices[0].message.content
+```
+
+If your gateway is routing to OpenAI, a real response can look like this:
+
+```json
+{
+  "id": "chatcmpl-abc123",
+  "created": 1677858242,
+  "model": "gpt-4o-mini-2024-07-18",
+  "object": "chat.completion",
+  "system_fingerprint": "fp_406d6473f8",
+  "choices": [
+    {
+      "finish_reason": "stop",
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "Hello! How can I assist you today?",
+        "tool_calls": null,
+        "function_call": null,
+        "annotations": []
+      }
+    }
+  ],
+  "usage": {
+    "completion_tokens": 9,
+    "prompt_tokens": 13,
+    "total_tokens": 22,
+    "completion_tokens_details": {
+      "accepted_prediction_tokens": 0,
+      "audio_tokens": 0,
+      "reasoning_tokens": 0,
+      "rejected_prediction_tokens": 0
+    },
+    "prompt_tokens_details": {
+      "audio_tokens": 0,
+      "cached_tokens": 0
+    }
+  },
+  "service_tier": "default"
+}
+```
+
+`id`, `created`, the resolved model version, token counts, and message text will vary by request. Other providers may return a smaller or slightly different set of fields, but `choices[0].message.content` is the main field to read.
+
+## 7. Add Keys And The UI
+
+If you need virtual keys, spend tracking, or the admin UI, add a database next.
+
+- Add `database_url` under `general_settings`
+- Use [Virtual keys](/docs/proxy/virtual_keys) for key creation and budgets
+- Use [Admin UI](/docs/proxy/ui) to manage models and keys
+- Use the [Docker + Database tutorial](/docs/proxy/docker_quick_start) if you want a fuller setup
+
+## 8. Pick Your Next Step
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "🖥️",
+    title: "Make LLM Requests",
+    description: "Point LiteLLM or OpenAI-compatible clients to the gateway.",
+    to: "/docs/proxy/user_keys",
+  },
+  {
+    icon: "🎛️",
+    title: "Model Config",
+    description: "Add more models and gateway settings.",
+    to: "/docs/proxy/configs",
+  },
+  {
+    icon: "🔑",
+    title: "Virtual Keys",
+    description: "Create keys, budgets, and access controls.",
+    to: "/docs/proxy/virtual_keys",
+  },
+  {
+    icon: "📈",
+    title: "Add Logging",
+    description: "Capture logs, spend, and traces.",
+    to: "/docs/proxy/logging",
+  },
+  {
+    icon: "🔀",
+    title: "Load Balance",
+    description: "Route across deployments, regions, or providers.",
+    to: "/docs/proxy/load_balancing",
+  },
+  {
+    icon: "🛡️",
+    title: "Add Guardrails",
+    description: "Add safety checks and policy enforcement.",
+    to: "/docs/proxy/guardrails/quick_start",
+  },
+  {
+    icon: "📊",
+    title: "Reliability",
+    description: "Configure retries, fallbacks, and timeouts.",
+    to: "/docs/proxy/reliability",
+  },
+]}
+/>
+
+## When To Use The SDK Path Instead
+
+If you only need to call models from one application and do not need centralized auth or shared infrastructure, start with the [SDK Quickstart](/docs/learn/sdk_quickstart) instead.

docs/my-website/docs/learn/index.md

@@ -0,0 +1,117 @@
+---
+title: Learn LiteLLM
+sidebar_label: Learn
+slug: /learn
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+LiteLLM gives you one OpenAI-compatible interface for 100+ LLM providers. Start with the path that matches your setup.
+
+---
+
+## Start Here
+
+Pick one path first.
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "🐍",
+    title: "SDK Quickstart",
+    description: "Use LiteLLM directly in application code.",
+    listDescription: [
+      "Install",
+      "First request",
+      "Next SDK features",
+    ],
+    to: "/docs/learn/sdk_quickstart",
+  },
+  {
+    icon: "🖥️",
+    title: "Gateway Quickstart",
+    description: "Run LiteLLM as a shared gateway.",
+    listDescription: [
+      "Start proxy",
+      "Add models and keys",
+      "Connect clients",
+    ],
+    to: "/docs/learn/gateway_quickstart",
+  },
+]}
+/>
+
+---
+
+## Common Tasks
+
+Jump to a specific task.
+
+<NavigationCards
+columns={3}
+items={[
+  {
+    icon: "⚡",
+    title: "Stream Responses",
+    description: "Return tokens as they are generated.",
+    to: "/docs/guides/core_request_response_patterns",
+  },
+  {
+    icon: "🧰",
+    title: "Use Tools",
+    description: "Add function calling to your app.",
+    to: "/docs/guides/tools_integrations",
+  },
+  {
+    icon: "🔀",
+    title: "Add Routing",
+    description: "Retries, fallbacks, and load balancing.",
+    to: "/docs/routing-load-balancing",
+  },
+  {
+    icon: "🔑",
+    title: "Set Up Keys",
+    description: "Gateway auth, virtual keys, and access control.",
+    to: "/docs/proxy/virtual_keys",
+  },
+  {
+    icon: "📈",
+    title: "Add Logging",
+    description: "Capture request logs and spend data.",
+    to: "/docs/proxy/logging",
+  },
+  {
+    icon: "🌐",
+    title: "Choose A Provider",
+    description: "Find provider-specific auth and params.",
+    to: "/docs/providers",
+  },
+]}
+/>
+
+---
+
+## Docs Map
+
+Use these when you already know the type of doc you want.
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "📚",
+    title: "Guides",
+    description: "Feature reference.",
+    to: "/docs/guides",
+  },
+  {
+    icon: "🛠️",
+    title: "Tutorials",
+    description: "Step-by-step integrations.",
+    to: "/docs/tutorials",
+  },
+]}
+/>
+
+Not sure where to start? Use [SDK Quickstart](/docs/learn/sdk_quickstart) for app code or [Gateway Quickstart](/docs/learn/gateway_quickstart) for shared infrastructure.

docs/my-website/docs/learn/sdk_quickstart.md

@@ -0,0 +1,174 @@
+---
+title: SDK Quickstart
+sidebar_label: SDK Quickstart
+description: Make your first LiteLLM SDK call, then jump to the right docs for the next feature you need.
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+Use this path if you are integrating LiteLLM directly into application code.
+
+## 1. Install LiteLLM
+
+```bash
+pip install litellm
+```
+
+## 2. Set Provider Credentials
+
+Start with one provider and set its environment variables.
+
+- OpenAI: `OPENAI_API_KEY`
+- Anthropic: `ANTHROPIC_API_KEY`
+- Azure OpenAI: `AZURE_API_KEY`, `AZURE_API_BASE`, `AZURE_API_VERSION`
+- Bedrock: standard AWS credentials
+- Vertex AI: `VERTEXAI_PROJECT`, `VERTEXAI_LOCATION`
+
+If you have not picked a provider yet, browse [all supported providers](/docs/providers).
+
+## 3. Make Your First Call
+
+```python
+from litellm import completion
+import os
+
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+response = completion(
+    model="openai/gpt-4o",
+    messages=[{"role": "user", "content": "Hello, how are you?"}],
+)
+
+print(response.choices[0].message.content)
+```
+
+## 4. Check The Response
+
+The line below:
+
+```python
+print(response.choices[0].message.content)
+```
+
+prints the assistant text, for example:
+
+```text
+Hello! I'm doing well, thanks for asking.
+```
+
+If you print the full object with:
+
+```python
+print(response)
+```
+
+you will see a Python `ModelResponse(...)` object. For an OpenAI-backed model, it can look like this:
+
+```python
+ModelResponse(
+    id='chatcmpl-abc123',
+    created=1773782130,
+    model='gpt-4o-2024-08-06',
+    object='chat.completion',
+    system_fingerprint='fp_4ff89bf575',
+    choices=[
+        Choices(
+            finish_reason='stop',
+            index=0,
+            message=Message(
+                content="Hello! I'm just a program, but I'm here to help you. How can I assist you today?",
+                role='assistant',
+                tool_calls=None,
+                function_call=None,
+                provider_specific_fields={'refusal': None},
+                annotations=[]
+            ),
+            provider_specific_fields={}
+        )
+    ],
+    usage=Usage(
+        completion_tokens=21,
+        prompt_tokens=13,
+        total_tokens=34,
+        completion_tokens_details=CompletionTokensDetailsWrapper(...),
+        prompt_tokens_details=PromptTokensDetailsWrapper(...)
+    ),
+    service_tier='default'
+)
+```
+
+The same response follows an OpenAI-style shape. Conceptually, it looks like this:
+
+```json
+{
+  "id": "chatcmpl-abc123",
+  "object": "chat.completion",
+  "created": 1677858242,
+  "model": "gpt-4o",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "Hello! I'm doing well, thanks for asking."
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 13,
+    "completion_tokens": 12,
+    "total_tokens": 25
+  }
+}
+```
+
+`id`, `created`, token counts, and message text will vary by request.
+
+If you call an OpenAI-backed model, you may also see extra fields such as `system_fingerprint`, `service_tier`, `tool_calls`, `function_call`, `annotations`, `provider_specific_fields`, and detailed token usage. For the full output reference, see [completion output](/docs/completion/output).
+
+Need more provider examples? See the main [Getting Started](/docs/#quick-start) page.
+
+## 5. Pick Your Next Step
+
+<NavigationCards
+columns={3}
+items={[
+{
+icon: "⚡",
+title: "Stream Responses",
+description: "Receive tokens incrementally with stream=True.",
+to: "/docs/completion/stream",
+},
+{
+icon: "🧰",
+title: "Use Tools",
+description: "Add function calling in a provider-agnostic way.",
+to: "/docs/completion/function_call",
+},
+{
+icon: "📦",
+title: "Return JSON",
+description: "Constrain responses to structured JSON output.",
+to: "/docs/completion/json_mode",
+},
+{
+icon: "🔀",
+title: "Add Routing",
+description: "Use retries, fallbacks, and load balancing in app code.",
+to: "/docs/routing",
+},
+{
+icon: "🌐",
+title: "Choose A Provider",
+description: "Find provider-specific auth, model naming, and params.",
+to: "/docs/providers",
+},
+]}
+/>
+
+## When To Use Gateway Instead
+
+Use LiteLLM Gateway if you need centralized auth, virtual keys, spend tracking, shared logging, or one OpenAI-compatible endpoint for multiple apps.
+
+[Go to Gateway Quickstart →](/docs/learn/gateway_quickstart)

docs/my-website/docs/load_test_advanced.md

@@ -11,7 +11,7 @@ Tutorial on how to get to 1K+ RPS with LiteLLM Proxy on locust
     - [Github releases](https://github.com/BerriAI/litellm/releases)
     - [litellm docker containers](https://github.com/BerriAI/litellm/pkgs/container/litellm)
     - [litellm database docker container](https://github.com/BerriAI/litellm/pkgs/container/litellm-database)
-- [ ] Ensure you're following **ALL** [best practices for production](./proxy/production_setup.md)
+- [ ] Ensure you're following **ALL** [best practices for production](./proxy/prod.md)
 - [ ] Locust - Ensure you're Locust instance can create 1K+ requests per second
     - 👉 You can use our **[maintained locust instance here](https://locust-load-tester-production.up.railway.app/)**
     - If you're self hosting locust
@@ -222,4 +222,4 @@ class MyUser(HttpUser):
     def on_start(self):
         self.api_key = os.getenv('API_KEY', 'sk-1234')
         self.client.headers.update({'Authorization': f'Bearer {self.api_key}'})
-```
+```

docs/my-website/docs/mcp_zero_trust.md

@@ -0,0 +1,294 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# MCP Zero Trust Auth (JWT Signer)
+
+![Zero Trust MCP Gateway](/img/mcp_zero_trust_gateway.png)
+
+MCP servers have no built-in way to verify that a request actually came through LiteLLM. Without this guardrail, any client that can reach your MCP server directly can call tools — bypassing your access controls entirely.
+
+`MCPJWTSigner` fixes this. It signs every outbound tool call with a short-lived RS256 JWT. Your MCP server verifies the signature against LiteLLM's public key. Requests that didn't go through LiteLLM have no valid signature and are rejected.
+
+---
+
+## Basic setup
+
+Add the guardrail to your config and point your MCP server at LiteLLM's JWKS endpoint. Every tool call gets a signed JWT automatically — no changes needed on the client side.
+
+```yaml title="config.yaml"
+mcp_servers:
+  - server_name: weather
+    url: http://localhost:8000/mcp
+    transport: http
+
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+      issuer: "https://my-litellm.example.com"  # defaults to request base URL
+      audience: "mcp"                            # default: "mcp"
+      ttl_seconds: 300                           # default: 300
+```
+
+**Bring your own signing key** — recommended for production. Auto-generated keys are lost on restart.
+
+```bash
+export MCP_JWT_SIGNING_KEY="-----BEGIN RSA PRIVATE KEY-----\n..."
+# or point to a file
+export MCP_JWT_SIGNING_KEY="file:///secrets/mcp-signing-key.pem"
+```
+
+**Build a verified MCP server with [FastMCP](https://gofastmcp.com):**
+
+```python title="weather_server.py"
+from fastmcp import FastMCP, Context
+from fastmcp.server.auth.providers.jwt import JWTVerifier
+
+auth = JWTVerifier(
+    jwks_uri="https://my-litellm.example.com/.well-known/jwks.json",
+    issuer="https://my-litellm.example.com",
+    audience="mcp",
+    algorithm="RS256",
+)
+
+mcp = FastMCP("weather-server", auth=auth)
+
+@mcp.tool()
+async def get_weather(city: str, ctx: Context) -> str:
+    caller = ctx.client_id  # JWT `sub` — the verified user identity
+    return f"Weather in {city}: sunny, 72°F (requested by {caller})"
+
+if __name__ == "__main__":
+    mcp.run(transport="http", host="0.0.0.0", port=8000)
+```
+
+FastMCP fetches the JWKS automatically and re-fetches when the signing key changes.
+
+LiteLLM publishes OIDC discovery so MCP servers find the key without any manual configuration:
+
+```
+GET /.well-known/openid-configuration  →  { "jwks_uri": "https://<litellm>/.well-known/jwks.json" }
+GET /.well-known/jwks.json             →  { "keys": [{ "kty": "RSA", "alg": "RS256", ... }] }
+```
+
+> **Read further only if you need to:** thread a corporate IdP identity into the JWT, enforce specific claims on callers, add custom metadata, use AWS Bedrock AgentCore Gateway, or debug JWT rejections.
+
+---
+
+## Thread IdP identity into MCP JWTs
+
+By default the outbound JWT `sub` is LiteLLM's internal `user_id`. If your users authenticate with Okta, Azure AD, or another IdP, the MCP server sees a LiteLLM-internal ID — not the user's email or employee ID.
+
+With verify+re-sign, LiteLLM validates the incoming IdP token first, then builds the outbound JWT using the real identity claims from that token. The MCP server gets the user's actual identity without ever having to trust the original IdP directly.
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+      issuer: "https://my-litellm.example.com"
+
+      # Validate the incoming Bearer token against the IdP
+      access_token_discovery_uri: "https://login.microsoftonline.com/{tenant}/v2.0/.well-known/openid-configuration"
+      verify_issuer: "https://login.microsoftonline.com/{tenant}/v2.0"
+      verify_audience: "api://my-app"
+
+      # Which claim to use for `sub` in the outbound JWT — first non-empty value wins
+      end_user_claim_sources:
+        - "token:sub"       # from the verified incoming JWT
+        - "token:email"     # fallback to email
+        - "litellm:user_id" # last resort: LiteLLM's internal user_id
+```
+
+If the incoming token is **opaque** (not a JWT — some IdPs issue these), add an introspection endpoint. LiteLLM will POST the token to it (RFC 7662) and use the returned claims:
+
+```yaml
+      token_introspection_endpoint: "https://idp.example.com/oauth2/introspect"
+```
+
+**Supported `end_user_claim_sources` values:**
+
+| Source | Resolves to |
+|--------|-------------|
+| `token:<claim>` | Any claim from the verified incoming JWT (e.g. `token:sub`, `token:email`, `token:oid`) |
+| `litellm:user_id` | LiteLLM's internal user ID |
+| `litellm:email` | User email from LiteLLM auth context |
+| `litellm:end_user_id` | End-user ID if set separately |
+| `litellm:team_id` | Team ID from LiteLLM auth context |
+
+---
+
+## Block callers missing required attributes
+
+Some MCP servers expose sensitive operations that should only be reachable by verified employees — not service accounts, not external API keys. You can enforce this at the LiteLLM layer so the MCP server never receives the request at all.
+
+`required_claims` rejects with `403` if the incoming token is missing any listed claim. `optional_claims` forwards claims that are useful but not mandatory.
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+
+      access_token_discovery_uri: "https://idp.example.com/.well-known/openid-configuration"
+
+      # Service accounts without `employee_id` are blocked before the tool runs
+      required_claims:
+        - "sub"
+        - "employee_id"
+
+      # Forward these into the outbound JWT when present — skipped silently if absent
+      optional_claims:
+        - "groups"
+        - "department"
+```
+
+**What the client sees when blocked:**
+```json
+HTTP 403
+{ "error": "MCPJWTSigner: incoming token is missing required claims: ['employee_id']. Configure the IdP to include these claims." }
+```
+
+---
+
+## Add custom metadata to every JWT
+
+Your MCP server may need context that LiteLLM doesn't carry natively — which deployment sent the request, a tenant ID, an environment tag. Use claim operations to inject, override, or strip claims from the outbound JWT.
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+
+      # add: insert only when the key is not already in the JWT
+      add_claims:
+        deployment_id: "prod-us-east-1"
+        tenant_id: "acme-corp"
+
+      # set: always override — even if the claim came from the incoming token
+      set_claims:
+        env: "production"
+
+      # remove: strip claims the MCP server shouldn't see
+      remove_claims:
+        - "nbf"   # some validators reject nbf; remove it if yours does
+```
+
+Operations run in order — `add_claims` → `set_claims` → `remove_claims`. `set_claims` always wins over `add_claims`; `remove_claims` beats both.
+
+---
+
+## AWS Bedrock AgentCore Gateway
+
+Bedrock AgentCore Gateway uses two separate JWTs: one to authenticate the transport connection and another to authorize tool calls. They need different `aud` values and TTLs — a single JWT won't work for both.
+
+LiteLLM can issue both in one hook and inject them into separate headers:
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+      issuer: "https://my-litellm.example.com"
+      audience: "mcp-resource"   # for the MCP resource layer
+      ttl_seconds: 300
+
+      # Second JWT for the transport channel — same sub/act/scope, different aud + TTL
+      channel_token_audience: "bedrock-agentcore-gateway"
+      channel_token_ttl: 60      # transport tokens should be short-lived
+```
+
+LiteLLM injects two headers on every tool call:
+- `Authorization: Bearer <resource-token>` — audience `mcp-resource`, TTL 300s
+- `x-mcp-channel-token: Bearer <channel-token>` — audience `bedrock-agentcore-gateway`, TTL 60s
+
+Both tokens are signed with the same LiteLLM key, so your MCP server only needs to trust one JWKS endpoint.
+
+---
+
+## Control which scopes go into the JWT
+
+By default LiteLLM generates least-privilege scopes per request:
+- Tool call → `mcp:tools/call mcp:tools/{name}:call`
+- List tools → `mcp:tools/call mcp:tools/list`
+
+If your MCP server does its own scope enforcement and needs a specific format, set `allowed_scopes` to replace auto-generation entirely:
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+
+      allowed_scopes:
+        - "mcp:tools/call"
+        - "mcp:tools/list"
+        - "mcp:admin"
+```
+
+Every JWT carries exactly those scopes regardless of which tool is being called.
+
+---
+
+## Debug JWT rejections
+
+Your MCP server is returning 401 and you're not sure what's in the JWT. Enable `debug_headers` and LiteLLM adds a `x-litellm-mcp-debug` response header with the key claims that were signed:
+
+```yaml title="config.yaml"
+guardrails:
+  - guardrail_name: mcp-jwt-signer
+    litellm_params:
+      guardrail: mcp_jwt_signer
+      mode: pre_mcp_call
+      default_on: true
+      debug_headers: true
+```
+
+Response header:
+```
+x-litellm-mcp-debug: v=1; kid=a3f1b2c4d5e6f708; sub=alice@corp.com; iss=https://my-litellm.example.com; exp=1712345678; scope=mcp:tools/call mcp:tools/get_weather:call
+```
+
+Check that `kid` matches what the MCP server fetched from JWKS, `iss`/`aud` match your server's expected values, and `exp` hasn't passed. Disable in production — the header leaks claim metadata.
+
+---
+
+## JWT claims reference
+
+| Claim | Value |
+|-------|-------|
+| `iss` | `issuer` config value (or request base URL) |
+| `aud` | `audience` config value (default: `"mcp"`) |
+| `sub` | Resolved via `end_user_claim_sources` (default: `user_id` → api-key hash → `"litellm-proxy"`) |
+| `act.sub` | `team_id` → `org_id` → `"litellm-proxy"` (RFC 8693 delegation) |
+| `email` | `user_email` from LiteLLM auth context (when available) |
+| `scope` | Auto-generated per tool call, or `allowed_scopes` when set |
+| `iat`, `exp`, `nbf` | Standard timing claims (RFC 7519) |
+
+---
+
+## Limitations
+
+- **OpenAPI-backed MCP servers** (`spec_path` set) do not support JWT injection. LiteLLM logs a warning and skips the header. Use SSE/HTTP transport servers to get full JWT injection.
+- The keypair is **in-memory by default** and rotated on each restart unless `MCP_JWT_SIGNING_KEY` is set. FastMCP's `JWTVerifier` handles key rotation transparently via JWKS key ID matching.
+
+---
+
+## Related
+
+- [MCP Guardrails](./mcp_guardrail) — PII masking and blocking for MCP calls
+- [MCP OAuth](./mcp_oauth) — upstream OAuth2 for MCP server access
+- [MCP AWS SigV4](./mcp_aws_sigv4) — AWS-signed requests to MCP servers

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

@@ -83,6 +83,9 @@ os.environ["LANGFUSE_OTEL_HOST"] = "https://cloud.langfuse.com"  # EU region
 # Or use self-hosted instance
 # os.environ["LANGFUSE_OTEL_HOST"] = "https://my-langfuse.company.com"
 
+# Optional: Ignore otel context propagation to prevent parent-child relationships with spans from other providers
+# os.environ["OTEL_IGNORE_CONTEXT_PROPAGATION"] = "true"
+
 litellm.callbacks = ["langfuse_otel"]
 ```
 
@@ -124,6 +127,9 @@ export LANGFUSE_PUBLIC_KEY="pk-lf-..."
 export LANGFUSE_SECRET_KEY="sk-lf-..."
 export LANGFUSE_OTEL_HOST="https://us.cloud.langfuse.com"  # Default US region
 # export LANGFUSE_OTEL_HOST="https://otel.my-langfuse.company.com"  # custom OTEL endpoint
+
+# Optional: Ignore otel context propagation to prevent parent-child relationships with spans from other providers
+# export OTEL_IGNORE_CONTEXT_PROPAGATION="true"
 ```
 
 2. Setup config.yaml

docs/my-website/docs/prompt_management.md

@@ -0,0 +1,48 @@
+---
+title: Prompt Management with Responses API
+---
+
+# Prompt Management with Responses API
+
+Use LiteLLM Prompt Management with `/v1/responses` by passing `prompt_id` and optional `prompt_variables`.
+
+## Basic Usage
+
+```bash
+curl -X POST "http://localhost:4000/v1/responses" \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-4o",
+    "prompt_id": "my-responses-prompt",
+    "prompt_variables": {"topic": "large language models"},
+    "input": []
+  }'
+```
+
+## Multi-turn Follow-up in `input`
+
+To send follow-up turns in one request, pass message history in `input`.
+
+```bash
+curl -X POST "http://localhost:4000/v1/responses" \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-4o",
+    "prompt_id": "my-responses-prompt",
+    "prompt_variables": {"topic": "large language models"},
+    "input": [
+      {"role": "user", "content": "Topic is LLMs. Start short."},
+      {"role": "assistant", "content": "Sure, go ahead."},
+      {"role": "user", "content": "Now give me 3 bullets and include pricing caveat."}
+    ]
+  }'
+```
+
+## Notes
+
+- Prompt template messages are merged with your `input` messages.
+- Prompt variable substitution applies to prompt message content.
+- Tool call payload fields are not substituted by prompt variables.
+- For follow-ups with `previous_response_id`, include `prompt_id` again if you want prompt management applied on that turn.

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

@@ -1032,7 +1032,7 @@ print("list_batches_response=", list_batches_response)
 </TabItem>
 </Tabs>
 
-### [Health Check Azure Batch models](./proxy/health.md#batch-models-azure-only)
+### [Health Check Azure Batch models](../../proxy/health.md#batch-models-azure-only)
 
 
 ### [BETA] Loadbalance Multiple Azure Deployments 

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

@@ -372,7 +372,6 @@ response = completion(
 
 ## Related Documentation
 
-- [Anthropic Provider Documentation](./anthropic.md) - For standard Anthropic API usage
+- [Anthropic Provider Documentation](../anthropic.md) - For standard Anthropic API usage
 - [Azure OpenAI Documentation](./azure.md) - For Azure OpenAI models
-- [Azure Authentication Guide](../secret_managers/azure_key_vault.md) - For Azure AD token setup
-
+- [Azure Authentication Guide](../../secret_managers/azure_key_vault.md) - For Azure AD token setup

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

@@ -54,6 +54,7 @@ response = completion(
 - stream
 - tools
 - tool_choice
+- include_server_side_tool_invocations
 - functions
 - response_format
 - n
@@ -856,7 +857,112 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 </TabItem>
 </Tabs>
 
-### URL Context 
+### Context Circulation (Server-Side Tool Combination)
+
+Context circulation allows Gemini 3+ models to combine **built-in tools** (like Google Search) with **your custom functions** in the same request. Without it, Gemini returns an error if you try to use both.
+
+When enabled, Gemini can execute Google Search server-side, use those results to decide whether to call your custom functions, and return the full chain of reasoning.
+
+**How it works:**
+1. You pass `include_server_side_tool_invocations=True` along with both Google Search and your function tools
+2. Gemini executes server-side tools internally and returns `toolCall`/`toolResponse` parts alongside any `functionCall` parts
+3. LiteLLM extracts the server-side invocations into `provider_specific_fields["server_side_tool_invocations"]`
+4. On subsequent turns, include the full assistant message in your conversation history — LiteLLM re-injects the server-side parts automatically
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+response = completion(
+    model="gemini/gemini-3-flash-preview",
+    messages=[{"role": "user", "content": "What's the weather in Buenos Aires? If it's raining, schedule a meeting."}],
+    tools=[
+        {"type": "web_search_preview"},  # Google Search (server-side)
+        {
+            "type": "function",
+            "function": {
+                "name": "schedule_meeting",
+                "description": "Schedule a meeting",
+                "parameters": {
+                    "type": "object",
+                    "properties": {"reason": {"type": "string"}},
+                    "required": ["reason"],
+                },
+            },
+        },
+    ],
+    include_server_side_tool_invocations=True,
+)
+
+msg = response.choices[0].message
+
+# Server-side tool results are in provider_specific_fields
+psf = msg.provider_specific_fields or {}
+for invocation in psf.get("server_side_tool_invocations", []):
+    print(invocation["tool_type"])  # e.g. "GOOGLE_SEARCH_WEB"
+    print(invocation["id"])
+    print(invocation["args"])       # e.g. {"queries": ["weather Buenos Aires"]}
+    print(invocation["response"])   # Search results from Google
+
+# For multi-turn: just append the full message to history
+messages.append(msg)
+messages.append({"role": "user", "content": "Thanks!"})
+# LiteLLM automatically re-injects the server-side parts + thought signatures
+response2 = completion(
+    model="gemini/gemini-3-flash-preview",
+    messages=messages,
+    tools=tools,
+    include_server_side_tool_invocations=True,
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Setup config.yaml
+```yaml
+model_list:
+  - model_name: gemini-3-flash
+    litellm_params:
+      model: gemini/gemini-3-flash-preview
+      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-3-flash",
+  "messages": [{"role": "user", "content": "What is the weather in Buenos Aires?"}],
+  "tools": [
+    {"type": "web_search_preview"},
+    {"type": "function", "function": {"name": "schedule_meeting", "description": "Schedule a meeting", "parameters": {"type": "object", "properties": {"reason": {"type": "string"}}}}}
+  ],
+  "include_server_side_tool_invocations": true
+}'
+```
+
+</TabItem>
+</Tabs>
+
+:::info
+
+- Context circulation requires **Gemini 3+** models
+- Server-side tool invocations (`toolCall`/`toolResponse`) are **not** included in `tool_calls` — they are in `provider_specific_fields["server_side_tool_invocations"]` because they were already executed by Google, not by your code
+- `thought_signatures` are automatically preserved alongside server-side invocations for multi-turn coherence
+
+:::
+
+### URL Context
 
 <Tabs>
 <TabItem value="sdk" label="SDK">

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

@@ -1153,4 +1153,4 @@ response = completion(
 
 LiteLLM supports OpenAI's video generation models including Sora.
 
-For detailed documentation on video generation, see [OpenAI Video Generation →](./openai/video_generation.md)
+For detailed documentation on video generation, see [OpenAI Video Generation →](./openai/videos.md)

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

@@ -7,7 +7,7 @@ import Image from '@theme/IdealImage';
 - Enforce 'user' param for all openai endpoint calls
 
 :::tip
-**Understanding Callback Hooks?** Check out our [Callback Management Guide](../observability/callback_management.md) to understand the differences between proxy-specific hooks like `async_pre_call_hook` and general logging hooks like `async_log_success_event`.
+**Understanding Callback Hooks?** Check out our [Callback Guide](../observability/callbacks.md) to understand the differences between proxy-specific hooks like `async_pre_call_hook` and general logging hooks like `async_log_success_event`.
 :::
 
 ## Which Hook Should I Use?

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

@@ -206,7 +206,7 @@ router_settings:
 
 | Name | Type | Description |
 |------|------|-------------|
-| completion_model | string | The default model to use for completions when `model` is not specified in the request |
+| completion_model | string | The model to use for all completions, overriding any `model` 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) |
@@ -361,10 +361,11 @@ router_settings:
 | redis_url | str | URL for Redis server. **Known performance issue with Redis URL.** |
 | cache_responses | boolean | Flag to enable caching LLM Responses, if cache set under `router_settings`. If true, caches responses. Defaults to False. |
 | router_general_settings | RouterGeneralSettings | [SDK-Only] Router general settings - contains optimizations like 'async_only_mode'. [Docs](../routing.md#router-general-settings) |
-| optional_pre_call_checks | List[str] | List of pre-call checks to add to the router. Supported: `router_budget_limiting`, `prompt_caching`, `responses_api_deployment_check`, `encrypted_content_affinity`, `deployment_affinity`, `session_affinity`, `forward_client_headers_by_model_group` |
+| optional_pre_call_checks | List[str] | List of pre-call checks to add to the router. Supported: `router_budget_limiting`, `prompt_caching`, `responses_api_deployment_check`, `encrypted_content_affinity` (requires LiteLLM >= 1.82.3), `deployment_affinity`, `session_affinity`, `forward_client_headers_by_model_group` |
 | deployment_affinity_ttl_seconds | int | TTL (seconds) for user-key → deployment affinity mapping when `deployment_affinity` is enabled (configured at Router init / proxy startup). Defaults to `3600` (1 hour). |
+| model_group_affinity_config | Dict[str, List[str]] | Per-model-group affinity flags. Keys are model group names; values are lists of checks to enable (`deployment_affinity`, `responses_api_deployment_check`, `session_affinity`). Groups not listed fall back to the global `optional_pre_call_checks`. [Docs](../response_api.md#per-model-group-affinity-configuration) |
 | ignore_invalid_deployments | boolean | If true, ignores invalid deployments. Default for proxy is True - to prevent invalid models from blocking other models from being loaded. |
-| search_tools | List[SearchToolTypedDict] | List of search tool configurations for Search API integration. Each tool specifies a search_tool_name and litellm_params with search_provider, api_key, api_base, etc. [Further Docs](../search.md) |
+| search_tools | List[SearchToolTypedDict] | List of search tool configurations for Search API integration. Each tool specifies a search_tool_name and litellm_params with search_provider, api_key, api_base, etc. [Further Docs](../search/index.md) |
 | guardrail_list | List[GuardrailTypedDict] | List of guardrail configurations for guardrail load balancing. Enables load balancing across multiple guardrail deployments with the same guardrail_name. [Further Docs](./guardrails/guardrail_load_balancing.md) |
 
 
@@ -401,8 +402,10 @@ router_settings:
 | AUTH_STRATEGY | Strategy used for authentication (e.g., OAuth, API key)
 | AUTO_REDIRECT_UI_LOGIN_TO_SSO | Flag to enable automatic redirect of UI login page to SSO when SSO is configured. Default is **false**
 | AUDIO_SPEECH_CHUNK_SIZE | Chunk size for audio speech processing. Default is 1024
-| ANTHROPIC_API_KEY | API key for Anthropic service
+| ANTHROPIC_API_KEY | API key for Anthropic service. Uses `x-api-key` header for authentication.
+| ANTHROPIC_AUTH_TOKEN | Alternative auth token for Anthropic service. Uses `Authorization: Bearer` header instead of `x-api-key`. Used as fallback when `ANTHROPIC_API_KEY` is not set.
 | ANTHROPIC_API_BASE | Base URL for Anthropic API. Default is https://api.anthropic.com
+| ANTHROPIC_BASE_URL | Alternative to `ANTHROPIC_API_BASE` for setting the Anthropic API base URL. Used as fallback when `ANTHROPIC_API_BASE` is not set.
 | ANTHROPIC_TOKEN_COUNTING_BETA_VERSION | Beta version header for Anthropic token counting API. Default is `token-counting-2024-11-01`
 | AWS_ACCESS_KEY_ID | Access Key ID for AWS services
 | AWS_BATCH_ROLE_ARN | ARN of the AWS IAM role for batch operations
@@ -811,7 +814,7 @@ router_settings:
 | LITELLM_MODE | Operating mode for LiteLLM (e.g., production, development)
 | LITELLM_NON_ROOT | Flag to run LiteLLM in non-root mode for enhanced security in Docker containers
 | LITELLM_RATE_LIMIT_WINDOW_SIZE | Rate limit window size for LiteLLM. Default is 60
-| LITELLM_REASONING_AUTO_SUMMARY | If set to "true", automatically enables detailed reasoning summaries for reasoning models (e.g., o1, o3-mini, deepseek-reasoner). When enabled, adds `summary: "detailed"` to reasoning effort configurations. Default is "false"
+| LITELLM_REASONING_AUTO_SUMMARY | If set to "true", automatically enables detailed reasoning summaries (`summary: "detailed"`) for reasoning models across all translation paths (Anthropic adapter, Responses API, etc.). Default is "false"
 | LITELLM_SALT_KEY | Salt key for encryption in LiteLLM
 | LITELLM_SSL_CIPHERS | SSL/TLS cipher configuration for faster handshakes. Controls cipher suite preferences for OpenSSL connections.
 | LITELLM_SECRET_AWS_KMS_LITELLM_LICENSE | AWS KMS encrypted license for LiteLLM
@@ -902,6 +905,7 @@ router_settings:
 | OTEL_SERVICE_NAME | Service name identifier for OpenTelemetry
 | OTEL_TRACER_NAME | Tracer name for OpenTelemetry tracing
 | OTEL_LOGS_EXPORTER | Exporter type for OpenTelemetry logs (e.g., console)
+| OTEL_IGNORE_CONTEXT_PROPAGATION | When true, ignore parent span context propagation in OpenTelemetry callbacks
 | PAGERDUTY_API_KEY | API key for PagerDuty Alerting
 | PANW_PRISMA_AIRS_API_KEY | API key for PANW Prisma AIRS service
 | PANW_PRISMA_AIRS_API_BASE | Base URL for PANW Prisma AIRS service
@@ -949,6 +953,8 @@ router_settings:
 | QDRANT_URL | Connection URL for Qdrant database
 | QDRANT_VECTOR_SIZE | Vector size for Qdrant operations. Default is 1536
 | REDIS_CONNECTION_POOL_TIMEOUT | Timeout in seconds for Redis connection pool. Default is 5
+| REDIS_CIRCUIT_BREAKER_FAILURE_THRESHOLD | Number of consecutive failures before the Redis circuit breaker opens. Default is 5
+| REDIS_CIRCUIT_BREAKER_RECOVERY_TIMEOUT | Time in seconds before the Redis circuit breaker attempts recovery after opening. Default is 60
 | REDIS_CLUSTER_NODES | JSON-formatted list of Redis cluster startup nodes for Redis Cluster mode. Example: `[{"host": "node1", "port": 6379}]`
 | REDIS_HOST | Hostname for Redis server
 | REDIS_PASSWORD | Password for Redis service

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

@@ -602,6 +602,22 @@ Since you shouldn't use 12.5, round down to **10** to leave a safety buffer. Thi
 - Total maximum connections: 8 workers × 10 connections = 80 connections
 - This stays safely under your database's 100 connection limit
 
+## LiteLLM License Key (Enterprise)
+
+To enable [LiteLLM Enterprise features](https://docs.litellm.ai/docs/proxy/enterprise), set your license key as an environment variable:
+
+```bash
+export LITELLM_LICENSE="eyJ..."
+```
+
+The license key is a JWT token provided when you purchase a LiteLLM Enterprise license. Once set, LiteLLM will automatically detect and activate enterprise features.
+
+You can also add it to your `.env` file:
+
+```env
+LITELLM_LICENSE="eyJ..."
+```
+
 ## Extras
 
 

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

@@ -1,25 +1,90 @@
-
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
+import Image from '@theme/IdealImage';
 
 # Getting Started Tutorial
 
 End-to-End tutorial for LiteLLM Proxy to:
-- Add an Azure OpenAI model 
-- Make a successful /chat/completion call 
-- Generate a virtual key 
-- Set RPM limit on virtual key 
+- Add an Azure OpenAI model
+- Make a successful /chat/completion call
+- Generate a virtual key
+- Set RPM limit on virtual key
 
+## Quick Install (Recommended for local / beginners)
+
+New to LiteLLM? This is the easiest way to get started locally. One command installs LiteLLM and walks you through setup interactively — no config files to write by hand.
+
+### 1. Install
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh
+```
+
+This detects your OS, installs `litellm[proxy]`, and drops you straight into the setup wizard.
+
+### 2. Follow the wizard
+
+```
+$ litellm --setup
+
+  Welcome to LiteLLM
+
+  Choose your LLM providers
+  ○ 1. OpenAI        GPT-4o, GPT-4o-mini, o1
+  ○ 2. Anthropic     Claude Opus, Sonnet, Haiku
+  ○ 3. Azure OpenAI  GPT-4o via Azure
+  ○ 4. Google Gemini Gemini 2.0 Flash, 1.5 Pro
+  ○ 5. AWS Bedrock   Claude, Llama via AWS
+  ○ 6. Ollama        Local models
+
+  ❯ Provider(s): 1,2
+
+  ❯ OpenAI API key: sk-...
+  ❯ Anthropic API key: sk-ant-...
+
+  ❯ Port [4000]:
+  ❯ Master key [auto-generate]:
+
+  ✔ Config saved → ./litellm_config.yaml
+
+  ❯ Start the proxy now? (Y/n):
+```
+
+The wizard walks you through:
+1. Pick your LLM providers (OpenAI, Anthropic, Azure, Bedrock, Gemini, Ollama)
+2. Enter API keys for each provider
+3. Set a port and master key (or accept the defaults)
+4. Config is saved to `./litellm_config.yaml` and the proxy starts immediately
+
+### 3. Make a call
+
+Your proxy is running on `http://0.0.0.0:4000`. Test it:
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer <your-master-key>' \
+-d '{
+    "model": "gpt-4o",
+    "messages": [{"role": "user", "content": "Hello!"}]
+}'
+```
+
+:::tip Already have pip installed?
+You can skip the curl install and run `litellm --setup` directly after `pip install 'litellm[proxy]'`.
+:::
+
+---
 
 ## Pre-Requisites 
 
-- Install LiteLLM Docker Image **OR** LiteLLM CLI (pip package)
+Choose your install method. **Docker Compose** users complete their full setup inside the tab and are done. **Docker** and **pip** users continue with the steps below the tabs.
 
 <Tabs>
 
 <TabItem value="docker" label="Docker">
 
-```
+```bash
 docker pull docker.litellm.ai/berriai/litellm:main-latest
 ```
 
@@ -37,7 +102,25 @@ $ pip install 'litellm[proxy]'
 
 <TabItem value="docker-compose" label="Docker Compose (Proxy + DB)">
 
-Use this docker compose to spin up the proxy with a postgres database running locally. 
+Docker Compose bundles LiteLLM with a Postgres database. Follow the steps below — the proxy will be fully running by the end.
+
+### Step 1 — Pull the LiteLLM database image
+
+LiteLLM provides a dedicated `litellm-database` image for proxy deployments that connect to Postgres.
+
+```bash
+docker pull ghcr.io/berriai/litellm-database:main-latest
+```
+
+See all available tags on the [GitHub Container Registry](https://github.com/BerriAI/litellm/pkgs/container/litellm-database).
+
+---
+
+### Step 2 — Set up a database
+
+Complete all three config files **before** running `docker compose up`. The proxy server will not start correctly if any of these are missing.
+
+#### 2.1 — Get `docker-compose.yml` and create `.env`
 
 ```bash
 # Get the docker compose file
@@ -46,26 +129,154 @@ curl -O https://raw.githubusercontent.com/BerriAI/litellm/main/docker-compose.ym
 # Add the master key - you can change this after setup
 echo 'LITELLM_MASTER_KEY="sk-1234"' > .env
 
-# Add the litellm salt key - you cannot change this after adding a model
-# It is used to encrypt / decrypt your LLM API Key credentials
-# We recommend - https://1password.com/password-generator/ 
-# password generator to get a random hash for litellm salt key
+# Add the litellm salt key — cannot be changed after adding a model
+# Used to encrypt/decrypt your LLM API key credentials
+# Generate a strong random value: https://1password.com/password-generator/
 echo 'LITELLM_SALT_KEY="sk-1234"' >> .env
 
-# Start
+# Add your model credentials
+echo 'AZURE_API_BASE="https://openai-***********/"' >> .env
+echo 'AZURE_API_KEY="your-azure-api-key"' >> .env
+```
+
+#### 2.2 — Create `config.yaml`
+
+The default `docker-compose.yml` starts a Postgres container at `db:5432`. Your `config.yaml` must include `database_url` pointing to it:
+
+```yaml
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: azure/my_azure_deployment
+      api_base: os.environ/AZURE_API_BASE
+      api_key: os.environ/AZURE_API_KEY
+      api_version: "2025-01-01-preview"
+
+general_settings:
+  master_key: sk-1234 # 🔑 your proxy admin key (must start with sk-)
+  database_url: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
+```
+
+:::tip
+`database_url` enables virtual keys, spend tracking, and the UI. Replace it with your [Supabase](https://supabase.com/) or [Neon](https://neon.tech/) connection string if you prefer a managed database.
+:::
+
+#### 2.3 — Create `prometheus.yml`
+
+This file **must exist as a file** before `docker compose up`. If it is missing, Docker auto-creates it as an empty directory and the Prometheus container fails to start.
+
+```yaml
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: "litellm"
+    static_configs:
+      - targets: ["litellm:4000"]
+```
+
+Also verify that the `config.yaml` volume mount and `--config` flag are **not commented out** in `docker-compose.yml`:
+
+```yaml
+services:
+  litellm:
+    volumes:
+      - ./config.yaml:/app/config.yaml # ✅ must be uncommented
+    command:
+      - "--config=/app/config.yaml" # ✅ must be uncommented
+```
+
+:::warning
+All three files (`.env`, `config.yaml`, `prometheus.yml`) must be present before running `docker compose up`. See [Troubleshooting](#troubleshooting) if you run into issues.
+:::
+
+---
+
+### Step 3 — Start the proxy server and test it
+
+After `config.yaml`, `prometheus.yml`, and `.env` are complete, start the proxy:
+
+```bash
 docker compose up
 ```
 
+Once running, test it with a curl 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": "gpt-4o",
+    "messages": [{"role": "user", "content": "Hello!"}]
+  }'
+```
+
+**Expected response:**
+
+```json
+{
+  "id": "chatcmpl-abcd",
+  "created": 1773817678,
+  "model": "gpt-4o",
+  "object": "chat.completion",
+  "system_fingerprint": "fp_6b1ef07cda",
+  "choices": [
+    {
+      "finish_reason": "stop",
+      "index": 0,
+      "message": {
+        "content": "Hello! How can I assist you today?",
+        "role": "assistant",
+        "annotations": []
+      }
+    }
+  ],
+  "usage": {
+    "completion_tokens": 9,
+    "prompt_tokens": 9,
+    "total_tokens": 18,
+    "completion_tokens_details": {
+      "accepted_prediction_tokens": 0,
+      "audio_tokens": 0,
+      "reasoning_tokens": 0,
+      "rejected_prediction_tokens": 0
+    },
+    "prompt_tokens_details": {
+      "audio_tokens": 0,
+      "cached_tokens": 0
+    }
+  },
+  "service_tier": "default"
+}
+```
+
+---
+
+### Optional — Navigate to the LiteLLM UI and generate a virtual key
+
+Open [http://localhost:4000/ui](http://localhost:4000/ui) in your browser and log in with your master key (`sk-1234`).
+
+Navigate to **Virtual Keys** and click **+ Create New Key**:
+
+<Image img={require('../../img/litellm_ui_create_key.png')} alt="LiteLLM UI — Create Virtual Key" />
+
+Virtual keys let you track spend, set rate limits, and control model access per user or team.
+
 </TabItem>
+
 </Tabs>
 
-## 1. Add a model 
+:::note Docker Compose users
+Your setup is complete — the steps below are for **Docker** and **pip** users only.
+:::
 
-Control LiteLLM Proxy with a config.yaml file.
+---
 
-Setup your config.yaml with your azure model.
+## Step 1 — Add a model
 
-Note: When using the proxy with a database, you can also **just add models via UI** (UI is available on `/ui` route).
+Control LiteLLM Proxy with a `config.yaml` file. Create one with your Azure model:
 
 ```yaml
 model_list:
@@ -89,8 +300,6 @@ You can read more about how model resolution works in the [Model Configuration](
     - **`api_base`** (`str`) - The API base for your azure deployment.
     - **`api_version`** (`str`) - The API Version to use when calling Azure's OpenAI API. Get the latest Inference API version [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/api-version-deprecation?source=recommendations#latest-preview-api-releases).
 
----
-
 
 ---
 
@@ -138,19 +347,19 @@ $ litellm --config /app/config.yaml --detailed_debug
 
 </Tabs>
 
+Confirm your config was loaded correctly — you should see this in the logs:
 
-Confirm your config.yaml got mounted correctly
-
-```bash
+```
 Loaded config YAML (api_key and environment_variables are not shown):
 {
-"model_list": [
-{
-"model_name ...
+  "model_list": [
+    {
+      "model_name": ...
 ```
 
 ### 2.2 Make Call 
 
+LiteLLM Proxy is 100% OpenAI-compatible. Test your model via `/chat/completions`:
 
 ```bash
 curl -X POST 'http://0.0.0.0:4000/chat/completions' \
@@ -244,15 +453,17 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
 - [Other/Non-Chat Completion Endpoints](../embedding/supported_embedding.md)
 - [Pass-through for VertexAI, Bedrock, etc.](../pass_through/vertex_ai.md)
 
-## 3. Generate a virtual key
+## Optional: Generate a virtual key
 
-Track Spend, and control model access via virtual keys for the proxy
+Track spend and control model access via virtual keys for the proxy.
 
-### 3.1 Set up a Database 
+### Prerequisite — Set up a database
 
-**Requirements**
-- Need a postgres database (e.g. [Supabase](https://supabase.com/), [Neon](https://neon.tech/), etc)
+:::note Docker Compose users
+Your Postgres container is already running — skip ahead to [Create Key w/ RPM Limit](#create-key-w-rpm-limit) below.
+:::
 
+**Docker / pip users** — you need a Postgres database (e.g. [Supabase](https://supabase.com/), [Neon](https://neon.tech/), or self-hosted). Add `general_settings` to your `config.yaml`:
 
 ```yaml
 model_list:
@@ -268,7 +479,9 @@ general_settings:
   database_url: "postgresql://<user>:<password>@<host>:<port>/<dbname>" # 👈 KEY CHANGE
 ```
 
-Save config.yaml as `litellm_config.yaml` (used in 3.2).
+Save config.yaml as `litellm_config.yaml` before continuing.
+
+You must finish this setup before starting the proxy server.
 
 ---
 
@@ -294,7 +507,7 @@ See All General Settings [here](http://localhost:3000/docs/proxy/configs#all-set
         `database_url: "postgresql://..."`
      - Set `DATABASE_URL=postgresql://<user>:<password>@<host>:<port>/<dbname>` in your env 
 
-### 3.2 Start Proxy 
+### Start Proxy
 
 ```bash
 docker run \
@@ -302,12 +515,11 @@ docker run \
     -e AZURE_API_KEY=d6*********** \
     -e AZURE_API_BASE=https://openai-***********/ \
     -p 4000:4000 \
-    docker.litellm.ai/berriai/litellm:main-latest \
+    ghcr.io/berriai/litellm-database:main-latest \
     --config /app/config.yaml --detailed_debug
 ```
 
-
-### 3.3 Create Key w/ RPM Limit
+### Create Key w/ RPM Limit
 
 Create a key with `rpm_limit: 1`. This will only allow 1 request per minute for calls to proxy with this key.
 
@@ -330,9 +542,9 @@ curl -L -X POST 'http://0.0.0.0:4000/key/generate' \
 }
 ```
 
-### 3.4 Test it! 
+### Test it!
 
-**Use your virtual key from step 3.3**
+**Use the virtual key you just created.**
 
 1st call - Expect to work! 
 
@@ -546,6 +758,24 @@ model_list:
 
 ## Troubleshooting 
 
+### `prometheus.yml` mount error — "not a directory"
+
+If you see:
+
+```bash
+Error: cannot create subdirectories in ".../prometheus.yml": not a directory
+```
+
+Docker created `prometheus.yml` as an **empty directory** instead of a file. This happens when the file is missing at `docker compose up` time.
+
+Fix it:
+Then create the file (see [Step 2.3 — Create `prometheus.yml`](#23--create-prometheusyml)) and run `docker compose up` again.
+```bash
+rm -rf prometheus.yml
+```
+
+Then create the file (see [Step 2.4](#step-24--create-prometheusyml)) and run `docker compose up` again.
+
 ### Non-root docker image?
 
 If you need to run the docker image as a non-root user, use [this](https://github.com/BerriAI/litellm/pkgs/container/litellm-non_root).
@@ -645,6 +875,3 @@ LiteLLM Proxy uses the [LiteLLM Python SDK](https://docs.litellm.ai/docs/routing
 - Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
 
 [![Chat on WhatsApp](https://img.shields.io/static/v1?label=Chat%20on&message=WhatsApp&color=success&logo=WhatsApp&style=flat-square)](https://wa.link/huol9n) [![Chat on Discord](https://img.shields.io/static/v1?label=Chat%20on&message=Discord&color=blue&logo=Discord&style=flat-square)](https://discord.gg/wuPM9dRgDw) 
-
-
-

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

@@ -114,4 +114,4 @@ Understand spend distribution across endpoints:
 
 - [Customer Usage](./customer_usage.md) - Track spend and usage for individual customers
 - [Cost Tracking](./cost_tracking.md) - Comprehensive cost tracking and analytics
-- [Spend Logs](./spend_logs.md) - Detailed request-level spend logs
+- [Spend Logs](./cost_tracking.md#-spend-logs-api---individual-transaction-logs) - Detailed request-level spend logs

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

@@ -0,0 +1,139 @@
+# Akto
+
+## Overview
+[Akto](https://www.akto.io/) provides API security guardrails and data ingestion for LLM traffic.
+
+Akto now uses a **two-entry guardrail pattern** in LiteLLM:
+- `akto-validate` (`pre_call`) for request validation
+- `akto-ingest` (`post_call`) for request/response ingestion
+
+There is no `on_flagged` setting anymore.
+
+Use these as two separate guardrails in `config.yaml`:
+- `guardrail_name: "akto-validate"`
+- `guardrail_name: "akto-ingest"`
+
+## 1. Get Your Akto Credentials
+
+Set up the Akto Guardrail API Service and grab:
+- `AKTO_GUARDRAIL_API_BASE` — your Guardrail API Base URL
+- `AKTO_API_KEY` — your API key
+
+## 2. Configure in `config.yaml`
+
+### Block + Ingest (recommended)
+
+Use both entries below. This gives you:
+- pre-call block decision
+- post-call ingestion for allowed traffic
+
+Keep these as two separate entries (`akto-validate` and `akto-ingest`).
+
+```yaml
+guardrails:
+  - guardrail_name: "akto-validate"
+    litellm_params:
+      guardrail: akto
+      mode: pre_call
+      akto_base_url: os.environ/AKTO_GUARDRAIL_API_BASE
+      akto_api_key: os.environ/AKTO_API_KEY
+      default_on: true
+      unreachable_fallback: fail_closed   # optional: fail_open | fail_closed (default: fail_closed)
+      guardrail_timeout: 5                # optional, default: 5
+      akto_account_id: "1000000"         # optional, env fallback: AKTO_ACCOUNT_ID
+      akto_vxlan_id: "0"                 # optional, env fallback: AKTO_VXLAN_ID
+
+  - guardrail_name: "akto-ingest"
+    litellm_params:
+      guardrail: akto
+      mode: post_call
+      akto_base_url: os.environ/AKTO_GUARDRAIL_API_BASE
+      akto_api_key: os.environ/AKTO_API_KEY
+      default_on: true
+```
+
+### Monitor-only mode
+
+If you only want logging/ingestion and no blocking, keep only `akto-ingest`.
+
+```yaml
+guardrails:
+  - guardrail_name: "akto-ingest"
+    litellm_params:
+      guardrail: akto
+      mode: post_call
+      akto_base_url: os.environ/AKTO_GUARDRAIL_API_BASE
+      akto_api_key: os.environ/AKTO_API_KEY
+      default_on: true
+```
+
+## 3. Test It
+
+```shell
+curl -i http://localhost:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer <your litellm key>" \
+  -d '{
+    "model": "gpt-3.5-turbo",
+    "messages": [
+      {"role": "user", "content": "Hello, how are you?"}
+    ]
+  }'
+```
+
+If a request gets blocked:
+
+```json
+{
+  "error": {
+    "message": "Prompt injection detected",
+    "type": "None",
+    "param": "None",
+    "code": "403"
+  }
+}
+```
+
+## 4. How It Works
+
+**Block + Ingest mode:**
+```
+Request → LiteLLM → Akto guardrail check
+  → Allowed  → forward to LLM → ingest response
+  → Blocked  → ingest blocked marker → 403 error
+```
+
+**Monitor-only mode:**
+```
+Request → LiteLLM → forward to LLM → get response
+  → Send to Akto (guardrails + ingest) → log only
+```
+
+## 5. Event behavior
+
+| Entry | LiteLLM hook | Akto call behavior |
+|------|---|---|
+| `akto-validate` | `pre_call` | Awaited call with `guardrails=true`, `ingest_data=false` |
+| `akto-ingest` | `post_call` | Fire-and-forget call with `guardrails=true`, `ingest_data=true` |
+
+When blocked in `pre_call`, LiteLLM sends one fire-and-forget ingest payload with blocked metadata and returns `403`.
+
+## 6. Parameters
+
+| Parameter | Env Variable | Default | Description |
+|-----------|-------------|---------|-------------|
+| `akto_base_url` | `AKTO_GUARDRAIL_API_BASE` | *required* | Akto Guardrail API Base URL |
+| `akto_api_key` | `AKTO_API_KEY` | *required* | API key (sent as `Authorization` header) |
+| `akto_account_id` | `AKTO_ACCOUNT_ID` | `1000000` | Akto account id included in payload |
+| `akto_vxlan_id` | `AKTO_VXLAN_ID` | `0` | Akto vxlan id included in payload |
+| `unreachable_fallback` | — | `fail_closed` | `fail_open` or `fail_closed` |
+| `guardrail_timeout` | — | `5` | Timeout in seconds |
+| `default_on` | — | `true` (recommended) | Enables the guardrail entry by default |
+
+## 7. Error Handling
+
+| Scenario | `fail_closed` (default) | `fail_open` |
+|----------|------------------------|-------------|
+| Akto unreachable | ❌ Blocked (503) | ✅ Passes through |
+| Akto returns error | ❌ Blocked (503) | ✅ Passes through |
+| Guardrail says no | ❌ Blocked (403) | ❌ Blocked (403) |

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

@@ -117,6 +117,14 @@ guardrails:
 
 :::
 
+:::note Streaming and post_call guardrails
+
+For **streaming responses**, `post_call` guardrails run on the fully assembled response **after** all chunks have been delivered to the client. This means `post_call` guardrails on streaming are **audit-only** — they can inspect and log the complete response, but cannot block content delivery. Guardrail results are recorded in `guardrail_information` within the logging payload for compliance and auditing.
+
+To filter or block streaming content in real-time, use `async_post_call_streaming_iterator_hook` instead, which processes chunks as they arrive.
+
+:::
+
 <details>
 <summary>Advanced: Multiple modes with individual event hooks</summary>
 
@@ -655,8 +663,8 @@ class myCustomGuardrail(CustomGuardrail):
 | `apply_guardrail` | Simple method to check and optionally modify text | ✅ | INPUT or OUTPUT | ✅ | ✅ | ✅ |
 | `async_pre_call_hook` | A hook that runs before the LLM API call | ✅ | INPUT | ✅ | ❌ | ✅ |
 | `async_moderation_hook` | A hook that runs during the LLM API call| ✅ | INPUT | ❌ | ❌ | ✅ |
-| `async_post_call_success_hook` | A hook that runs after a successful LLM API call| ✅ | INPUT, OUTPUT | ❌ | ✅ | ✅ |
-| `async_post_call_streaming_iterator_hook` | A hook that processes streaming responses | ✅ | OUTPUT | ❌ | ✅ | ✅ |
+| `async_post_call_success_hook` | A hook that runs after a successful LLM API call. For streaming, runs on the assembled response after delivery (audit-only, cannot block). | ✅ | INPUT, OUTPUT | ❌ | ✅ | ✅ (non-streaming only) |
+| `async_post_call_streaming_iterator_hook` | A hook that processes streaming responses in real-time (can filter/block chunks) | ✅ | OUTPUT | ❌ | ✅ | ✅ |
 
 
 ## Frequently Asked Questions

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

@@ -0,0 +1,190 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import { ControlPlaneArchitecture } from '@site/src/components/ControlPlaneArchitecture';
+
+# [BETA] High Availability Control Plane
+
+Deploy a single LiteLLM UI that manages multiple independent LiteLLM proxy instances, each with its own database, Redis, and master key.
+
+:::info
+
+This is an Enterprise feature.
+
+[Enterprise Pricing](https://www.litellm.ai/#pricing)
+
+[Get free 7-day trial key](https://www.litellm.ai/enterprise#trial)
+
+:::
+
+## Why This Architecture?
+
+In the [standard multi-region setup](./control_plane_and_data_plane.md), all instances share a single database and master key. This works, but introduces a shared dependency. If the database goes down, every instance is affected.
+
+The **High Availability Control Plane** takes a different approach:
+
+| | Shared Database (Standard) | High Availability Control Plane |
+|---|---|---|
+| **Database** | Single shared DB for all instances | Each instance has its own DB |
+| **Redis** | Shared Redis | Each instance has its own Redis |
+| **Master Key** | Same key across all instances | Each instance has its own key |
+| **Failure isolation** | DB outage affects all instances | Failure is isolated to one instance |
+| **User management** | Centralized, one user table | Independent, each worker manages its own users |
+| **UI** | One UI per admin instance | Single control plane UI manages all workers |
+
+### Benefits
+
+- **True high availability**: no shared infrastructure means no single point of failure
+- **Blast radius containment**: a misconfiguration or outage on one worker doesn't affect others
+- **Regional isolation**: workers can run in different regions with data residency requirements
+- **Simpler operations**: each worker is a self-contained LiteLLM deployment
+
+## Architecture
+
+<ControlPlaneArchitecture />
+
+The **control plane** is a LiteLLM instance that serves the admin UI and knows about all the workers. It does not proxy LLM requests, it is purely for administration.
+
+Each **worker** is a fully independent LiteLLM proxy that handles LLM requests for its region or team. Workers have their own users, keys, teams, and budgets.
+
+## Setup
+
+### 1. Control Plane Configuration
+
+The control plane needs a `worker_registry` that lists all worker instances.
+
+```yaml title="cp_config.yaml"
+model_list: []
+
+general_settings:
+  master_key: sk-1234
+  database_url: os.environ/DATABASE_URL
+
+worker_registry:
+  - worker_id: "worker-a"
+    name: "Worker A"
+    url: "http://localhost:4001"
+  - worker_id: "worker-b"
+    name: "Worker B"
+    url: "http://localhost:4002"
+```
+
+Start the control plane:
+
+```bash
+litellm --config cp_config.yaml --port 4000
+```
+
+### 2. Worker Configuration
+
+Each worker needs `control_plane_url` in its `general_settings` to enable cross-origin authentication from the control plane UI.
+
+`PROXY_BASE_URL` must also be set for each worker so that SSO callback redirects resolve correctly.
+
+<Tabs>
+<TabItem value="worker-a" label="Worker A">
+
+```yaml title="worker_a_config.yaml"
+model_list: []
+
+general_settings:
+  master_key: sk-worker-a-1234
+  database_url: os.environ/WORKER_A_DATABASE_URL
+  control_plane_url: "http://localhost:4000"
+```
+
+```bash
+PROXY_BASE_URL=http://localhost:4001 litellm --config worker_a_config.yaml --port 4001
+```
+
+</TabItem>
+<TabItem value="worker-b" label="Worker B">
+
+```yaml title="worker_b_config.yaml"
+model_list: []
+
+general_settings:
+  master_key: sk-worker-b-1234
+  database_url: os.environ/WORKER_B_DATABASE_URL
+  control_plane_url: "http://localhost:4000"
+```
+
+```bash
+PROXY_BASE_URL=http://localhost:4002 litellm --config worker_b_config.yaml --port 4002
+```
+
+</TabItem>
+</Tabs>
+
+:::important
+Each worker must have its own `master_key` and `database_url`. The whole point of this architecture is that workers are independent.
+:::
+
+### 3. SSO Configuration (Optional)
+
+SSO is configured on the **control plane** instance the same way as a standard LiteLLM proxy. See the [SSO setup guide](./admin_ui_sso.md) for full instructions.
+
+If using SSO, make sure to register each worker URL and the control plane URL as allowed callback URLs in your SSO provider's dashboard.
+
+## How It Works
+
+### Login Flow
+
+1. User visits the control plane UI (`http://localhost:4000/ui`)
+2. The login page shows a **worker selector** dropdown listing all registered workers
+3. User selects a worker (e.g. "Worker A") and logs in with username/password or SSO
+4. The UI authenticates against the **selected worker** using the `/v3/login` endpoint
+5. On success, the UI stores the worker's JWT and points all subsequent API calls at the worker
+6. The user can now manage keys, teams, models, and budgets on that worker, all from the control plane UI
+
+### Switching Workers
+
+Once logged in, users can switch workers from the **navbar dropdown** without leaving the UI. Switching redirects back to the login page to authenticate against the new worker.
+
+### Discovery
+
+The control plane exposes a `/.well-known/litellm-ui-config` endpoint that the UI reads on load. This endpoint returns:
+- `is_control_plane: true`
+- The list of workers with their IDs, names, and URLs
+
+This is how the login page knows to show the worker selector.
+
+## Local Testing
+
+To try this out locally, start each instance in a separate terminal:
+
+```bash
+# Terminal 1: Control Plane
+litellm --config cp_config.yaml --port 4000
+
+# Terminal 2: Worker A
+PROXY_BASE_URL=http://localhost:4001 litellm --config worker_a_config.yaml --port 4001
+
+# Terminal 3: Worker B
+PROXY_BASE_URL=http://localhost:4002 litellm --config worker_b_config.yaml --port 4002
+```
+
+Then open `http://localhost:4000/ui`. You should see the worker selector on the login page.
+
+## Configuration Reference
+
+### Control Plane Settings
+
+| Field | Location | Description |
+|---|---|---|
+| `worker_registry` | Top-level config | List of worker instances |
+| `worker_registry[].worker_id` | Required | Unique identifier for the worker |
+| `worker_registry[].name` | Required | Display name shown in the UI |
+| `worker_registry[].url` | Required | Full URL of the worker instance |
+
+### Worker Settings
+
+| Field | Location | Description |
+|---|---|---|
+| `general_settings.control_plane_url` | Required | URL of the control plane instance. Enables `/v3/login` and `/v3/login/exchange` endpoints on this worker. |
+| `PROXY_BASE_URL` | Environment variable | The worker's own external URL. Required for SSO callback redirects. |
+
+## Related Documentation
+
+- [Standard Multi-Region Setup](./control_plane_and_data_plane.md) - shared-database architecture for admin/worker split
+- [SSO Setup](./admin_ui_sso.md) - configuring SSO for the admin UI
+- [Production Deployment](./prod.md) - production best practices

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

@@ -146,5 +146,5 @@ Test new router settings on specific keys or teams before applying globally:
 - [Router Settings Reference](./config_settings.md#router_settings---reference) - Complete reference of all router settings
 - [Load Balancing](./load_balancing.md) - Learn about routing strategies and load balancing
 - [Reliability](./reliability.md) - Configure fallbacks, retries, and error handling
-- [Keys](./keys.md) - Manage API keys and their settings
-- [Teams](./teams.md) - Organize keys into teams
+- [Keys](./virtual_keys.md) - Manage API keys and their settings
+- [Teams](./multi_tenant_architecture.md) - Organize keys into teams

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

@@ -352,7 +352,7 @@ If `order=1` deployment is unavailable (e.g., rate-limited), the router falls ba
 
 When load balancing OpenAI's Responses API across deployments with **different API keys** (e.g., different Azure regions or organizations), encrypted content items (like `rs_...` reasoning items) can only be decrypted by the originating API key.
 
-**Solution:** Use the `encrypted_content_affinity` pre-call check to automatically route follow-up requests containing encrypted items to the correct deployment:
+**Solution:** Use the `encrypted_content_affinity` pre-call check (requires LiteLLM >= 1.82.3) to automatically route follow-up requests containing encrypted items to the correct deployment:
 
 ```yaml
 model_list:

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

@@ -187,7 +187,7 @@ Use tags and multiple comparisons to run structured A/B tests:
 
 ## Related Features
 
-- [Playground Chat UI](./playground.md) - Single model testing interface
+- [Playground Chat UI](./ui.md) - Single model testing interface
 - [Model Management](./model_management.md) - Configure and manage models
-- [Guardrails](./guardrails.md) - Set up safety filters
+- [Guardrails](./guardrails/quick_start.md) - Set up safety filters
 - [AI Hub](./ai_hub.md) - Share models and agents with your organization

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

@@ -311,7 +311,7 @@ litellm_settings:
 1. **At Startup**: When the proxy starts, it reads the `prompts` field from `config.yaml`
 2. **Initialization**: Each prompt is initialized based on its `prompt_integration` type
 3. **In-Memory Storage**: Prompts are stored in the `IN_MEMORY_PROMPT_REGISTRY`
-4. **Access**: Use these prompts via the `/v1/chat/completions` endpoint with `prompt_id` in the request
+4. **Access**: Use these prompts via `/v1/chat/completions` or `/v1/responses` with `prompt_id` in the request
 
 ### Using Config-Loaded Prompts
 
@@ -331,6 +331,23 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
 }'
 ```
 
+You can also use the same `prompt_id` with the Responses API:
+
+```bash
+curl -L -X POST 'http://0.0.0.0:4000/v1/responses' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "gpt-4o",
+    "prompt_id": "coding_assistant",
+    "prompt_variables": {
+        "language": "python",
+        "task": "create a web scraper"
+    },
+    "input": []
+}'
+```
+
 ### Prompt Schema Reference
 
 Each prompt in the `prompts` list requires:

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

@@ -125,4 +125,4 @@ curl -X DELETE "https://your-proxy-url/schedule/anthropic_beta_headers_reload" \
 ## Related
 
 - [Model Cost Map Sync](./sync_models_github.md) - Auto-sync model pricing data
-- [Anthropic Beta Headers](../completion/anthropic.md#beta-features) - Using Anthropic beta features
+- [Anthropic Beta Headers](../providers/anthropic.md) - Using Anthropic beta features

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

@@ -87,6 +87,6 @@ Change the setting from the UI and have it take effect immediately—perfect for
 
 ## Related Documentation
 
-- [Admin UI Overview](./ui_overview.md) – General guide to the LiteLLM Admin UI
-- [Models and Endpoints](./models_and_endpoints.md) – Managing models and API endpoints
+- [Admin UI Overview](./ui.md) – General guide to the LiteLLM Admin UI
+- [Models and Endpoints](./model_management.md) – Managing models and API endpoints
 - [Config Settings](./config_settings.md) – `store_model_in_db` in `general_settings`

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

@@ -79,4 +79,4 @@ curl -X POST http://localhost:4000/v1/chat/completions \
 ## See Also
 - [Proxy Quick Start](./quick_start.md)
 - [User Management](./users.md)
-- [Key Management](./key_management.md)
+- [Key Management](./virtual_keys.md)

docs/my-website/docs/reasoning_content.md

@@ -13,6 +13,7 @@ Supported Providers:
 - Deepseek (`deepseek/`)
 - Anthropic API (`anthropic/`)
 - Bedrock (Anthropic + Deepseek + GPT-OSS) (`bedrock/`)
+- OpenAI Responses API (`openai/responses/`)
 - Vertex AI (Anthropic) (`vertexai/`)
 - OpenRouter (`openrouter/`)
 - XAI (`xai/`)
@@ -594,9 +595,26 @@ Expected Response
 
 :::tip gpt-5.4: reasoning_effort + function tools
 
-LiteLLM drops `reasoning_effort` from `gpt-5.4` requests to `litellm.completion()` that include tools, since that combination is supported in the Responses API.
+When `gpt-5.4+` requests to `litellm.completion()` include both `reasoning_effort` and `tools`, LiteLLM **automatically routes** the request through the Responses API bridge. This works for both **OpenAI** (`openai/gpt-5.4`) and **Azure** (`azure/gpt-5.4`) providers — no extra configuration needed.
 
-If you need reasoning **and** tools together, use `openai/responses/gpt-5.4` to route through the Responses API instead. See [Responses API Bridge](/docs/providers/openai#openai-chat-completion-to-responses-api-bridge) for details.
+You can also route explicitly via `openai/responses/gpt-5.4` or `azure/responses/gpt-5.4`. See [Responses API Bridge](/docs/providers/openai#openai-chat-completion-to-responses-api-bridge) for details.
+
+**Azure custom deployment names:** Auto-routing relies on the deployment name matching the `gpt-5.4*` pattern. If you use a custom deployment name (e.g. `"my-reasoning-model"`), enable routing via:
+
+**SDK:**
+```python
+litellm.completion(model="azure/responses/my-reasoning-model", ...)
+```
+
+**Proxy config:**
+```yaml
+model_list:
+  - model_name: my-reasoning-model
+    litellm_params:
+      model: azure/my-reasoning-model
+    model_info:
+      mode: responses
+```
 
 :::
 
@@ -683,3 +701,69 @@ response = litellm.completion(
     reasoning_effort={"effort": "low", "summary": "detailed"},  # Explicit control
 )
 ```
+
+### Summary Preservation via `/v1/messages` Adapter
+
+When using the Anthropic `/v1/messages` adapter to route non-Claude models (e.g., `openai/gpt-5.1`), the `thinking.summary` value is preserved and forwarded to the downstream provider. For example:
+
+```python
+import litellm
+
+response = await litellm.anthropic.messages.acreate(
+    model="openai/gpt-5.1",
+    messages=[{"role": "user", "content": "Hello"}],
+    max_tokens=8096,
+    thinking={"type": "enabled", "budget_tokens": 5000, "summary": "concise"},
+)
+# The summary="concise" is preserved when routing to OpenAI's Responses API
+```
+
+### Enabling Default Summary Injection for `/v1/messages` Adapter
+
+When the Anthropic `/v1/messages` adapter translates `thinking` parameters to OpenAI `reasoning_effort` for non-Claude models, you can opt-in to automatic `summary="detailed"` injection using the `reasoning_auto_summary` flag. This ensures that reasoning text is returned in the response (matching the Anthropic thinking behavior).
+
+To **enable** this default injection, use the `reasoning_auto_summary` flag:
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+import litellm
+
+# Enable default summary="detailed" injection
+litellm.reasoning_auto_summary = True
+
+response = await litellm.anthropic.messages.acreate(
+    model="openai/gpt-5.1",
+    messages=[{"role": "user", "content": "Hello"}],
+    max_tokens=8096,
+    thinking={"type": "enabled", "budget_tokens": 5000},
+)
+# summary="detailed" will be automatically added to reasoning_effort
+```
+
+</TabItem>
+
+<TabItem value="env" label="Environment Variable">
+
+```bash
+export LITELLM_REASONING_AUTO_SUMMARY=true
+```
+
+</TabItem>
+
+<TabItem value="proxy" label="Proxy Config">
+
+```yaml
+litellm_settings:
+  reasoning_auto_summary: true
+```
+
+</TabItem>
+</Tabs>
+
+:::info
+
+This flag only affects the automatic injection of `summary="detailed"` when no user-provided summary is present. If you explicitly pass `thinking.summary` (e.g., `"concise"` or `"auto"`), your value is always preserved regardless of this flag.
+
+:::

docs/my-website/docs/response_api.md

@@ -1160,12 +1160,12 @@ follow_up = await router.aresponses(
 To enable session continuity for Responses API in your LiteLLM proxy, set `optional_pre_call_checks` in your proxy config.yaml.
 
 - `responses_api_deployment_check`: high priority routing when `previous_response_id` is provided
-- `encrypted_content_affinity`: **[Recommended]** content-aware routing for encrypted items (e.g., `rs_...` reasoning items)
+- `encrypted_content_affinity`: **[Recommended]** content-aware routing for encrypted items (e.g., `rs_...` reasoning items) (**requires LiteLLM >= 1.82.3**)
 - `session_affinity`: sticky sessions based on session id (takes priority over `deployment_affinity`)
 - `deployment_affinity`: sticky sessions based on user key (applies even without `previous_response_id`)
 
 :::tip Recommended: Use `encrypted_content_affinity`
-For Responses API with load balancing across deployments with **different API keys**, use `encrypted_content_affinity` instead of `deployment_affinity`. It only pins requests that contain encrypted content, avoiding quota reduction while preventing `invalid_encrypted_content` errors.
+For Responses API with load balancing across deployments with **different API keys**, use `encrypted_content_affinity` instead of `deployment_affinity`. It only pins requests that contain encrypted content, avoiding quota reduction while preventing `invalid_encrypted_content` errors. (Requires LiteLLM >= 1.82.3.)
 :::
 
 Notes:
@@ -1364,6 +1364,85 @@ litellm --config config.yaml
 | `deployment_affinity` | Simple sticky sessions | All requests from same API key | ❌ Reduces quota by # of users |
 
 
+## Per-Model-Group Affinity Configuration
+
+By default, `optional_pre_call_checks` applies globally to all model groups. Use `model_group_affinity_config` when you want different affinity behavior per model group — for example, enabling stickiness only for models spread across providers (Azure + Bedrock) while leaving single-provider groups free to load-balance.
+
+Groups not listed fall back to the global `optional_pre_call_checks` settings.
+
+<Tabs>
+<TabItem value="python-sdk" label="Python SDK">
+
+```python
+router = litellm.Router(
+    model_list=[
+        {
+            "model_name": "gpt-4",
+            "litellm_params": {"model": "azure/gpt-4", "api_key": "...", "api_base": "https://endpoint1.openai.azure.com"},
+        },
+        {
+            "model_name": "gpt-4",
+            "litellm_params": {"model": "bedrock/anthropic.claude-v2", "aws_region_name": "us-east-1"},
+        },
+        {
+            "model_name": "text-embedding-ada-002",
+            "litellm_params": {"model": "azure/text-embedding-ada-002", "api_key": "...", "api_base": "https://endpoint1.openai.azure.com"},
+        },
+        {
+            "model_name": "text-embedding-ada-002",
+            "litellm_params": {"model": "azure/text-embedding-ada-002", "api_key": "...", "api_base": "https://endpoint2.openai.azure.com"},
+        },
+    ],
+    # gpt-4: cross-provider (Azure + Bedrock) — enable deployment affinity
+    # text-embedding-ada-002: same provider — no affinity, let it load balance freely
+    model_group_affinity_config={
+        "gpt-4": ["deployment_affinity", "responses_api_deployment_check"],
+    },
+)
+```
+
+</TabItem>
+<TabItem value="proxy-server" label="Proxy Server">
+
+```yaml title="config.yaml"
+model_list:
+  - model_name: gpt-4
+    litellm_params:
+      model: azure/gpt-4
+      api_key: os.environ/AZURE_API_KEY_1
+      api_base: https://endpoint1.openai.azure.com
+
+  - model_name: gpt-4
+    litellm_params:
+      model: bedrock/anthropic.claude-v2
+      aws_region_name: us-east-1
+
+  - model_name: text-embedding-ada-002
+    litellm_params:
+      model: azure/text-embedding-ada-002
+      api_key: os.environ/AZURE_API_KEY_1
+      api_base: https://endpoint1.openai.azure.com
+
+  - model_name: text-embedding-ada-002
+    litellm_params:
+      model: azure/text-embedding-ada-002
+      api_key: os.environ/AZURE_API_KEY_2
+      api_base: https://endpoint2.openai.azure.com
+
+router_settings:
+  # gpt-4: cross-provider — enable stickiness
+  # text-embedding-ada-002: not listed — load balances freely
+  model_group_affinity_config:
+    "gpt-4":
+      - deployment_affinity
+      - responses_api_deployment_check
+```
+
+</TabItem>
+</Tabs>
+
+**Supported values:** `deployment_affinity`, `responses_api_deployment_check`, `session_affinity`
+
 ## Calling non-Responses API endpoints (`/responses` to `/chat/completions` Bridge)
 
 LiteLLM allows you to call non-Responses API models via a bridge to LiteLLM's `/chat/completions` endpoint. This is useful for calling Anthropic, Gemini and even non-Responses API OpenAI models.
@@ -1556,6 +1635,12 @@ curl -X POST "http://localhost:4000/v1/responses" \
   }'
 ```
 
+## File Search (Vector Stores)
+
+For full `file_search` usage (native + emulated fallback), SDK/Proxy examples, architecture diagram, and Q&A, see:
+
+- [`File Search in the Responses API — E2E Testing Guide`](/docs/tutorials/file_search_responses_api)
+
 ## Session Management
 
 LiteLLM Proxy supports session management for all supported models. This allows you to store and fetch conversation history (state) in LiteLLM Proxy. 

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

@@ -37,7 +37,7 @@ Click **+ Add New Plugin** to register a plugin in your marketplace.
 Enter the plugin information:
 
 - **Name**: Plugin identifier (kebab-case, e.g., `my-plugin`)
-- **Source Type**: Choose GitHub or URL
+- **Source Type**: Choose GitHub, Git URL, or Git Subdir
 - **Repository/URL**: The git source (e.g., `org/repo` for GitHub)
 - **Version**: Semantic version (optional)
 - **Description**: What the plugin does
@@ -216,6 +216,22 @@ curl -X DELETE http://localhost:4000/claude-code/plugins/my-plugin \
 
 Use this format for GitLab, Bitbucket, or self-hosted git repositories.
 
+</TabItem>
+<TabItem value="git-subdir" label="Git Subdir">
+
+```json
+{
+  "name": "my-plugin",
+  "source": {
+    "source": "git-subdir",
+    "url": "https://github.com/org/repo.git",
+    "path": "plugins/my-plugin"
+  }
+}
+```
+
+Use this format when your plugin lives in a subdirectory of a git repository. The `path` field must be a relative path of slash-separated segments (alphanumeric, dots, hyphens, underscores only).
+
 </TabItem>
 </Tabs>
 

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

@@ -0,0 +1,241 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# File Search in the Responses API
+
+LiteLLM now supports `file_search` in the Responses API across both:
+- providers that support it natively (like OpenAI / Azure), and
+- providers that do not (like Anthropic, Bedrock, and other non-native providers) via emulation.
+
+## What this is
+
+`file_search` lets models retrieve grounded context from your vector stores and answer with citations.
+LiteLLM keeps one OpenAI-compatible output shape while routing requests through either native passthrough or an emulated fallback.
+
+Two paths are covered:
+
+| Path | When it runs | What LiteLLM does |
+| --- | --- | --- |
+| **Native passthrough** | Provider natively supports `file_search` (OpenAI, Azure) | Decodes unified vector store ID → forwards to provider as-is |
+| **Emulated fallback** | Provider doesn't support `file_search` (Anthropic, Bedrock, etc.) | Converts to a function tool → intercepts tool call → runs vector search → synthesizes OpenAI-format output |
+
+In `tools[].vector_store_ids`, LiteLLM accepts both provider-native IDs (e.g. `vs_...`) **and** **managed vector store unified IDs** (URL-safe base64 strings from the proxy managed-vector flow), e.g. `litellm.responses(..., tools=[{"type": "file_search", "vector_store_ids": ["bGl0ZWxsbV9wcm94eT..."]}])`.
+
+## Usage
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy" default>
+
+### 1. Setup `config.yaml`
+
+```yaml title="config.yaml"
+model_list:
+  - model_name: gpt-4.1
+    litellm_params:
+      model: openai/gpt-4.1
+      api_key: os.environ/OPENAI_API_KEY
+
+  - model_name: claude-sonnet
+    litellm_params:
+      model: anthropic/claude-sonnet-4-5
+      api_key: os.environ/ANTHROPIC_API_KEY
+```
+
+### 2. Start the proxy
+
+```bash
+litellm --config config.yaml
+```
+
+### 3. Call Responses API with `file_search`
+
+```python title="Proxy call"
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:4000", api_key="sk-your-proxy-key")
+
+response = client.responses.create(
+    model="claude-sonnet",  # swap to "gpt-4.1" for native path
+    input="What does LiteLLM support?",
+    tools=[{
+        "type": "file_search",
+        "vector_store_ids": ["vs_abc123"]
+    }],
+    include=["file_search_call.results"],
+)
+
+print(response.output)
+```
+
+</TabItem>
+<TabItem value="sdk" label="LiteLLM SDK">
+
+### 1. Install + set keys
+
+```bash
+pip install litellm
+export OPENAI_API_KEY="sk-..."
+export ANTHROPIC_API_KEY="sk-ant-..."
+```
+
+### 2. Call Responses API with `file_search`
+
+```python title="SDK call"
+import litellm
+
+response = litellm.responses(
+    model="anthropic/claude-sonnet-4-5",  # swap to openai/gpt-4.1 for native path
+    input="What does LiteLLM support?",
+    tools=[{
+        "type": "file_search",
+        "vector_store_ids": ["vs_abc123"]
+    }],
+    include=["file_search_call.results"],
+)
+
+print(response.output)
+```
+
+</TabItem>
+</Tabs>
+
+### Behavior Matrix
+
+| Path | SDK model | Proxy model | Behavior |
+| --- | --- | --- | --- |
+| Native passthrough | `openai/gpt-4.1` | `gpt-4.1` | Provider executes native `file_search` |
+| Emulated fallback | `anthropic/claude-sonnet-4-5` | `claude-sonnet` | LiteLLM converts to function tool and synthesizes OpenAI-format output |
+
+
+
+## Architecture Diagram
+
+```mermaid
+flowchart TD
+    A[Client SDK or Proxy Caller] --> B[LiteLLM Responses API]
+    B --> C{Provider supports native file_search?}
+
+    C -->|Yes| D[Native passthrough path]
+    D --> D1[Decode unified vector_store_id if needed]
+    D1 --> D2[Forward request to provider unchanged]
+    D2 --> D3[Provider performs file_search]
+    D3 --> Z[OpenAI-compatible output]
+
+    C -->|No| E[Emulated fallback path]
+    E --> E1[Convert file_search to litellm_file_search function tool]
+    E1 --> E2[First model call returns tool call with one or more queries]
+    E2 --> E3[LiteLLM executes vector search for each query]
+    E3 --> E4[Second model call with tool_result context]
+    E4 --> E5[Synthesize file_search_call + message + citations]
+    E5 --> Z[OpenAI-compatible output]
+```
+
+
+
+## Prerequisites
+
+```bash
+pip install 'litellm[proxy]'
+export OPENAI_API_KEY="sk-..."          # for native path
+export ANTHROPIC_API_KEY="sk-ant-..."  # for emulated path
+```
+
+
+
+## Example response shape
+
+## Validating the Output Format
+
+Regardless of which path ran, the response always follows the OpenAI Responses API format:
+
+```json
+{
+  "output": [
+    {
+      "type": "file_search_call",
+      "id": "fs_abc123",
+      "status": "completed",
+      "queries": ["What does LiteLLM support?"],
+      "search_results": null
+    },
+    {
+      "type": "message",
+      "role": "assistant",
+      "content": [
+        {
+          "type": "output_text",
+          "text": "LiteLLM is a unified interface...",
+          "annotations": [
+            {
+              "type": "file_citation",
+              "index": 150,
+              "file_id": "file-xxxx",
+              "filename": "knowledge.txt"
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}
+```
+
+**Validation script:**
+
+```python showLineNumbers title="Validate response structure"
+def validate_file_search_response(response):
+    """Assert that response follows OpenAI file_search output format."""
+    output = response.output
+    assert len(output) >= 2, "Expected at least 2 output items"
+
+    # First item: file_search_call
+    fs_call = output[0]
+    fs_type = fs_call["type"] if isinstance(fs_call, dict) else fs_call.type
+    assert fs_type == "file_search_call", f"Expected file_search_call, got {fs_type}"
+
+    fs_status = fs_call["status"] if isinstance(fs_call, dict) else fs_call.status
+    assert fs_status == "completed"
+
+    # Second item: message
+    msg = output[1]
+    msg_type = msg["type"] if isinstance(msg, dict) else msg.type
+    assert msg_type == "message"
+
+    content = msg["content"] if isinstance(msg, dict) else msg.content
+    assert len(content) > 0
+    text_block = content[0]
+    text = text_block["text"] if isinstance(text_block, dict) else text_block.text
+    assert isinstance(text, str) and len(text) > 0
+
+    print("✅ Response structure valid")
+    print(f"   Queries: {fs_call['queries'] if isinstance(fs_call, dict) else fs_call.queries}")
+    print(f"   Answer length: {len(text)} chars")
+    annotations = text_block["annotations"] if isinstance(text_block, dict) else text_block.annotations
+    print(f"   Citations: {len(annotations)}")
+
+validate_file_search_response(response)
+```
+
+
+
+## Q&A
+
+- **Why do I see `UnsupportedParamsError`?** This usually means `file_search` was passed to a provider that does not support it natively and emulation could not route correctly. Check:
+  - The model string is valid (for example, `anthropic/claude-sonnet-4-5`).
+  - `custom_llm_provider` resolves correctly so LiteLLM can load the provider config.
+- **Why does vector search return no results?** Common causes:
+  - The vector store ID is wrong or has no files attached.
+  - In LiteLLM-managed stores, file ingestion is not complete (`status != completed`).
+  - The query is too narrow; try a broader query.
+- **Why am I getting `403 Access denied` on vector store calls?** The caller does not have access to that vector store.
+  - The store may belong to another team.
+  - Use an admin/proxy key if your setup requires cross-team access.
+- **Why are `annotations` empty in emulated mode?** `file_citation` annotations require `file_id` metadata in search results. If your vector backend does not return file-level metadata, the answer text is still generated but citations can be empty.
+
+
+
+## What to check next
+
+- [File Search reference in Responses API docs](/docs/response_api#file-search-vector-stores) — full API reference
+- [Vector Store management](/docs/vector_store_files) — create and manage vector stores
+- [Managed vector stores](/docs/providers/bedrock_vector_store) — provider-specific setup

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

@@ -0,0 +1,98 @@
+---
+title: Tutorials
+sidebar_label: Overview
+---
+
+import NavigationCards from '@site/src/components/NavigationCards';
+
+**Tutorials** are step-by-step walkthroughs for integrating LiteLLM with external tools, frameworks, and services — or building complete end-to-end workflows.
+
+> Need help choosing the right path before you start? See [Learn →](/docs/learn)
+
+---
+
+## Getting Started
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "⚡",
+    title: "Getting Started",
+    description: "Installation, playground, text completion, and mock completions.",
+    to: "/docs/tutorials/getting_started",
+  },
+]}
+/>
+
+---
+
+## Integrations
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "🤖",
+    title: "Agent SDKs & Frameworks",
+    description: "OpenAI Agents SDK, Claude Agent SDK, Google ADK, CopilotKit, Letta, LiveKit, Instructor.",
+    to: "/docs/agent_sdks",
+  },
+  {
+    icon: "🛠️",
+    title: "AI Coding Tools",
+    description: "Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Qwen Code, OpenAI Codex.",
+    to: "/docs/ai_tools",
+  },
+  {
+    icon: "🐍",
+    title: "Python SDK",
+    description: "Gradio, fallbacks, provider-specific params — no proxy required.",
+    to: "/docs/tutorials/python_sdk",
+  },
+  {
+    icon: "🔌",
+    title: "Provider Setup",
+    description: "Azure OpenAI, HuggingFace, TogetherAI, local models, and more.",
+    to: "/docs/tutorials/provider_tutorials",
+  },
+]}
+/>
+
+---
+
+## Proxy
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "👥",
+    title: "Proxy: Admin & Access",
+    description: "User and team management, SSO, SCIM, and routing rules.",
+    to: "/docs/tutorials/proxy_admin_access",
+  },
+  {
+    icon: "🛡️",
+    title: "Proxy: Features & Safety",
+    description: "Prompt caching, passthrough APIs, realtime, guardrails, and PII masking.",
+    to: "/docs/tutorials/proxy_features_safety",
+  },
+]}
+/>
+
+---
+
+## Observability & Evaluation
+
+<NavigationCards
+columns={2}
+items={[
+  {
+    icon: "🔍",
+    title: "Observability & Evaluation",
+    description: "Logging to Elasticsearch, benchmarking, and evaluation suites.",
+    to: "/docs/tutorials/observability_evaluation",
+  },
+]}
+/>

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

@@ -1,7 +1,3 @@
----
-displayed_sidebar: tutorialSidebar
----
-
 # Set up environment
 
 Let's get the necessary keys to set up our demo environment.
@@ -11,7 +7,5 @@ Every LLM provider needs API keys (e.g. `OPENAI_API_KEY`). You can get API keys
 Let's get them for our demo!
 
 **OpenAI**: https://platform.openai.com/account/api-keys  
-**Cohere**: https://dashboard.cohere.com/welcome/login?redirect_uri=%2Fapi-keys  (no credit card required)  
+**Cohere**: https://dashboard.cohere.com/welcome/login?redirect_uri=%2Fapi-keys (no credit card required)  
 **AI21**: https://studio.ai21.com/account/api-key (no credit card required)
-
-

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

@@ -0,0 +1,151 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Vertex AI PayGo and Priority
+
+## Priority PayGo
+
+LiteLLM supports Priority PayGo.  
+Send a priority header, get priority queueing, and pay priority token rates.
+
+:::info Which models support Priority PayGo?
+As of this writing: `gemini/gemini-2.5-pro`, `vertex_ai/gemini-3-pro-preview`, `vertex_ai/gemini-3.1-pro-preview`, `vertex_ai/gemini-3-flash-preview`, and their variants.  
+Check `supports_service_tier: true` in LiteLLM's [model pricing JSON](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json).
+:::
+
+### Send a priority request
+
+Use this header:
+
+`X-Vertex-AI-LLM-Shared-Request-Type: priority`
+
+<Tabs>
+<TabItem value="litellm-sdk" label="LiteLLM SDK">
+
+```python
+import litellm
+
+response = litellm.completion(
+    model="vertex_ai/gemini-3-pro-preview",
+    messages=[{"role": "user", "content": "Summarize the Gettysburg Address."}],
+    vertex_project="YOUR_PROJECT_ID",
+    vertex_location="us-central1",
+    extra_headers={"X-Vertex-AI-LLM-Shared-Request-Type": "priority"},
+)
+
+print(response.choices[0].message.content)
+```
+
+</TabItem>
+<TabItem value="proxy-config" label="Proxy config">
+
+```yaml title="config.yaml"
+model_list:
+  - model_name: gemini-priority
+    litellm_params:
+      model: vertex_ai/gemini-3-pro-preview
+      vertex_project: "YOUR_PROJECT_ID"
+      vertex_location: "us-central1"
+      vertex_credentials: os.environ/GOOGLE_APPLICATION_CREDENTIALS
+      extra_headers:
+        X-Vertex-AI-LLM-Shared-Request-Type: priority
+```
+
+```bash
+curl http://localhost:4000/v1/chat/completions \
+  -H "Authorization: Bearer sk-your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "gemini-priority", "messages": [{"role": "user", "content": "Hello"}]}'
+```
+
+</TabItem>
+<TabItem value="pass-through" label="Pass-through mode">
+
+Use `x-pass-` so LiteLLM forwards provider-specific headers.
+
+```bash
+MODEL_ID="gemini-3-pro-preview-0325"
+PROJECT_ID="YOUR_PROJECT_ID"
+
+curl -X POST \
+  "${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/global/publishers/google/models/${MODEL_ID}:generateContent" \
+  -H "Authorization: Bearer sk-your-litellm-key" \
+  -H "Content-Type: application/json" \
+  -H "x-pass-X-Vertex-AI-LLM-Shared-Request-Type: priority" \
+  -d '{"contents": [{"role": "user", "parts": [{"text": "Hello!"}]}]}'
+```
+
+</TabItem>
+</Tabs>
+
+### How cost tracking works
+
+![Vertex AI Priority PayGo Cost Tracking Flow](/img/vertex_cost_tracking_flow.svg)
+
+**`trafficType` → `service_tier` mapping**
+
+| `usageMetadata.trafficType` | `service_tier` | Pricing keys used |
+|---|---|---|
+| `ON_DEMAND` | `None` | `input_cost_per_token` |
+| `ON_DEMAND_PRIORITY` | `"priority"` | `input_cost_per_token_priority` |
+| `FLEX` / `BATCH` | `"flex"` | `input_cost_per_token_flex` |
+
+If a tier-specific key is missing, LiteLLM falls back to standard pricing keys.
+
+---
+
+## Standard PayGo vs Provisioned Throughput
+
+This is a different header from priority routing:
+
+| Header value | Behavior |
+|---|---|
+| `X-Vertex-AI-LLM-Request-Type: shared` | Force standard PayGo (bypass PT) |
+| `X-Vertex-AI-LLM-Request-Type: dedicated` | Force Provisioned Throughput only (`429` if exhausted) |
+
+### Native route example
+
+```python
+import litellm
+
+response = litellm.completion(
+    model="vertex_ai/gemini-2.0-flash",
+    messages=[{"role": "user", "content": "Hello!"}],
+    vertex_project="YOUR_PROJECT_ID",
+    vertex_location="us-central1",
+    extra_headers={"X-Vertex-AI-LLM-Request-Type": "shared"},
+)
+```
+
+### Pass-through example
+
+```bash
+MODEL_ID="gemini-2.0-flash-001"
+PROJECT_ID="YOUR_PROJECT_ID"
+
+curl -X POST \
+  "${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/global/publishers/google/models/${MODEL_ID}:generateContent" \
+  -H "Authorization: Bearer sk-your-litellm-key" \
+  -H "Content-Type: application/json" \
+  -H "x-pass-X-Vertex-AI-LLM-Request-Type: shared" \
+  -d '{
+    "contents": [{"role": "user", "parts": [{"text": "Hello!"}]}]
+  }'
+```
+
+---
+
+## Troubleshooting 
+
+**Q: What does `403 Permission denied` or `IAM_PERMISSION_DENIED` mean?**  
+A: The service account or Application Default Credentials (ADC) user does not have the `roles/aiplatform.user` role. To resolve this, re-run the `gcloud projects add-iam-policy-binding`.
+
+**Q: What should I do if I get a `429 Quota exceeded` error?**  
+A: This means you've hit the per-region QPM (queries per minute) or TPM (tokens per minute) quota. You can:
+- Request a quota increase from the [GCP Quotas console](https://console.cloud.google.com/iam-admin/quotas)
+- Add more regions to your LiteLLM configuration for load balancing
+- Upgrade to [Provisioned Throughput](https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput) for guaranteed capacity
+
+**Q: How do I fix the `VERTEXAI_PROJECT not set` error?**  
+A: Either pass the `vertex_project` parameter explicitly in your LiteLLM call, or set the `VERTEXAI_PROJECT` environment variable before running your code.
+

docs/my-website/docs/vertex_batch_passthrough.md

@@ -155,6 +155,6 @@ Common error scenarios and their solutions:
 
 ## Related Documentation
 
-- [Vertex AI Provider Documentation](./vertex.md)
-- [General Batches API Documentation](../batches.md)
-- [Cost Tracking and Monitoring](../observability/telemetry.md)
+- [Vertex AI Provider Documentation](./providers/vertex.md)
+- [General Batches API Documentation](./batches.md)
+- [Cost Tracking and Monitoring](./observability/telemetry.md)

docs/my-website/docusaurus.config.js

@@ -2,9 +2,9 @@
 // Note: type annotations allow type checking and IDEs autocompletion
 
 // @ts-ignore
-const lightCodeTheme = require('prism-react-renderer/themes/github');
+const lightCodeTheme = require('prism-react-renderer/themes/vsLight');
 // @ts-ignore
-const darkCodeTheme = require('prism-react-renderer/themes/dracula');
+const darkCodeTheme = require('prism-react-renderer/themes/nightOwl');
 
 const inkeepConfig = {
   baseSettings: {
@@ -87,18 +87,88 @@ const config = {
       },
     ],
     [
-      '@docusaurus/plugin-content-blog',
+      '@docusaurus/plugin-content-docs',
       {
-        id: 'release_notes',
+        id: 'release-notes',
         path: './release_notes',
         routeBasePath: 'release_notes',
-        blogTitle: 'Release Notes',
-        blogSidebarTitle: 'Releases',
-        blogSidebarCount: 'ALL',
-        postsPerPage: 'ALL',
-        showReadingTime: false,
-        sortPosts: 'descending',
-        include: ['**/*.{md,mdx}'],
+        sidebarPath: require.resolve('./sidebars-release-notes.js'),
+        async sidebarItemsGenerator({defaultSidebarItemsGenerator, docs, ...args}) {
+          const items = await defaultSidebarItemsGenerator({docs, ...args});
+
+          // Build map of doc id -> year from frontmatter date
+          const docYearMap = {};
+          for (const doc of docs) {
+            const date = doc.frontMatter && doc.frontMatter.date;
+            if (date) {
+              const year = new Date(date).getFullYear();
+              docYearMap[doc.id] = year;
+            }
+          }
+
+          function parseVersion(str) {
+            const match = (str || '').match(/v?(\d+)\.(\d+)\.(\d+)/);
+            if (!match) return [0, 0, 0];
+            return [parseInt(match[1]), parseInt(match[2]), parseInt(match[3])];
+          }
+          function compareVersionsDesc(a, b) {
+            const [aMaj, aMin, aPatch] = parseVersion(a.label || a.id || '');
+            const [bMaj, bMin, bPatch] = parseVersion(b.label || b.id || '');
+            if (bMaj !== aMaj) return bMaj - aMaj;
+            if (bMin !== aMin) return bMin - aMin;
+            return bPatch - aPatch;
+          }
+
+          // Flatten and transform doc items (filter index, shorten labels)
+          function flattenDocs(list) {
+            const result = [];
+            for (const item of list) {
+              if (item.type === 'doc' && item.id === 'index') continue;
+              if (item.type === 'doc') {
+                const label = item.id.replace(/\/index$/, '');
+                result.push({...item, label});
+              } else if (item.type === 'category') {
+                if (item.link && item.link.type === 'doc' && item.link.id !== 'index') {
+                  const id = item.link.id;
+                  const label = id.replace(/\/index$/, '');
+                  result.push({type: 'doc', id, label});
+                } else {
+                  result.push(...flattenDocs(item.items));
+                }
+              }
+            }
+            return result;
+          }
+
+          const docItems = flattenDocs(items);
+
+          // Group by year
+          const byYear = {};
+          for (const item of docItems) {
+            const year = docYearMap[item.id] || 'Other';
+            if (!byYear[year]) byYear[year] = [];
+            byYear[year].push(item);
+          }
+
+          // Sort each year's items by version descending
+          for (const year of Object.keys(byYear)) {
+            byYear[year].sort(compareVersionsDesc);
+          }
+
+          // Build categories sorted by year descending
+          const years = Object.keys(byYear).sort((a, b) => {
+            // Object.keys() returns strings; avoid numeric subtraction type errors.
+            const na = Number.parseInt(a, 10);
+            const nb = Number.parseInt(b, 10);
+            return nb - na;
+          });
+          return years.map(year => ({
+            type: 'category',
+            label: String(year),
+            collapsed: year !== String(years[0]),
+            items: byYear[year],
+          }));
+        },
       },
     ],
     [
@@ -130,6 +200,20 @@ const config = {
         };
       },
     }),
+    // Ensure gtag exists before the GA script loads.
+    () => ({
+      name: 'gtag-shim',
+      injectHtmlTags() {
+        return {
+          headTags: [
+            {
+              tagName: 'script',
+              innerHTML: `window.dataLayer=window.dataLayer||[];function gtag(){dataLayer.push(arguments);}if(!window.gtag){window.gtag=gtag;}`,
+            },
+          ],
+        };
+      },
+    }),
   ],
 
   presets: [
@@ -137,10 +221,13 @@ const config = {
       'classic',
       /** @type {import('@docusaurus/preset-classic').Options} */
       ({
-        gtag: {
-          trackingID: 'G-K7K215ZVNC',
-          anonymizeIP: true,
-        },
+        gtag:
+          process.env.NODE_ENV === 'production'
+            ? {
+                trackingID: 'G-K7K215ZVNC',
+                anonymizeIP: true,
+              }
+            : undefined,
         docs: {
           sidebarPath: require.resolve('./sidebars.js'),
         },
@@ -181,34 +268,39 @@ const config = {
             label: 'Docs',
           },
           {
+            type: 'docSidebar',
+            sidebarId: 'learnSidebar',
+            position: 'left',
+            label: 'Learn',
+          },
+          {
+            type: 'docSidebar',
             sidebarId: 'integrationsSidebar',
             position: 'left',
             label: 'Integrations',
-            to: "docs/integrations"
           },
           {
-            sidebarId: 'tutorialSidebar',
             position: 'left',
             label: 'Enterprise',
             to: "docs/enterprise"
           },
-          { to: '/release_notes', label: 'Release Notes', position: 'left' },
           { to: '/blog', label: 'Blog', position: 'left' },
-          {
-            href: 'https://models.litellm.ai/',
-            label: '💸 LLM Model Cost Map',
-            position: 'right',
-          },
           {
             href: 'https://github.com/BerriAI/litellm',
-            label: 'GitHub',
             position: 'right',
+            className: 'header-github-link',
+            'aria-label': 'GitHub repository',
           },
           {
             href: 'https://www.litellm.ai/support',
-            label: 'Slack/Discord',
             position: 'right',
-          }
+            className: 'header-discord-link',
+            'aria-label': 'Discord / Slack community',
+          },
+          {
+            type: 'search',
+            position: 'right',
+          },
         ],
       },
       footer: {

docs/my-website/release_notes/index.md

@@ -0,0 +1,52 @@
+---
+title: Release Notes
+sidebar_label: Overview
+slug: /
+---
+
+# Release Notes
+
+LiteLLM ships new releases regularly with new provider support, performance improvements, and enterprise features. Use the sidebar to browse all releases.
+
+## Latest Release
+
+### [v1.82.3 — Nebius AI, gpt-5.4, Gemini 3.x, FLUX Kontext, and 116 New Models](/release_notes/v1.82.3/v1-82-3)
+
+_March 16, 2026_
+
+116 new models including Nebius AI, gpt-5.4, Gemini 3.x, and FLUX Kontext.
+
+---
+
+## Recent Releases
+
+| Version                             | Date         | Highlights                                                 |
+| ----------------------------------- | ------------ | ---------------------------------------------------------- |
+| [v1.82.0](/release_notes/v1.82.0/v1-82-0)   | Feb 28, 2026 | Realtime Guardrails, Projects Management, and 10+ Performance Optimizations |
+| [v1.81.14](/release_notes/v1.81.14/v1-81-14) | Feb 21, 2026 | New Gateway Level Guardrails & Compliance Playground       |
+| [v1.81.12](/release_notes/v1.81.12/v1-81-12) | Feb 14, 2026 | Guardrail Policy Templates & Action Builder                |
+| [v1.81.9](/release_notes/v1.81.9/v1-81-9)   | Feb 7, 2026  | Control which MCP Servers are exposed on the Internet      |
+| [v1.81.6](/release_notes/v1.81.6/v1-81-6)   | Jan 31, 2026 | Logs v2 with Tool Call Tracing                             |
+| [v1.81.3](/release_notes/v1.81.3-stable/v1-81-3)   | Jan 26, 2026 | Performance — 25% CPU Usage Reduction                      |
+| [v1.81.0](/release_notes/v1.81.0/v1-81-0)          | Jan 18, 2026 | Claude Code — Web Search Across All Providers              |
+| [v1.80.15](/release_notes/v1.80.15/v1-80-15)       | Jan 10, 2026 | Manus API Support                                          |
+| [v1.80.8](/release_notes/v1.80.8-stable/v1-80-8)   | Dec 6, 2025  | Introducing A2A Agent Gateway                              |
+| [v1.80.5](/release_notes/v1.80.5-stable/v1-80-5)   | Nov 22, 2025 | Gemini 3.0 Support                                         |
+| [v1.80.0](/release_notes/v1.80.0-stable/v1-80-0)   | Nov 15, 2025 | Introducing Agent Hub: Register, Publish, and Share Agents |
+| [v1.79.3](/release_notes/v1.79.3-stable/v1-79-3)   | Nov 8, 2025  | Built-in Guardrails on AI Gateway                          |
+| [v1.79.0](/release_notes/v1.79.0-stable/v1-79-0)   | Oct 26, 2025 | Search APIs                                                |
+| [v1.78.5](/release_notes/v1.78.5-stable/v1-78-5)   | Oct 18, 2025 | Native OCR Support                                         |
+| [v1.78.0](/release_notes/v1.78.0-stable/v1-78-0)   | Oct 11, 2025 | MCP Gateway: Control Tool Access by Team, Key              |
+| [v1.77.7](/release_notes/v1.77.7-stable/v1-77-7)   | Oct 4, 2025  | 2.9x Lower Median Latency                                  |
+| [v1.77.5](/release_notes/v1.77.5-stable/v1-77-5)   | Sep 29, 2025 | MCP OAuth 2.0 Support                                      |
+| [v1.77.3](/release_notes/v1.77.3-stable/v1-77-3)   | Sep 21, 2025 | Priority Based Rate Limiting                               |
+
+---
+
+## Stay Updated
+
+- **GitHub**: Watch the [BerriAI/litellm](https://github.com/BerriAI/litellm) repository for release notifications
+- **Discord**: Join our [community](https://discord.com/invite/wuPM9dRgDw) for announcements
+- **Twitter**: Follow [@LiteLLM](https://twitter.com/LiteLLM)
+
+Use the sidebar to browse the full release history.

docs/my-website/release_notes/v1.63.14/index.md

@@ -62,10 +62,10 @@ Here's a Demo Instance to test changes:
    - Infer aws region from bedrock application profile id - (`arn:aws:bedrock:us-east-1:...`)
 - Ollama - support calling via `/v1/completions` [Get Started](../../docs/providers/ollama#using-ollama-fim-on-v1completions)
 - Bedrock - support `us.deepseek.r1-v1:0` model name [Docs](../../docs/providers/bedrock#supported-aws-bedrock-models)
-- OpenRouter - `OPENROUTER_API_BASE` env var support [Docs](../../docs/providers/openrouter.md)
+- OpenRouter - `OPENROUTER_API_BASE` env var support [Docs](../../docs/providers/openrouter)
 - Azure - add audio model parameter support - [Docs](../../docs/providers/azure#azure-audio-model)
 - OpenAI - PDF File support [Docs](../../docs/completion/document_understanding#openai-file-message-type)
-- OpenAI - o1-pro Responses API streaming support [Docs](../../docs/response_api.md#streaming)
+- OpenAI - o1-pro Responses API streaming support [Docs](../../docs/response_api#streaming)
 - [BETA] MCP - Use MCP Tools with LiteLLM SDK [Docs](../../docs/mcp)
 
 2. **Bug Fixes**
@@ -102,7 +102,7 @@ Here's a Demo Instance to test changes:
    - fix logging to just log the LLM I/O [PR](https://github.com/BerriAI/litellm/pull/9353)
    - Dynamic API Key/Space param support [Get Started](../../docs/observability/arize_integration#pass-arize-spacekey-per-request)
 - StandardLoggingPayload - Log litellm_model_name in payload. Allows knowing what the model sent to API provider was [Get Started](../../docs/proxy/logging_spec#standardlogginghiddenparams)
-- Prompt Management - Allow building custom prompt management integration [Get Started](../../docs/proxy/custom_prompt_management.md)
+- Prompt Management - Allow building custom prompt management integration [Get Started](../../docs/proxy/custom_prompt_management)
 
 ## Performance / Reliability improvements
 
@@ -128,4 +128,4 @@ Here's a Demo Instance to test changes:
 
 ## Complete Git Diff
 
-[Here's the complete git diff](https://github.com/BerriAI/litellm/compare/v1.63.11-stable...v1.63.14.rc)
+[Here's the complete git diff](https://github.com/BerriAI/litellm/compare/v1.63.11-stable...v1.63.14.rc)

docs/my-website/release_notes/v1.63.2-stable/index.md

@@ -64,15 +64,15 @@ Here's a Demo Instance to test changes:
 9. Bedrock - handle thinking blocks in assistant message. [Get Started](https://docs.litellm.ai/docs/providers/bedrock#usage---thinking--reasoning-content)
 10. Anthropic - Return `signature` on streaming. [Get Started](https://docs.litellm.ai/docs/providers/bedrock#usage---thinking--reasoning-content)
 - Note: We've also migrated from `signature_delta` to `signature`. [Read more](https://docs.litellm.ai/release_notes/v1.63.0)
-11. Support format param for specifying image type. [Get Started](../../docs/completion/vision.md#explicitly-specify-image-type)
-12. Anthropic - `/v1/messages` endpoint - `thinking` param support. [Get Started](../../docs/anthropic_unified.md)
+11. Support format param for specifying image type. [Get Started](../../docs/completion/vision#explicitly-specify-image-type)
+12. Anthropic - `/v1/messages` endpoint - `thinking` param support. [Get Started](../../docs/anthropic_unified)
 - Note: this refactors the [BETA] unified `/v1/messages` endpoint, to just work for the Anthropic API. 
 13. Vertex AI - handle $id in response schema when calling vertex ai. [Get Started](https://docs.litellm.ai/docs/providers/vertex#json-schema)
 
 ## Spend Tracking Improvements
 
 1. Batches API - Fix cost calculation to run on retrieve_batch. [Get Started](https://docs.litellm.ai/docs/batches)
-2. Batches API - Log batch models in spend logs / standard logging payload. [Get Started](../../docs/proxy/logging_spec.md#standardlogginghiddenparams)
+2. Batches API - Log batch models in spend logs / standard logging payload. [Get Started](../../docs/proxy/logging_spec#standardlogginghiddenparams)
 
 ## Management Endpoints / UI
 
@@ -109,4 +109,4 @@ Here's a Demo Instance to test changes:
 
 ## Complete Git Diff
 
-[Here's the complete git diff](https://github.com/BerriAI/litellm/compare/v1.61.20-stable...v1.63.2-stable)
+[Here's the complete git diff](https://github.com/BerriAI/litellm/compare/v1.61.20-stable...v1.63.2-stable)

docs/my-website/release_notes/v1.80.15/index.md

@@ -53,7 +53,7 @@ pip install litellm==1.80.15
 - **MCP Global Mode** - [Configure MCP servers globally with visibility controls](../../docs/mcp)
 - **Interactions API Bridge** - [Use all LiteLLM providers with the Interactions API](../../docs/interactions)
 - **RAG Query Endpoint** - [New RAG Search/Query endpoint for retrieval-augmented generation](../../docs/search/index)
-- **UI Usage - Endpoint Activity** - [Users can now see Endpoint Activity Metrics in the UI](../../docs/proxy/endpoint_activity.md)
+- **UI Usage - Endpoint Activity** - [Users can now see Endpoint Activity Metrics in the UI](../../docs/proxy/endpoint_activity)
 - **50% Overhead Reduction** - LiteLLM now sends 2.5× more requests to LLM providers
 
 
@@ -640,4 +640,3 @@ Users can now see Endpoint Activity Metrics in the UI.
 
 **[View complete changelog on GitHub](https://github.com/BerriAI/litellm/compare/v1.80.11.rc.1...v1.80.15-stable.1)**
 
-

docs/my-website/release_notes/v1.81.0/index.md

@@ -48,7 +48,7 @@ pip install litellm==1.81.0
 - **Claude Code** - Support for using web search across Bedrock, Vertex AI, and all LiteLLM providers
 - **Major Change** - [50MB limit on image URL downloads](#major-change---chatcompletions-image-url-download-size-limit) to improve reliability
 - **Performance** - [25% CPU Usage Reduction](#performance---25-cpu-usage-reduction) by removing premature model.dump() calls from the hot path
-- **Deleted Keys Audit Table on UI** - [View deleted keys and teams for audit purposes](../../docs/proxy/deleted_keys_teams.md) with spend and budget information at the time of deletion
+- **Deleted Keys Audit Table on UI** - [View deleted keys and teams for audit purposes](../../docs/proxy/deleted_keys_teams) with spend and budget information at the time of deletion
 
 ---
 
@@ -166,7 +166,7 @@ LiteLLM now reduces CPU usage by removing premature `model.dump()` calls from th
 
 <Image img={require('../../img/ui_deleted_keys_table.png')} />
 
-LiteLLM now provides a comprehensive audit table for deleted API keys and teams directly in the UI. This feature allows you to easily track the spend of deleted keys, view their associated team information, and maintain accurate financial records for auditing and compliance purposes. The table displays key details including key aliases, team associations, and spend information captured at the time of deletion. For more information on how to use this feature, see the [Deleted Keys & Teams documentation](../../docs/proxy/deleted_keys_teams.md).
+LiteLLM now provides a comprehensive audit table for deleted API keys and teams directly in the UI. This feature allows you to easily track the spend of deleted keys, view their associated team information, and maintain accurate financial records for auditing and compliance purposes. The table displays key details including key aliases, team associations, and spend information captured at the time of deletion. For more information on how to use this feature, see the [Deleted Keys & Teams documentation](../../docs/proxy/deleted_keys_teams).
 
 ---
 

docs/my-website/release_notes/v1.81.12/index.md

@@ -62,13 +62,13 @@ This release fixes out-of-memory (OOM) risks from unbounded `asyncio.Queue()` us
 
 This release adds a visual action builder for guardrail policies with conditional execution support. You can now chain guardrails into multi-step pipelines — if a simple guardrail fails, route to an advanced one instead of immediately blocking. Each step has configurable ON PASS and ON FAIL actions (Next Step, Block, or Allow), and you can test the full pipeline with a sample message before saving.
 
-![Guardrail Action Builder](../img/release_notes/guard_actions.png)
+![Guardrail Action Builder](../../img/release_notes/guard_actions.png)
 
 ### Access Groups
 
 Access Groups simplify defining resource access across your organization. One group can grant access to models, MCP servers, and agents—simply attach it to a key or team. Create groups in the Admin UI, define which resources each group includes, then assign the group when creating keys or teams. Updates to a group apply automatically to all attached keys and teams.
 
-<Image img={require('../img/ui_access_groups.png')} />
+<Image img={require('../../img/ui_access_groups.png')} />
 
 ## New Providers and Endpoints
 

docs/my-website/release_notes/v1.81.14/index.md

@@ -56,7 +56,7 @@ pip install litellm==1.81.14
 
 AI Platform Admins can now browse built-in and partner guardrails from the Guardrail Garden. Guardrails are organized by use case — blocking financial advice, filtering insults, detecting competitor mentions, and more — so you can find the right one and deploy it in a few clicks.
 
-![Guardrail Garden](../img/release_notes/guardrail_garden.png)
+![Guardrail Garden](../../img/release_notes/guardrail_garden.png)
 
 ### 3 New Built-in Guardrails
 
@@ -72,7 +72,7 @@ These guardrails are built for production and on our benchmarks had a 100% Recal
 
 Previously, the `store_model_in_db` setting could only be configured in `proxy_config.yaml` under `general_settings`, requiring a proxy restart to take effect. Now you can enable or disable this setting directly from the Admin UI without any restarts. This is especially useful for cloud deployments where you don't have direct access to config files or want to avoid downtime. Enable `store_model_in_db` to move model definitions from your YAML into the database—reducing config complexity, improving scalability, and enabling dynamic model management across multiple proxy instances.
 
-![Store model in DB Setting](../img/ui_store_model_in_db.png)
+![Store model in DB Setting](../../img/ui_store_model_in_db.png)
 
 
 #### Eval results
@@ -91,14 +91,14 @@ We benchmarked our new built-in guardrails against labeled datasets before shipp
 
 The Compliance Playground lets you test any guardrail against our pre-built eval datasets or your own custom datasets, so you can see precision, recall, and false positive rate before rolling it out to production.
 
-![Compliance Playground](../img/release_notes/compliance_playground.png)
+![Compliance Playground](../../img/release_notes/compliance_playground.png)
 
 
 ---
 
 ## Performance & Reliability — Up to 13% Lower Latency
 
-<Image img={require('../img/release_notes/v1_81_14_perf.png')} />
+<Image img={require('../../img/release_notes/v1_81_14_perf.png')} />
 
 This release cuts latency across all percentiles through 20+ micro-optimizations across logging, cost calculation, routing, and connection management. See [benchmarking](../../docs/benchmarks) for more info about how to benchmark yourself. 
 

docs/my-website/release_notes/v1.81.9/index.md

@@ -81,7 +81,7 @@ This release makes it safe to expose MCP servers on the public internet by addin
 [Get started](../../docs/mcp_public_internet)
 
 <Image
-img={require('../img/release_notes/mcp_internet.png')}
+img={require('../../img/release_notes/mcp_internet.png')}
 style={{ maxWidth: '900px', width: '100%' }}
 />
 
@@ -92,7 +92,7 @@ Set a soft budget on any team to receive email alerts when spending crosses the
 [Get started](../../docs/proxy/ui_team_soft_budget_alerts)
 
 <Image
-img={require('../img/ui_team_soft_budget_alerts.png')}
+img={require('../../img/ui_team_soft_budget_alerts.png')}
 style={{ maxWidth: '900px', width: '100%' }}
 />
 

docs/my-website/release_notes/v1.82.3/index.md

@@ -0,0 +1,530 @@
+---
+title: "v1.82.3 - Nebius AI, gpt-5.4, Gemini 3.x, FLUX Kontext, and 116 New Models"
+slug: "v1-82-3"
+date: 2026-03-16T00:00:00
+authors:
+  - name: Krrish Dholakia
+    title: CEO, LiteLLM
+    url: https://www.linkedin.com/in/krish-d/
+    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - name: Ishaan Jaff
+    title: CTO, LiteLLM
+    url: https://www.linkedin.com/in/reffajnaahsi/
+    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+hide_table_of_contents: false
+---
+
+## Deploy this version
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+<Tabs>
+<TabItem value="docker" label="Docker">
+
+``` showLineNumbers title="docker run litellm"
+docker run \
+-e STORE_MODEL_IN_DB=True \
+-p 4000:4000 \
+ghcr.io/berriai/litellm:main-1.82.3-stable
+```
+
+</TabItem>
+<TabItem value="pip" label="Pip">
+
+``` showLineNumbers title="pip install litellm"
+pip install litellm==1.82.3
+```
+
+</TabItem>
+</Tabs>
+
+## Key Highlights
+
+- **Nebius AI — new provider** — [30 models across DeepSeek, Qwen, Llama, Mistral, NVIDIA, and BAAI available via Nebius AI cloud](../../docs/providers/nebius) - [PR #22614](https://github.com/BerriAI/litellm/pull/22614)
+- **OpenAI gpt-5.4 / gpt-5.4-pro — day 0** — Full pricing and routing support for `gpt-5.4` (1M context, $2.50/$15.00) and `gpt-5.4-pro` ($30.00/$180.00) on OpenAI and Azure
+- **Gemini 3.x models** — `gemini-3-flash-preview`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-image-preview`, and `gemini-embedding-2-preview` added to cost map for Google AI and Vertex AI
+- **FLUX Kontext image editing** — `flux-kontext-pro` and `flux-kontext-max` added to Black Forest Labs, alongside `flux-pro-1.0-fill` and `flux-pro-1.0-expand` for inpainting and outpainting
+- **116 new models, 132 deprecated models cleaned up** — Major model map refresh including Mistral Magistral, Dashscope Qwen3 VL, xAI Grok via Azure AI, ZAI GLM-5, Serper Search; removal of OpenAI GPT-3.5/GPT-4 legacy variants, Gemini 1.5, and Vertex AI PaLM2
+- **SageMaker Nova provider** — [New `sagemaker_nova` provider for Amazon Nova models on SageMaker](../../docs/providers/aws_sagemaker) - [PR #21542](https://github.com/BerriAI/litellm/pull/21542)
+- **Hashicorp Vault secret manager** — Config override backend powered by Hashicorp Vault, with full UI for managing vault-sourced credentials - [PR #22939](https://github.com/BerriAI/litellm/pull/22939), [PR #23036](https://github.com/BerriAI/litellm/pull/23036)
+- **Responses API WebSocket streaming** — Real-time WebSocket streaming for the Responses API, including support across all providers - [PR #22559](https://github.com/BerriAI/litellm/pull/22559), [PR #22771](https://github.com/BerriAI/litellm/pull/22771)
+- **Org Admin RBAC expansion** — Org Admins can now access team management endpoints, view and invite internal users, and manage team membership without requiring a global admin role - [PR #23085](https://github.com/BerriAI/litellm/pull/23085), [PR #23080](https://github.com/BerriAI/litellm/pull/23080)
+- **Guardrail mode defaults and tag-based modes** — Set a default guardrail mode list globally, and specify a list of modes in tag-based guardrail configs - [PR #22676](https://github.com/BerriAI/litellm/pull/22676), [PR #23020](https://github.com/BerriAI/litellm/pull/23020)
+- **Secret redaction in logs** — API keys, tokens, and credentials automatically scrubbed from all proxy log output. Enabled by default; opt out with `LITELLM_DISABLE_REDACT_SECRETS=true` - [PR #23668](https://github.com/BerriAI/litellm/pull/23668)
+- **Streaming stability fix** — Critical fix for `RuntimeError: Cannot send a request, as the client has been closed.` crashes after ~1 hour in production - [PR #22926](https://github.com/BerriAI/litellm/pull/22926)
+
+---
+
+## New Providers and Endpoints
+
+### New Providers (7 new providers)
+
+| Provider | Supported LiteLLM Endpoints | Description |
+| -------- | --------------------------- | ----------- |
+| [Nebius AI](../../docs/providers/nebius) (`nebius/`) | `/chat/completions`, `/embeddings` | EU-based AI cloud with 30+ open models — DeepSeek, Qwen3, Llama 3.1/3.3, NVIDIA Nemotron, BAAI embeddings |
+| [ZAI](../../docs/providers/zai) (`zai/`) | `/chat/completions` | ZhipuAI GLM-5 models via ZAI cloud |
+| [Black Forest Labs](../../docs/providers/black_forest_labs) (`black_forest_labs/`) | `/images/generations`, `/images/edits` | FLUX image generation and editing — Kontext Pro/Max, Pro 1.0 Fill/Expand |
+| [Serper](../../docs/providers/serper) (`serper/`) | `/search` | Web search via Serper API |
+| [SageMaker Nova](../../docs/providers/aws_sagemaker) (`sagemaker_nova/`) | `/chat/completions` | Amazon Nova models via SageMaker endpoint |
+| [Google Search API](../../docs/providers/google_search) (`google_search/`) | `/search` | Google Search API integration - [PR #22752](https://github.com/BerriAI/litellm/pull/22752) |
+| [Bedrock Mantle](../../docs/providers/bedrock) (`bedrock_mantle/`) | `/chat/completions` | Amazon Bedrock via Mantle — alternative auth and routing path for Bedrock models - [PR #22866](https://github.com/BerriAI/litellm/pull/22866) |
+
+---
+
+## New Models / Updated Models
+
+#### New Model Support (116 new models)
+
+| Provider | Model | Context Window | Input ($/1M tokens) | Output ($/1M tokens) | Features |
+| -------- | ----- | -------------- | ------------------- | -------------------- | -------- |
+| OpenAI | `gpt-5.4` | 1.05M | $2.50 | $15.00 | chat, vision, tools, reasoning |
+| OpenAI | `gpt-5.4-pro` | 1.05M | $30.00 | $180.00 | responses, vision, tools, reasoning |
+| OpenAI | `gpt-5.3-chat-latest` | 128K | $1.75 | $14.00 | chat, vision, tools, reasoning |
+| Azure OpenAI | `azure/gpt-5.4` | 1.05M | $2.50 | $15.00 | chat, vision, tools, reasoning |
+| Azure OpenAI | `azure/gpt-5.4-pro` | 1.05M | $30.00 | $180.00 | responses, vision, tools, reasoning |
+| Azure OpenAI | `azure/gpt-5.3-chat` | 128K | $1.75 | $14.00 | chat, vision, tools, reasoning |
+| Google Gemini | `gemini/gemini-3-flash-preview` | 1M | $0.50 | $3.00 | chat, vision, tools, reasoning |
+| Google Gemini | `gemini/gemini-3.1-pro-preview` | 1M | $2.00 | $12.00 | chat, vision, tools, reasoning |
+| Google Gemini | `gemini/gemini-3.1-flash-image-preview` | 65K | $0.25 | $1.50 | image generation, vision |
+| Google Gemini | `gemini/gemini-3.1-flash-lite-preview` | - | - | - | chat |
+| Google Gemini | `gemini/gemini-3-pro-image-preview` | - | - | - | image generation |
+| Google Gemini | `gemini/gemini-embedding-2-preview` | 8K | $0.20 | - | embeddings |
+| Google Vertex AI | `vertex_ai/gemini-3-flash-preview` | - | - | - | chat |
+| Google Vertex AI | `vertex_ai/gemini-3.1-pro-preview` | - | - | - | chat |
+| Google Vertex AI | `vertex_ai/gemini-3.1-flash-lite-preview` | - | - | - | chat |
+| Google Vertex AI | `vertex_ai/gemini-embedding-2-preview` | - | $0.20 | - | embeddings |
+| Mistral | `mistral/magistral-medium-1-2-2509` | 40K | $2.00 | $5.00 | chat, tools, reasoning |
+| Mistral | `mistral/magistral-small-1-2-2509` | 40K | $0.50 | $1.50 | chat, tools, reasoning |
+| Mistral | `mistral/mistral-large-2512` | 262K | $0.50 | $1.50 | chat, vision, tools |
+| Mistral | `mistral/mistral-medium-3-1-2508` | - | - | - | chat |
+| Mistral | `mistral/mistral-small-3-2-2506` | - | - | - | chat |
+| Mistral | `mistral/ministral-3-3b-2512` | - | - | - | chat |
+| Mistral | `mistral/ministral-3-8b-2512` | - | - | - | chat |
+| Mistral | `mistral/ministral-3-14b-2512` | - | - | - | chat |
+| Black Forest Labs | `black_forest_labs/flux-kontext-pro` | - | - | - | image editing |
+| Black Forest Labs | `black_forest_labs/flux-kontext-max` | - | - | - | image editing |
+| Black Forest Labs | `black_forest_labs/flux-pro-1.0-fill` | - | - | - | image editing (inpaint) |
+| Black Forest Labs | `black_forest_labs/flux-pro-1.0-expand` | - | - | - | image editing (outpaint) |
+| Black Forest Labs | `black_forest_labs/flux-pro-1.1` | - | - | - | image generation |
+| Black Forest Labs | `black_forest_labs/flux-pro-1.1-ultra` | - | - | - | image generation |
+| Black Forest Labs | `black_forest_labs/flux-dev` | - | - | - | image generation |
+| Black Forest Labs | `black_forest_labs/flux-pro` | - | - | - | image generation |
+| Azure AI | `azure_ai/grok-4-1-fast-non-reasoning` | 131K | $0.20 | $0.50 | chat, tools |
+| Azure AI | `azure_ai/grok-4-1-fast-reasoning` | 131K | $0.20 | $0.50 | chat, tools, reasoning |
+| Azure AI | `azure_ai/mistral-document-ai-2512` | - | - | - | OCR |
+| Dashscope | `dashscope/qwen3-next-80b-a3b-instruct` | 262K | $0.15 | $1.20 | chat |
+| Dashscope | `dashscope/qwen3-next-80b-a3b-thinking` | 262K | $0.15 | $1.20 | chat, reasoning |
+| Dashscope | `dashscope/qwen3-vl-235b-a22b-instruct` | 131K | $0.40 | $1.60 | chat, vision |
+| Dashscope | `dashscope/qwen3-vl-235b-a22b-thinking` | 131K | $0.40 | $4.00 | chat, vision, reasoning |
+| Dashscope | `dashscope/qwen3-vl-32b-instruct` | 131K | $0.16 | $0.64 | chat, vision |
+| Dashscope | `dashscope/qwen3-vl-32b-thinking` | 131K | $0.16 | $2.87 | chat, vision, reasoning |
+| Dashscope | `dashscope/qwen3-vl-plus` | 260K | - | - | chat, vision |
+| Dashscope | `dashscope/qwen3.5-plus` | 992K | - | - | chat |
+| Dashscope | `dashscope/qwen3-max-2026-01-23` | 258K | - | - | chat |
+| Nebius AI | `nebius/deepseek-ai/DeepSeek-R1` | 128K | $0.80 | $2.40 | chat, reasoning |
+| Nebius AI | `nebius/deepseek-ai/DeepSeek-R1-0528` | 164K | $0.80 | $2.40 | chat, reasoning |
+| Nebius AI | `nebius/deepseek-ai/DeepSeek-V3` | 128K | $0.50 | $1.50 | chat |
+| Nebius AI | `nebius/deepseek-ai/DeepSeek-V3-0324` | 128K | $0.50 | $1.50 | chat |
+| Nebius AI | `nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B` | 128K | $0.25 | $0.75 | chat |
+| Nebius AI | `nebius/Qwen/Qwen3-235B-A22B` | 262K | $0.20 | $0.60 | chat |
+| Nebius AI | `nebius/Qwen/Qwen3-32B` | 32K | $0.10 | $0.30 | chat |
+| Nebius AI | `nebius/Qwen/Qwen3-30B-A3B` | 32K | $0.10 | $0.30 | chat |
+| Nebius AI | `nebius/Qwen/Qwen3-14B` | 32K | $0.08 | $0.24 | chat |
+| Nebius AI | `nebius/Qwen/Qwen3-4B` | 32K | $0.08 | $0.24 | chat |
+| Nebius AI | `nebius/Qwen/QwQ-32B` | 32K | $0.15 | $0.45 | chat |
+| Nebius AI | `nebius/Qwen/Qwen2.5-72B-Instruct` | 128K | $0.13 | $0.40 | chat |
+| Nebius AI | `nebius/Qwen/Qwen2.5-32B-Instruct` | 128K | $0.06 | $0.20 | chat |
+| Nebius AI | `nebius/Qwen/Qwen2.5-VL-72B-Instruct` | 131K | $0.13 | $0.40 | chat, vision |
+| Nebius AI | `nebius/Qwen/Qwen2-VL-72B-Instruct` | 131K | $0.13 | $0.40 | chat, vision |
+| Nebius AI | `nebius/Qwen/Qwen2-VL-7B-Instruct` | 131K | $0.02 | $0.06 | chat, vision |
+| Nebius AI | `nebius/meta-llama/Meta-Llama-3.1-405B-Instruct` | 128K | $1.00 | $3.00 | chat |
+| Nebius AI | `nebius/meta-llama/Meta-Llama-3.1-70B-Instruct` | 128K | $0.13 | $0.40 | chat |
+| Nebius AI | `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct` | 128K | $0.02 | $0.06 | chat |
+| Nebius AI | `nebius/meta-llama/Llama-3.3-70B-Instruct` | 128K | $0.13 | $0.40 | chat |
+| Nebius AI | `nebius/meta-llama/Llama-Guard-3-8B` | 128K | $0.02 | $0.06 | chat |
+| Nebius AI | `nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1` | 128K | $0.60 | $1.80 | chat |
+| Nebius AI | `nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1` | 131K | $0.10 | $0.40 | chat |
+| Nebius AI | `nebius/NousResearch/Hermes-3-Llama-3.1-405B` | 128K | $1.00 | $3.00 | chat |
+| Nebius AI | `nebius/google/gemma-3-27b-it` | 128K | $0.06 | $0.20 | chat |
+| Nebius AI | `nebius/mistralai/Mistral-Nemo-Instruct-2407` | 128K | $0.04 | $0.12 | chat |
+| Nebius AI | `nebius/Qwen/Qwen2.5-Coder-7B` | 32K | $0.01 | $0.03 | chat |
+| Nebius AI | `nebius/BAAI/bge-en-icl` | 32K | $0.01 | - | embeddings |
+| Nebius AI | `nebius/BAAI/bge-multilingual-gemma2` | 8K | $0.01 | - | embeddings |
+| Nebius AI | `nebius/intfloat/e5-mistral-7b-instruct` | 32K | $0.01 | - | embeddings |
+| AWS Bedrock | `mistral.devstral-2-123b` | 256K | $0.40 | $2.00 | chat, tools |
+| AWS Bedrock | `zai.glm-4.7-flash` | 200K | $0.07 | $0.40 | chat, tools, reasoning |
+| ZAI | `zai/glm-5` | 200K | $1.00 | $3.20 | chat, tools, reasoning |
+| ZAI | `zai/glm-5-code` | 200K | $1.20 | $5.00 | chat, tools, reasoning |
+| OpenRouter | `openrouter/anthropic/claude-sonnet-4.6` | - | - | - | chat |
+| OpenRouter | `openrouter/google/gemini-3.1-pro-preview` | - | - | - | chat |
+| OpenRouter | `openrouter/openai/gpt-5.1-codex-max` | - | - | - | chat |
+| OpenRouter | `openrouter/qwen/qwen3-coder-plus` | - | - | - | chat |
+| OpenRouter | `openrouter/qwen/qwen3.5-*` (5 models) | - | - | - | chat |
+| OpenRouter | `openrouter/z-ai/glm-5` | - | - | - | chat |
+| Together AI | `together_ai/Qwen/Qwen3.5-397B-A17B` | - | - | - | chat |
+| Perplexity | `perplexity/pplx-embed-v1-0.6b` | 32K | $0.00 | - | embeddings |
+| Perplexity | `perplexity/pplx-embed-v1-4b` | 32K | $0.03 | - | embeddings |
+| Serper | `serper/search` | - | - | - | search |
+
+#### Updated Models
+
+- **[AWS Bedrock](../../docs/providers/bedrock)**
+    - Add `cache_read_input_token_cost` and `cache_creation_input_token_cost` to Bedrock-hosted Anthropic models (`claude-3-opus`, `claude-3-sonnet`, `claude-3-haiku`, and APAC/EU variants) — prompt caching is now tracked for cost estimation
+    - Rename `apac.anthropic.claude-sonnet-4-6` → `au.anthropic.claude-sonnet-4-6` to reflect correct regional identifier
+
+- **[Azure OpenAI](../../docs/providers/azure)**
+    - Add `supports_none_reasoning_effort` to all `gpt-5.1-chat`, `gpt-5.1-codex`, and `gpt-5.4` variants (global, EU, standard deployments) — allows passing `reasoning_effort: null` to disable reasoning
+
+- **[Azure OpenAI](../../docs/providers/azure)** — Removed deprecated models
+    - Remove `azure/gpt-35-turbo-0301` (deprecated 2025-02-13)
+    - Remove `azure/gpt-35-turbo-0613` (deprecated 2025-02-13)
+
+#### Features
+
+- **[OpenAI](../../docs/providers/openai)**
+    - Day 0 support for `gpt-5.4` and `gpt-5.4-pro` on OpenAI and Azure
+
+- **[Google Gemini](../../docs/providers/gemini)**
+    - Add Gemini 3.x model cost map entries — `gemini-3-flash-preview`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3-pro-image-preview`, `gemini-embedding-2-preview`
+    - Add Gemini 2.0 Flash and Flash Lite to cost map (re-added with updated pricing)
+
+- **[Google Vertex AI](../../docs/providers/vertex)**
+    - Add `gemini-3-flash-preview`, `gemini-3.1-flash-lite-preview`, `gemini-flash-experimental`, and `gemini-embedding-2-preview` to Vertex AI model cost map
+
+- **[Mistral](../../docs/providers/mistral)**
+    - Add Magistral reasoning models (`magistral-medium-1-2-2509`, `magistral-small-1-2-2509`)
+    - Add `mistral-large-2512`, `mistral-medium-3-1-2508`, `mistral-small-3-2-2506`, `ministral-3-*` variants
+
+- **[Dashscope / Qwen](../../docs/providers/dashscope)**
+    - Add Qwen3 VL multimodal models (`qwen3-vl-235b`, `qwen3-vl-32b` — instruct and thinking variants)
+    - Add `qwen3-next-80b-a3b` (instruct + thinking), `qwen3.5-plus`, `qwen3-max-2026-01-23`
+
+- **[Black Forest Labs](../../docs/providers/black_forest_labs)**
+    - Add FLUX Kontext image editing models (`flux-kontext-pro`, `flux-kontext-max`)
+    - Add FLUX Pro 1.0 Fill (inpainting) and Expand (outpainting)
+    - Add `flux-pro-1.1`, `flux-pro-1.1-ultra`, `flux-dev`, `flux-pro`
+
+- **[Azure AI](../../docs/providers/azure_ai)**
+    - Add xAI Grok models via Azure AI Foundry (`grok-4-1-fast-non-reasoning`, `grok-4-1-fast-reasoning`)
+    - Add Mistral Document AI (`mistral-document-ai-2512`) — OCR mode
+
+- **[AWS Bedrock](../../docs/providers/bedrock)**
+    - Add `mistral.devstral-2-123b` (256K context, tools)
+    - Add `zai.glm-4.7-flash` via Bedrock Converse (200K context, tools, reasoning)
+
+- **[SageMaker](../../docs/providers/aws_sagemaker)**
+    - Add `sagemaker_nova` provider for Amazon Nova models on SageMaker - [PR #21542](https://github.com/BerriAI/litellm/pull/21542)
+
+#### Deprecated / Removed Models
+
+**OpenAI** — Legacy models removed from cost map:
+- `gpt-3.5-turbo-0301`, `gpt-3.5-turbo-0613`, `gpt-3.5-turbo-16k-0613`
+- `gpt-4-0314`, `gpt-4-32k`, `gpt-4-32k-0314`, `gpt-4-32k-0613`, `gpt-4-1106-vision-preview`, `gpt-4-vision-preview`
+- `gpt-4.5-preview`, `gpt-4.5-preview-2025-02-27`
+- `gpt-4o-audio-preview-2024-10-01`, `gpt-4o-realtime-preview-2024-10-01`
+- `o1-mini`, `o1-mini-2024-09-12`, `o1-preview`, `o1-preview-2024-09-12`
+
+**Google Gemini** — Gemini 1.5 and legacy 2.0 variants removed:
+- All `gemini-1.5-*` variants (flash, flash-8b, pro, and dated versions)
+- `gemini-2.0-flash-exp`, `gemini-2.0-pro-exp-02-05`, `gemini-2.5-flash-preview-04-17`, `gemini-2.5-flash-preview-05-20`
+
+**Google Vertex AI** — PaLM 2 / legacy models removed:
+- All `chat-bison`, `text-bison`, `codechat-bison`, `code-bison`, `code-gecko` variants
+- Gemini 1.0 Pro, 1.5 Flash/Pro, 2.0 Flash experimental, and preview variants
+
+**Perplexity** — Legacy Llama-sonar models removed:
+- `llama-3.1-sonar-huge-128k-online`, `llama-3.1-sonar-large/small-128k-chat/online`
+
+---
+
+## LLM API Endpoints
+
+#### Features
+
+- **[Responses API](../../docs/response_api)**
+    - Handle `response.failed`, `response.incomplete`, and `response.cancelled` terminal event types in background streaming — previously only `response.completed` was handled - [PR #23492](https://github.com/BerriAI/litellm/pull/23492)
+    - WebSocket streaming support for Responses API — real-time streaming via WebSocket for all providers - [PR #22559](https://github.com/BerriAI/litellm/pull/22559), [PR #22771](https://github.com/BerriAI/litellm/pull/22771)
+    - WebRTC support for real-time audio/video communication - [PR #23446](https://github.com/BerriAI/litellm/pull/23446)
+    - Responses API support for OpenAI-compatible JSON providers (`openai_like`) - [PR #21398](https://github.com/BerriAI/litellm/pull/21398)
+    - Route `gpt-5.4+` calls using both tools and reasoning to the Responses API automatically - [PR #23577](https://github.com/BerriAI/litellm/pull/23577)
+
+- **[Anthropic Files API](../../docs/providers/anthropic)**
+    - Full Anthropic Files API support — upload, retrieve, list, and delete files; use file references in messages - [PR #16594](https://github.com/BerriAI/litellm/pull/16594)
+
+- **[Mistral](../../docs/providers/mistral)**
+    - Voxtral audio transcription support — `mistral/voxtral-mini-*` and `mistral/voxtral-*` for audio transcription via Mistral - [PR #22801](https://github.com/BerriAI/litellm/pull/22801)
+
+- **[OpenAI](../../docs/providers/openai)**
+    - `litellm.acount_tokens()` public API — async token counting with full OpenAI provider support - [PR #22809](https://github.com/BerriAI/litellm/pull/22809)
+    - Normalize `reasoning_effort` dict to string for chat completion API - [PR #22981](https://github.com/BerriAI/litellm/pull/22981)
+
+- **[OpenRouter](../../docs/providers/openrouter)**
+    - Image edit support for OpenRouter models - [PR #22403](https://github.com/BerriAI/litellm/pull/22403)
+
+- **[Google Vertex AI](../../docs/providers/vertex)**
+    - VIDEO modality token usage tracking in `completion_tokens_details` - [PR #22550](https://github.com/BerriAI/litellm/pull/22550)
+
+- **Images API**
+    - `input_fidelity` parameter for image edit API - [PR #23201](https://github.com/BerriAI/litellm/pull/23201)
+
+- **General**
+    - Per-request `enable_json_schema_validation` flag for thread-safe JSON schema validation - [PR #21233](https://github.com/BerriAI/litellm/pull/21233)
+    - Model cost aliases expansion — define aliases in the cost map that inherit pricing from a parent model - [PR #23314](https://github.com/BerriAI/litellm/pull/23314), [PR #23457](https://github.com/BerriAI/litellm/pull/23457)
+    - Wildcards model support for the Files API - [PR #22740](https://github.com/BerriAI/litellm/pull/22740)
+
+#### Bugs
+
+- **[Anthropic](../../docs/providers/anthropic)**
+    - Preserve native tool format (web_search, bash, tool_search, etc.) when guardrails convert tools for the Anthropic Messages API - [PR #23526](https://github.com/BerriAI/litellm/pull/23526)
+    - Enforce `type: "object"` on tool input schemas in `_map_tool_helper` — fixes tool call failures for strict-schema providers - [PR #23103](https://github.com/BerriAI/litellm/pull/23103)
+    - Deduplicate `tool_result` messages by `tool_call_id` — prevents duplicate tool result errors in multi-turn conversations - [PR #23104](https://github.com/BerriAI/litellm/pull/23104)
+    - Map `reasoning_effort` to `output_config` for Claude 4.6 models - [PR #22220](https://github.com/BerriAI/litellm/pull/22220)
+
+- **[Google Gemini](../../docs/providers/gemini)**
+    - Correct streaming `finish_reason` for tool calls — was incorrectly returning `null` instead of `tool_calls` - [PR #21577](https://github.com/BerriAI/litellm/pull/21577)
+    - Preserve `$ref` in JSON Schema for Gemini 2.0+ — schema references were being stripped, breaking structured output - [PR #21597](https://github.com/BerriAI/litellm/pull/21597)
+    - Handle `minimal` `reasoning_effort` param for Gemini 3.1 models - [PR #22920](https://github.com/BerriAI/litellm/pull/22920)
+
+- **[Google Vertex AI](../../docs/providers/vertex)**
+    - Pass through native Gemini `imageConfig` params for image generation - [PR #21585](https://github.com/BerriAI/litellm/pull/21585)
+    - Prevent content truncation when `finish_reason` races ahead of content chunks in streaming - [PR #22692](https://github.com/BerriAI/litellm/pull/22692)
+    - Strip LiteLLM-internal keys from `extra_body` before merging to Gemini request body - [PR #23131](https://github.com/BerriAI/litellm/pull/23131)
+    - Drop unsupported `output_config` parameter from all Vertex AI requests - [PR #22884](https://github.com/BerriAI/litellm/pull/22884)
+    - Skip schema transforms for Gemini 2.0+ tool parameters — avoids breaking native Gemini schema handling - [PR #23265](https://github.com/BerriAI/litellm/pull/23265)
+
+- **[OpenRouter](../../docs/providers/openrouter)**
+    - Pattern-based fix for native model double-stripping when provider prefix matches model name - [PR #22320](https://github.com/BerriAI/litellm/pull/22320)
+    - Use provider-reported usage in streaming responses when `stream_options` is not set - [PR #21592](https://github.com/BerriAI/litellm/pull/21592)
+
+- **[AWS Bedrock](../../docs/providers/bedrock)**
+    - Extract region and model ID from `bedrock/{region}/{model}` path format - [PR #22546](https://github.com/BerriAI/litellm/pull/22546)
+    - Strip `scope` from `cache_control` for Anthropic messages on Bedrock and Azure AI - [PR #22867](https://github.com/BerriAI/litellm/pull/22867)
+    - Populate `completion_tokens_details` in Responses API responses - [PR #23243](https://github.com/BerriAI/litellm/pull/23243)
+
+- **[Azure AI](../../docs/providers/azure_ai)**
+    - Resolve `api_base` from environment variable in Document Intelligence OCR - [PR #21581](https://github.com/BerriAI/litellm/pull/21581)
+
+- **[Moonshot / Kimi](../../docs/providers/openai_compatible)**
+    - Auto-fill `reasoning_content` for Moonshot Kimi reasoning models - [PR #23580](https://github.com/BerriAI/litellm/pull/23580)
+    - Preserve `image_url` blocks in multimodal messages for Moonshot - [PR #21595](https://github.com/BerriAI/litellm/pull/21595)
+
+- **[HuggingFace](../../docs/providers/huggingface)**
+    - Forward `extra_headers` to HuggingFace embedding API - [PR #23525](https://github.com/BerriAI/litellm/pull/23525)
+
+- **Token Counting / Cost**
+    - Fix `count_tokens` to include system prompts and tools in token counting API requests - [PR #22301](https://github.com/BerriAI/litellm/pull/22301)
+    - Pass all custom pricing fields to `register_model` in `completion()` and `embedding()` - [PR #22552](https://github.com/BerriAI/litellm/pull/22552)
+
+- **Tools / Function Calling**
+    - Gracefully repair truncated JSON in tool call arguments — prevents crashes on malformed tool responses - [PR #22503](https://github.com/BerriAI/litellm/pull/22503)
+    - Fix `output_item.done` for function calls not emitting `finish_reason` in streaming - [PR #22553](https://github.com/BerriAI/litellm/pull/22553)
+    - Preserve thinking block order with multiple web searches - [PR #23093](https://github.com/BerriAI/litellm/pull/23093)
+
+- **General**
+    - Normalize `content_filtered` finish reason across providers - [PR #23564](https://github.com/BerriAI/litellm/pull/23564)
+    - Unify `finish_reason` mapping to OpenAI-compatible values across all providers - [PR #22138](https://github.com/BerriAI/litellm/pull/22138)
+    - Fix custom cost tracking on deployments for `/v1/messages` and `/v1/responses` - [PR #23647](https://github.com/BerriAI/litellm/pull/23647)
+    - Fix per-request custom pricing when `router_model_id` has no pricing data — now falls back to model name
+    - Fix batch list showing stale `validating` status after completion - [PR #22982](https://github.com/BerriAI/litellm/pull/22982)
+    - Fix batch retrieve returning raw `output_file_id` when `model_id` is missing - [PR #23194](https://github.com/BerriAI/litellm/pull/23194)
+    - Encode batch IDs when `x-litellm-model` header is used - [PR #22653](https://github.com/BerriAI/litellm/pull/22653)
+    - Map `reasoning` to `reasoning_content` in streaming Delta for gpt-oss providers - [PR #22803](https://github.com/BerriAI/litellm/pull/22803)
+
+---
+
+## Management Endpoints / UI
+
+#### Features
+
+- **Virtual Keys**
+    - Add Organization dropdown to Create/Edit Key form — `organization_id` is now a first-class field in Key Ownership - [PR #23595](https://github.com/BerriAI/litellm/pull/23595)
+    - Allow setting `organization_id` on `/key/update` — keys can be assigned or moved to a different organization after creation - [PR #23557](https://github.com/BerriAI/litellm/pull/23557)
+    - Manual Spend Reset for virtual keys from the UI — admins can reset key spend to zero on demand - [PR #22715](https://github.com/BerriAI/litellm/pull/22715)
+    - BYOK (Bring Your Own Key) — client-side provider API key takes precedence over proxy key for Anthropic `/v1/messages` - [PR #22964](https://github.com/BerriAI/litellm/pull/22964)
+    - UI login session duration configurable via `LITELLM_UI_SESSION_DURATION` environment variable - [PR #22182](https://github.com/BerriAI/litellm/pull/22182)
+    - Auto-redirect UI login to SSO via `auto_redirect_ui_login_to_sso: true` in config.yaml - [PR #23367](https://github.com/BerriAI/litellm/pull/23367)
+
+- **Access Control (RBAC)**
+    - Org Admins can now access team management endpoints — `/team/new`, `/team/update`, `/team/delete`, `/team/member_add`, `/team/member_delete` - [PR #23085](https://github.com/BerriAI/litellm/pull/23085), [PR #23095](https://github.com/BerriAI/litellm/pull/23095)
+    - Org Admins can view and invite internal users — full user management without requiring global admin role - [PR #23080](https://github.com/BerriAI/litellm/pull/23080)
+    - Allow Admin Viewers to access Audit Logs — view-only admin role now includes audit log access - [PR #23419](https://github.com/BerriAI/litellm/pull/23419)
+    - RBAC for Vector Stores and Agents — key/team-level access control for vector store and agent resources - [PR #22858](https://github.com/BerriAI/litellm/pull/22858)
+    - User filter scope (`scope_user_search_to_org`) is now opt-in — previously default-on, causing unintended restriction - [PR #23057](https://github.com/BerriAI/litellm/pull/23057)
+
+- **Vector Stores**
+    - Vector Store management endpoints — retrieve, list, update, and delete vector stores via `/v1/vector_stores/*` - [PR #23435](https://github.com/BerriAI/litellm/pull/23435)
+
+- **Teams**
+    - Batch expiry setting for teams — configure a default expiry duration for all team keys - [PR #22705](https://github.com/BerriAI/litellm/pull/22705)
+    - Team Admin can reset key spend - [PR #22725](https://github.com/BerriAI/litellm/pull/22725)
+
+- **Internal Users**
+    - Add/Remove Team Membership directly from the Internal Users info page — includes searchable dropdown and role selector; no longer requires navigating to each team - [PR #23638](https://github.com/BerriAI/litellm/pull/23638)
+
+- **Models**
+    - Attach knowledge base to model via UI - [PR #22656](https://github.com/BerriAI/litellm/pull/22656)
+
+- **Default Team Settings**
+    - Modernize page to antd (consistent with rest of app) - [PR #23614](https://github.com/BerriAI/litellm/pull/23614)
+    - Fix: default team params (budget, duration, tpm, rpm, permissions) now correctly applied on `/team/new` - [PR #23614](https://github.com/BerriAI/litellm/pull/23614)
+    - Fix: settings persist across proxy restarts (`default_team_params` added to `LITELLM_SETTINGS_SAFE_DB_OVERRIDES`) - [PR #23614](https://github.com/BerriAI/litellm/pull/23614)
+    - Fix: resolved race condition in `_update_litellm_setting` where `get_config()` could overwrite freshly saved values - [PR #23614](https://github.com/BerriAI/litellm/pull/23614)
+
+- **Usage**
+    - Auto-paginate daily spend data — all entity views (teams, orgs, customers, tags, agents, users) fetch pages progressively with charts updating after each page - [PR #23622](https://github.com/BerriAI/litellm/pull/23622)
+
+- **Models / Cost**
+    - Azure Model Router cost breakdown in UI — show per-sub-model `additional_costs` from `hidden_params` in `CostBreakdownViewer` - [PR #23550](https://github.com/BerriAI/litellm/pull/23550)
+
+- **User Management**
+    - New `/user/info/v2` endpoint — scoped, paginated replacement for the existing god endpoint that caused memory and stability issues on large installs - [PR #23437](https://github.com/BerriAI/litellm/pull/23437)
+
+#### Bugs
+
+- Fix Tag list endpoint returning 500 due to invalid Prisma `group_by` kwargs - [PR #23606](https://github.com/BerriAI/litellm/pull/23606)
+- Fix Team Admin getting 403 on `/user/filter/ui` when `scope_user_search_to_org` is enabled - [PR #23671](https://github.com/BerriAI/litellm/pull/23671)
+- Fix Public Model Hub not showing config-defined models after save - [PR #23501](https://github.com/BerriAI/litellm/pull/23501)
+- Fix fallback popup model dropdown z-index issue - [PR #23516](https://github.com/BerriAI/litellm/pull/23516)
+- Fix double-counting bug in org/team key limit checks on `/key/update`
+- Fix invite link allowing multiple password resets for the same link - [PR #22462](https://github.com/BerriAI/litellm/pull/22462)
+- Fix key expiry default duration not being applied when `duration` is not set - [PR #22956](https://github.com/BerriAI/litellm/pull/22956)
+- Fix all proxy models not including model access groups in key creation - [PR #23236](https://github.com/BerriAI/litellm/pull/23236)
+- Fix admin viewers unable to see all organizations - [PR #22940](https://github.com/BerriAI/litellm/pull/22940)
+- Fix Audit Logs UI: added server-side pagination, filtering, and drawer view - [PR #22476](https://github.com/BerriAI/litellm/pull/22476)
+- Fix virtual keys in teams view not applying the team filter correctly - [PR #23065](https://github.com/BerriAI/litellm/pull/23065)
+- Fix team expiry enforcement validation - [PR #22728](https://github.com/BerriAI/litellm/pull/22728)
+
+---
+
+## AI Integrations
+
+### Logging
+
+- **[Helicone](../../docs/observability/helicone_integration)**
+    - Add Gemini and Vertex AI support to HeliconeLogger — routes Gemini and Vertex AI requests through the correct Helicone provider URL - [PR #19288](https://github.com/BerriAI/litellm/pull/19288)
+    - Fix correct provider URL for Vertex AI Gemini models - [PR #22603](https://github.com/BerriAI/litellm/pull/22603)
+
+- **[Langfuse](../../docs/proxy/logging#langfuse)**
+    - Fix failure path kwargs inconsistency causing dropped traces on failed requests - [PR #22390](https://github.com/BerriAI/litellm/pull/22390)
+
+- **[Vantage](https://vantage.sh)**
+    - Add Vantage integration for FOCUS 1.2 CSV export — export LiteLLM proxy spend data as FinOps Open Cost & Usage Specification reports, with time-windowed filenames to prevent overwrites - [PR #23333](https://github.com/BerriAI/litellm/pull/23333)
+
+- **General**
+    - Fix silent metrics race condition causing metric collision across experiments - [PR #23542](https://github.com/BerriAI/litellm/pull/23542)
+
+### Guardrails
+
+- **Guardrail mode default list** — Configure a default list of guardrail modes applied globally when no per-request mode is specified - [PR #22676](https://github.com/BerriAI/litellm/pull/22676)
+- **Tag-based guardrail mode lists** — Specify a list of modes in tag-based guardrail configs instead of a single mode - [PR #23020](https://github.com/BerriAI/litellm/pull/23020)
+- **Fix presidio PII token leak** — Edge case where Anthropic handle in Presidio caused PII data exposure in token response - [PR #22627](https://github.com/BerriAI/litellm/pull/22627)
+- **Fix OTEL orphaned guardrail traces** — Span redundancy and missing response IDs in OpenTelemetry guardrail traces - [PR #23001](https://github.com/BerriAI/litellm/pull/23001)
+
+### Prompt Management
+
+No major prompt management changes in this release.
+
+### Secret Managers
+
+- **[Hashicorp Vault](../../docs/secret_managers)** — Full Hashicorp Vault integration as a config override backend — secrets defined in Vault are fetched at startup and override `config.yaml` values. UI support for managing vault-sourced credentials included - [PR #22939](https://github.com/BerriAI/litellm/pull/22939), [PR #23036](https://github.com/BerriAI/litellm/pull/23036)
+
+---
+
+## MCP Gateway
+
+#### Features
+
+- **Token authentication for MCP servers** — configure `auth_type: "bearer"` per MCP server to require token-based auth on tool calls - [PR #23260](https://github.com/BerriAI/litellm/pull/23260)
+- **Team-scoped MCP server filtering** — keys created under a team only see MCP servers available to that team - [PR #23323](https://github.com/BerriAI/litellm/pull/23323)
+- **Per-server health recheck in UI** — trigger a health check for individual MCP servers without reloading all servers - [PR #23328](https://github.com/BerriAI/litellm/pull/23328)
+
+#### Bugs
+
+- Fix MCP server URL and tools management issues causing tool discovery to fail - [PR #22751](https://github.com/BerriAI/litellm/pull/22751)
+- Fix MCP server health checks triggering on server deletion - [PR #23063](https://github.com/BerriAI/litellm/pull/23063)
+
+---
+
+## Spend Tracking, Budgets and Rate Limiting
+
+- **Fix budget-linked keys never having spend reset** — Keys linked to budget objects were not having their spend reset on the configured reset interval - [PR #20688](https://github.com/BerriAI/litellm/pull/20688)
+- **Flex pricing support** — Add `flex_pricing` field to cost map for providers that offer dynamic pricing tiers - [PR #22992](https://github.com/BerriAI/litellm/pull/22992)
+- **Fix spend log cleanup** — Resolved lock tracking, integer retention, and skip-log-level issues in spend log cleanup job - [PR #22687](https://github.com/BerriAI/litellm/pull/22687)
+- **Fix WebSearch spend log deduplication** — WebSearch interception was failing with thinking enabled; fixed along with spend log dedup - [PR #22679](https://github.com/BerriAI/litellm/pull/22679)
+- **Fix TypeError when request has no API key** — Spend tracking was throwing unhandled exception when API key was absent from request - [PR #23363](https://github.com/BerriAI/litellm/pull/23363)
+
+---
+
+## Performance / Loadbalancing / Reliability improvements
+
+- **Fix streaming crashes after ~1 hour** — `LLMClientCache._remove_key()` no longer calls `close()`/`aclose()` on evicted HTTP/SDK clients. In-flight requests were crashing with `RuntimeError: Cannot send a request, as the client has been closed.` after the 1-hour TTL expired. Cleanup now happens only at shutdown via `close_litellm_async_clients()` - [PR #22926](https://github.com/BerriAI/litellm/pull/22926)
+- **Fix OOM / Prisma connection loss** on large installs — unbounded managed-object poll was exhausting Prisma connections after ~60–70 minutes on instances with 336K+ queued response rows - [PR #23472](https://github.com/BerriAI/litellm/pull/23472)
+- **Centralize logging kwarg updates** — root cause fix migrating all logging updates to a single function, eliminating kwarg inconsistencies across logging paths - [PR #23659](https://github.com/BerriAI/litellm/pull/23659)
+- **Fix tiktoken cache for non-root offline containers** — tiktoken cache now works correctly in offline environments running as non-root users - [PR #23498](https://github.com/BerriAI/litellm/pull/23498)
+- **Block proxy startup when Redis transaction buffer has no Redis** — prevents silent data loss when `use_redis_transaction_buffer: true` is set without a Redis connection - [PR #23019](https://github.com/BerriAI/litellm/pull/23019)
+- **Fix `InFlightRequestsMiddleware` crash** — undefined kwargs in middleware were causing request failures - [PR #22523](https://github.com/BerriAI/litellm/pull/22523)
+- **Fix `BaseModelResponseIterator` crash on non-string stream chunks** — streaming was crashing when providers returned non-string chunk data - [PR #23497](https://github.com/BerriAI/litellm/pull/23497)
+- **Fix `SERVER_ROOT_PATH` prefix handling** — strip prefix before checking mapped pass-through routes to prevent double-prefix issues - [PR #23414](https://github.com/BerriAI/litellm/pull/23414)
+- **Add CodSpeed continuous performance benchmarks** — automated performance regression tracking on CI - [PR #23676](https://github.com/BerriAI/litellm/pull/23676)
+
+---
+
+## Security
+
+- **Secret redaction in proxy logs** — Adds a `SecretRedactionFilter` to all LiteLLM loggers that scrubs API keys, tokens, and credentials from log messages, format args, exception tracebacks, and extra fields. Enabled by default; opt out with `LITELLM_DISABLE_REDACT_SECRETS=true` - [PR #23668](https://github.com/BerriAI/litellm/pull/23668), [PR #23667](https://github.com/BerriAI/litellm/pull/23667)
+- **Bump PyJWT to `^2.12.0`** — addresses security vulnerability in `^2.10.1` - [PR #23678](https://github.com/BerriAI/litellm/pull/23678)
+- **Bump `tar` to 7.5.11 and `tornado` to 6.5.5** — addresses CVEs in transitive dependencies - [PR #23602](https://github.com/BerriAI/litellm/pull/23602)
+
+---
+
+## Database / Proxy Operations
+
+- **Fix Prisma migrate deploy on pre-existing instances** — resolved multiple bugs in migration recovery logic: missing return in the P3018 idempotent error handler and unhandled exceptions in `_roll_back_migration` that caused silent failures even after successful recovery - [PR #23655](https://github.com/BerriAI/litellm/pull/23655)
+- **Make DB migration failure exit opt-in** — proxy no longer exits on `prisma migrate deploy` failure by default; enable with `--enforce_prisma_migration_check` - [PR #23675](https://github.com/BerriAI/litellm/pull/23675)
+
+---
+
+## Documentation Updates
+
+- Add Anthropic `/v1/messages` → `/responses` parameter mapping reference - [PR #22893](https://github.com/BerriAI/litellm/pull/22893)
+- Update Okta SSO docs and custom SSO handler example - [PR #22786](https://github.com/BerriAI/litellm/pull/22786)
+- Add `LITELLM_MAX_BUDGET_PER_SESSION_TTL` to environment variables reference - [PR #23186](https://github.com/BerriAI/litellm/pull/23186)
+- Add DB query performance guidelines to `CLAUDE.md` - [PR #23196](https://github.com/BerriAI/litellm/pull/23196)
+- Add Gemini Vertex AI PayGo/priority cost tracking docs - [PR #22948](https://github.com/BerriAI/litellm/pull/22948)
+
+---
+
+## New Contributors
+
+* @ryanh-ai made their first contribution in [PR #21542](https://github.com/BerriAI/litellm/pull/21542)
+* @ryan-crabbe made their first contribution in [PR #23668](https://github.com/BerriAI/litellm/pull/23668)
+* @Jah-yee made their first contribution in [PR #23525](https://github.com/BerriAI/litellm/pull/23525)
+* @gambletan made their first contribution in [PR #23516](https://github.com/BerriAI/litellm/pull/23516)
+* @awais786 made their first contribution in [PR #23183](https://github.com/BerriAI/litellm/pull/23183)
+* @pradyyadav made their first contribution in [PR #23580](https://github.com/BerriAI/litellm/pull/23580)
+* @xianzongxie-stripe made their first contribution in [PR #23492](https://github.com/BerriAI/litellm/pull/23492)
+* @Harshit28j made their first contribution in [PR #23333](https://github.com/BerriAI/litellm/pull/23333)
+* @codspeed-hq[bot] made their first contribution in [PR #23676](https://github.com/BerriAI/litellm/pull/23676)
+
+---
+
+## Diff Summary
+
+## 03/16/2026
+* New Providers: 7
+* New Models / Updated Models: 116 new, 132 removed
+* LLM API Endpoints: 37
+* Management Endpoints / UI: 31
+* AI Integrations: 8
+* MCP Gateway: 5
+* Spend Tracking, Budgets and Rate Limiting: 5
+* Performance / Loadbalancing / Reliability improvements: 9
+* Security: 3
+* Database / Proxy Operations: 2
+* Documentation Updates: 5
+
+---
+
+## Full Changelog
+[v1.82.0-stable...v1.82.3-stable](https://github.com/BerriAI/litellm/compare/v1.82.0-stable...v1.82.3-stable)

docs/my-website/sidebars-release-notes.js

@@ -0,0 +1,14 @@
+// @ts-check
+
+/** @type {import('@docusaurus/plugin-content-docs').SidebarsConfig} */
+const sidebars = {
+  releaseNotesSidebar: [
+    { type: 'doc', id: 'index', label: 'Release Notes' },
+    {
+      type: 'autogenerated',
+      dirName: '.',
+    },
+  ],
+};
+
+module.exports = sidebars;

docs/my-website/sidebars.js

@@ -20,6 +20,7 @@ const sidebars = {
     {
       type: "category",
       label: "Observability",
+      link: { type: "doc", id: "integrations/observability_index" },
       items: [
         {
           type: "category",
@@ -29,61 +30,24 @@ const sidebars = {
               type: "autogenerated",
               dirName: "contribute_integration"
             }
-          ]
+          ],
         },
         {
           type: "autogenerated",
           dirName: "observability"
-        }
+        },
       ],
     },
     {
       type: "category",
-      label: "Guardrails",
+      label: "Guardrail Providers",
+      link: {
+        type: "generated-index",
+        title: "Guardrail Providers",
+        description: "Add safety and content filtering to LLM calls",
+        slug: "/guardrail_providers"
+      },
       items: [
-        "proxy/guardrails/quick_start",
-        "proxy/guardrails/team_based_guardrails",
-        "proxy/guardrails/guardrail_load_balancing",
-        "proxy/guardrails/test_playground",
-        "proxy/guardrails/litellm_content_filter",
-        "proxy/guardrails/realtime_guardrails",
-        {
-          type: "category",
-          label: "Providers",
-          items: [
-            ...[
-              "proxy/guardrails/qualifire",
-              "proxy/guardrails/aim_security",
-              "proxy/guardrails/onyx_security",
-              "proxy/guardrails/aporia_api",
-              "proxy/guardrails/azure_content_guardrail",
-              "proxy/guardrails/bedrock",
-              "proxy/guardrails/crowdstrike_aidr",
-              "proxy/guardrails/enkryptai",
-              "proxy/guardrails/ibm_guardrails",
-              "proxy/guardrails/grayswan",
-              "proxy/guardrails/hiddenlayer",
-              "proxy/guardrails/lasso_security",
-              "proxy/guardrails/guardrails_ai",
-              "proxy/guardrails/lakera_ai",
-              "proxy/guardrails/model_armor",
-              "proxy/guardrails/noma_security",
-              "proxy/guardrails/dynamoai",
-              "proxy/guardrails/openai_moderation",
-              "proxy/guardrails/pangea",
-              "proxy/guardrails/pillar_security",
-              "proxy/guardrails/pii_masking_v2",
-              "proxy/guardrails/panw_prisma_airs",
-              "proxy/guardrails/secret_detection",
-              "proxy/guardrails/custom_guardrail",
-              "proxy/guardrails/custom_code_guardrail",
-              "proxy/guardrails/prompt_injection",
-              "proxy/guardrails/tool_permission",
-              "proxy/guardrails/zscaler_ai_guard",
-              "proxy/guardrails/javelin"
-            ].sort(),
-          ],
-        },
         {
           type: "category",
           label: "Contributing to Guardrails",
@@ -93,16 +57,42 @@ const sidebars = {
             "adding_provider/adding_guardrail_support",
           ]
         },
-      ],
-    },
-    {
-      type: "category",
-      label: "Policies",
-      items: [
-        "proxy/guardrails/guardrail_policies",
-        "proxy/guardrails/policy_flow_builder",
-        "proxy/guardrails/policy_templates",
-        "proxy/guardrails/policy_tags",
+        {
+          type: "doc",
+          id: "proxy/guardrails/team_based_guardrails",
+          label: "Team Bring-Your-Own Guardrails",
+        },
+        ...[
+          "proxy/guardrails/qualifire",
+          "proxy/guardrails/aim_security",
+          "proxy/guardrails/onyx_security",
+          "proxy/guardrails/aporia_api",
+          "proxy/guardrails/azure_content_guardrail",
+          "proxy/guardrails/bedrock",
+          "proxy/guardrails/crowdstrike_aidr",
+          "proxy/guardrails/enkryptai",
+          "proxy/guardrails/ibm_guardrails",
+          "proxy/guardrails/grayswan",
+          "proxy/guardrails/hiddenlayer",
+          "proxy/guardrails/lasso_security",
+          "proxy/guardrails/guardrails_ai",
+          "proxy/guardrails/lakera_ai",
+          "proxy/guardrails/model_armor",
+          "proxy/guardrails/noma_security",
+          "proxy/guardrails/dynamoai",
+          "proxy/guardrails/openai_moderation",
+          "proxy/guardrails/pangea",
+          "proxy/guardrails/pillar_security",
+          "proxy/guardrails/pii_masking_v2",
+          "proxy/guardrails/panw_prisma_airs",
+          "proxy/guardrails/secret_detection",
+          "proxy/guardrails/custom_guardrail",
+          "proxy/guardrails/custom_code_guardrail",
+          "proxy/guardrails/prompt_injection",
+          "proxy/guardrails/tool_permission",
+          "proxy/guardrails/zscaler_ai_guard",
+          "proxy/guardrails/javelin"
+        ].sort(),
       ],
     },
     {
@@ -115,11 +105,6 @@ const sidebars = {
         "proxy/pyroscope_profiling"
       ]
     },
-    {
-      type: "doc",
-      id: "integrations/websearch_interception",
-      label: "Web Search Integration"
-    },
     {
       type: "category",
       label: "[Beta] Prompt Management",
@@ -140,7 +125,7 @@ const sidebars = {
     },
     {
       type: "category",
-      label: "AI Tools (OpenWebUI, Claude Code, etc.)",
+      label: "AI Tools",
       link: {
         type: "generated-index",
         title: "AI Tools",
@@ -167,14 +152,13 @@ const sidebars = {
         },
         "tutorials/opencode_integration",
         "tutorials/openclaw_integration",
-        "tutorials/cost_tracking_coding",
         "tutorials/cursor_integration",
         "tutorials/github_copilot_integration",
         "tutorials/litellm_gemini_cli",
-        "tutorials/google_genai_sdk",
         "tutorials/litellm_qwen_code_cli",
         "tutorials/openai_codex",
-        "tutorials/retool_assist"
+        "tutorials/retool_assist",
+        "tutorials/cost_tracking_coding"
       ]
     },
     {
@@ -191,7 +175,11 @@ const sidebars = {
         "tutorials/claude_agent_sdk",
         "tutorials/copilotkit_sdk",
         "tutorials/google_adk",
+        "tutorials/google_genai_sdk",
         "tutorials/livekit_xai_realtime",
+        "integrations/letta",
+        { type: "doc", id: "tutorials/instructor", label: "Instructor with LiteLLM" },
+        { type: "doc", id: "langchain/langchain", label: "LangChain with LiteLLM" },
         "projects/openai-agents"
       ]
     },
@@ -212,7 +200,20 @@ const sidebars = {
   ],
   // But you can create a sidebar manually
   tutorialSidebar: [
-    { type: "doc", id: "index", label: "Getting Started" },
+    // ════════════════════════════════════════════════════════════
+    // GET STARTED
+    // ════════════════════════════════════════════════════════════
+    {
+      type: "category",
+      label: "Get Started",
+      collapsible: false,
+      collapsed: false,
+      items: [
+        { type: "doc", id: "index", label: "Quickstart" },
+        { type: "link", label: "Models & Pricing", href: "https://models.litellm.ai" },
+        { type: "link", label: "Changelog", href: "/release_notes" },
+      ],
+    },
 
     {
       type: "category",
@@ -280,11 +281,6 @@ const sidebars = {
         },
         "completion/token_usage",
         "exception_mapping",
-        {
-          type: "category",
-          label: "LangChain, LlamaIndex, Instructor",
-          items: ["langchain/langchain", "tutorials/instructor"],
-        }
       ],
     },
     {
@@ -297,16 +293,46 @@ const sidebars = {
         slug: "/simple_proxy",
       },
       items: [
-        "proxy/docker_quick_start",
+        { type: "doc", id: "proxy/docker_quick_start", label: "Getting Started Tutorial" },
         {
-          type: "link",
-          label: "A2A Agent Gateway",
-          href: "https://docs.litellm.ai/docs/a2a",
-        },
-        {
-          type: "link",
-          label: "MCP Gateway",
-          href: "https://docs.litellm.ai/docs/mcp",
+          type: "category",
+          label: "Agent & MCP Gateway",
+          items: [
+            {
+              type: "category",
+              label: "A2A Agent Gateway",
+              items: [
+                "a2a",
+                "a2a_invoking_agents",
+                "a2a_agent_headers",
+                "a2a_cost_tracking",
+                "a2a_agent_permissions",
+                "a2a_iteration_budgets",
+              ],
+            },
+            {
+              type: "category",
+              label: "MCP Gateway",
+              items: [
+                "mcp",
+                "mcp_usage",
+                "mcp_openapi",
+                "mcp_oauth",
+                "mcp_aws_sigv4",
+                "mcp_zero_trust",
+                "mcp_public_internet",
+                "mcp_semantic_filter",
+                "mcp_control",
+                "mcp_cost",
+                "mcp_guardrail",
+                {
+                  type: "link",
+                  label: "MCP Troubleshooting Guide",
+                  href: "/docs/mcp_troubleshoot"
+                },
+              ],
+            },
+          ],
         },
         {
           "type": "category",
@@ -365,7 +391,11 @@ const sidebars = {
               type: "category",
               label: "Teams & Organizations",
               items: [
-                "proxy/access_control",
+                {
+                  type: "link",
+                  label: "Role-based Access Controls (RBAC) →",
+                  href: "/docs/proxy/access_control"
+                },
                 "proxy/self_serve",
                 "proxy/public_teams",
                 "proxy/ui_project_management",
@@ -400,6 +430,7 @@ const sidebars = {
             "proxy/architecture",
             "proxy/multi_tenant_architecture",
             "proxy/control_plane_and_data_plane",
+            "proxy/high_availability_control_plane",
             "proxy/db_deadlocks",
             "proxy/db_info",
             "proxy/image_handling",
@@ -448,14 +479,40 @@ const sidebars = {
         },
         "proxy/caching",
         {
-          type: "link",
+          type: "category",
           label: "Guardrails",
-          href: "https://docs.litellm.ai/docs/proxy/guardrails/quick_start",
+          items: [
+            "proxy/guardrails/quick_start",
+            "proxy/guardrails/team_based_guardrails",
+            "proxy/guardrails/guardrail_load_balancing",
+            "proxy/guardrails/test_playground",
+            "proxy/guardrails/litellm_content_filter",
+            "proxy/guardrails/realtime_guardrails",
+            {
+              type: "link",
+              label: "Providers →",
+              href: "/docs/guardrail_providers",
+            },
+            {
+              type: "category",
+              label: "Contributing to Guardrails",
+              items: [
+                "adding_provider/generic_guardrail_api",
+                "adding_provider/simple_guardrail_tutorial",
+                "adding_provider/adding_guardrail_support",
+              ]
+            },
+          ],
         },
         {
-          type: "link",
+          type: "category",
           label: "Policies",
-          href: "https://docs.litellm.ai/docs/proxy/guardrails/guardrail_policies",
+          items: [
+            "proxy/guardrails/guardrail_policies",
+            "proxy/guardrails/policy_flow_builder",
+            "proxy/guardrails/policy_templates",
+            "proxy/guardrails/policy_tags",
+          ],
         },
         {
           type: "category",
@@ -528,6 +585,7 @@ const sidebars = {
           label: "Spend Tracking",
           items: [
             "proxy/cost_tracking",
+            "tutorials/vertex_ai_pay_go",
             "proxy/request_tags",
             "proxy/custom_pricing",
             "proxy/pricing_calculator",
@@ -551,16 +609,9 @@ const sidebars = {
       },
       items: [
         {
-          type: "category",
+          type: "link",
           label: "/a2a - A2A Agent Gateway",
-          items: [
-            "a2a",
-            "a2a_invoking_agents",
-            "a2a_agent_headers",
-            "a2a_cost_tracking",
-            "a2a_agent_permissions",
-            "a2a_iteration_budgets"
-          ],
+          href: "/docs/a2a",
         },
         "assistants",
         "audio_transcription",
@@ -631,11 +682,13 @@ const sidebars = {
             "mcp_openapi",
             "mcp_oauth",
             "mcp_aws_sigv4",
+            "mcp_zero_trust",
             "mcp_public_internet",
             "mcp_semantic_filter",
             "mcp_control",
             "mcp_cost",
             "mcp_guardrail",
+            "mcp_zero_trust",
             "mcp_troubleshoot",
           ]
         },
@@ -686,6 +739,7 @@ const sidebars = {
         "proxy/realtime_webrtc",
         "rerank",
         "response_api",
+        "prompt_management",
         "response_api_compact",
         {
           type: "category",
@@ -973,51 +1027,14 @@ const sidebars = {
         "providers/zai",
       ],
     },
-    {
-      type: "category",
-      label: "Guides",
-      items: [
-        "budget_manager",
-        "completion/computer_use",
-        "completion/web_search",
-        "completion/web_fetch",
-        "completion/function_call",
-        "completion/audio",
-        "completion/document_understanding",
-        "completion/drop_params",
-        "completion/image_generation_chat",
-        "completion/json_mode",
-        "completion/knowledgebase",
-        "providers/anthropic_tool_search",
-        "guides/code_interpreter",
-        "completion/message_trimming",
-        "completion/message_sanitization",
-        "completion/model_alias",
-        "completion/mock_requests",
-        "completion/predict_outputs",
-        "completion/prefix",
-        "completion/prompt_caching",
-        "completion/prompt_formatting",
-        "completion/reliable_completions",
-        "completion/stream",
-        "completion/provider_specific_params",
-        "completion/vision",
-        "exception_mapping",
-        "completion/batching",
-        "guides/finetuned_models",
-        "guides/security_settings",
-        "proxy/veo_video_generation",
-        "reasoning_content",
-        "extras/creating_adapters",
-      ]
-    },
+
 
     {
       type: "category",
-      label: "Routing, Loadbalancing & Fallbacks",
+      label: "Routing & Load Balancing",
       link: {
         type: "generated-index",
-        title: "Routing, Loadbalancing & Fallbacks",
+        title: "Routing & Load Balancing",
         description: "Learn how to load balance, route, and set fallbacks for your LLM requests",
         slug: "/routing-load-balancing",
       },
@@ -1045,43 +1062,6 @@ const sidebars = {
         "load_test_rpm",
       ]
     },
-    {
-      type: "category",
-      label: "Tutorials",
-      items: [
-        {
-          type: "link",
-          label: "AI Coding Tools (OpenWebUI, Claude Code, Gemini CLI, OpenAI Codex, etc.)",
-          href: "/docs/ai_tools",
-        },
-        "tutorials/anthropic_file_usage",
-        "tutorials/default_team_self_serve",
-        "tutorials/msft_sso",
-        "tutorials/prompt_caching",
-        "tutorials/tag_management",
-        'tutorials/litellm_proxy_aporia',
-        "tutorials/presidio_pii_masking",
-        "tutorials/elasticsearch_logging",
-        "tutorials/gemini_realtime_with_audio",
-        "tutorials/claude_code_beta_headers",
-        {
-          type: "category",
-          label: "LiteLLM Python SDK Tutorials",
-          items: [
-            'tutorials/azure_openai',
-            'tutorials/instructor',
-            "tutorials/gradio_integration",
-            "tutorials/huggingface_codellama",
-            "tutorials/huggingface_tutorial",
-            "tutorials/TogetherAI_liteLLM",
-            "tutorials/finetuned_chat_gpt",
-            "tutorials/text_completion",
-            "tutorials/first_playground",
-            "tutorials/model_fallbacks",
-          ],
-        },
-      ]
-    },
     {
       type: "category",
       label: "Contributing",
@@ -1138,12 +1118,11 @@ const sidebars = {
             "projects/Codium PR Agent",
             "projects/Prompt2Model",
             "projects/SalesGPT",
+            "projects/Softgen",
             "projects/Quivr",
             "projects/Langstream",
             "projects/Otter",
-            "projects/GPT Migrate",
             "projects/YiVal",
-            "projects/LiteLLM Proxy",
             "projects/llm_cord",
             "projects/pgai",
             "projects/GPTLocalhost",
@@ -1181,23 +1160,310 @@ const sidebars = {
         "troubleshoot",
       ],
     },
+  ],
+};
+
+const learnSidebar = {
+  learnSidebar: [
+    // ── Landing page ──────────────────────────────────────────────────
+    { type: "doc", id: "learn/index", label: "Learn" },
     {
       type: "category",
-      label: "Blog",
+      label: "Start Here",
+      collapsible: true,
+      collapsed: false,
+      items: [
+        "learn/sdk_quickstart",
+        "learn/gateway_quickstart",
+      ],
+    },
+
+    // ── Guides ────────────────────────────────────────────────────────
+    {
+      type: "category",
+      label: "Guides",
+      collapsible: true,
+      collapsed: false,
+      link: { type: "doc", id: "guides/index" },
       items: [
         {
-          type: "link",
-          label: "Day 0 Support: Claude Sonnet 4.6",
-          href: "/blog/claude_sonnet_4_6",
+          type: "category",
+          label: "Core Requests",
+          collapsible: true,
+          collapsed: false,
+          link: {
+            type: "generated-index",
+            title: "Core Requests",
+            description: "Streaming, batching, structured outputs, and reasoning behavior",
+            slug: "/guides/core_request_response_patterns"
+          },
+          items: [
+            "completion/stream",
+            "completion/batching",
+            "completion/json_mode",
+            "reasoning_content",
+          ],
+        },
+        {
+          type: "category",
+          label: "Tool Calling",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Tool Calling",
+            description: "Function calling, web tools, interception patterns, computer use, code interpreter, and tool-call hygiene",
+            slug: "/guides/tools_integrations"
+          },
+          items: [
+            "completion/function_call",
+            "completion/web_search",
+            {
+              type: "doc",
+              id: "integrations/websearch_interception",
+              label: "Web Search Interception",
+            },
+            "completion/web_fetch",
+            "completion/computer_use",
+            "guides/code_interpreter",
+            "completion/message_sanitization",
+          ],
+        },
+        {
+          type: "category",
+          label: "Multimodal I/O",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Multimodal I/O",
+            description: "Vision, audio, PDFs, image generation, and video generation",
+            slug: "/guides/multimodal_io"
+          },
+          items: [
+            "completion/vision",
+            "completion/audio",
+            "completion/document_understanding",
+            "completion/image_generation_chat",
+            "proxy/veo_video_generation",
+          ],
+        },
+        {
+          type: "category",
+          label: "Retrieval & Knowledge",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Retrieval & Knowledge",
+            description: "Vector stores, file search, citations, and knowledge-base routing",
+            slug: "/guides/retrieval_knowledge"
+          },
+          items: [
+            "completion/knowledgebase",
+          ],
+        },
+        {
+          type: "category",
+          label: "Prompts & Context",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Prompts & Context",
+            description: "Prompt caching, trimming, formatting, assistant prefill, and predicted outputs",
+            slug: "/guides/prompts_context"
+          },
+          items: [
+            "completion/prefix",
+            "completion/predict_outputs",
+            "completion/message_trimming",
+            "completion/prompt_caching",
+            "completion/prompt_formatting",
+          ],
+        },
+        {
+          type: "category",
+          label: "Compatibility & Extensibility",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Compatibility & Extensibility",
+            description: "Provider-specific params, model aliases, fine-tuned models, and adapters",
+            slug: "/guides/compatibility_extensibility"
+          },
+          items: [
+            "completion/provider_specific_params",
+            "completion/drop_params",
+            "completion/model_alias",
+            "guides/finetuned_models",
+            "extras/creating_adapters",
+          ],
+        },
+        {
+          type: "category",
+          label: "Reliability, Testing & Spend",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Reliability, Testing & Spend",
+            description: "Retries, fallbacks, mock responses, and budget controls",
+            slug: "/guides/reliability_testing_spend"
+          },
+          items: [
+            "completion/mock_requests",
+            "completion/reliable_completions",
+            "budget_manager",
+          ],
+        },
+        {
+          type: "category",
+          label: "Security & Network",
+          collapsible: true,
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Security & Network",
+            description: "SSL, custom CA bundles, HTTP proxy settings, and per-service verification",
+            slug: "/guides/security_network"
+          },
+          items: [
+            "guides/security_settings",
+          ],
+        },
+      ],
+    },
+
+    // ── Tutorials ─────────────────────────────────────────────────────
+    {
+      type: "category",
+      label: "Tutorials",
+      collapsible: true,
+      collapsed: false,
+      link: { type: "doc", id: "tutorials/index" },
+      items: [
+        {
+          type: "category",
+          label: "Getting Started",
+          collapsed: false,
+          link: {
+            type: "generated-index",
+            title: "Getting Started",
+            description: "Installation, playground, text completion, and mock completions",
+            slug: "/tutorials/getting_started"
+          },
+          items: [
+            "tutorials/installation",
+            "tutorials/first_playground",
+            "tutorials/text_completion",
+            "tutorials/mock_completion",
+          ],
         },
         {
           type: "link",
-          label: "Incident: Broken Model Cost Map",
-          href: "/blog/model-cost-map-incident",
+          label: "Agent SDKs & Frameworks",
+          href: "/docs/agent_sdks",
+        },
+        {
+          type: "link",
+          label: "AI Coding Tools",
+          href: "/docs/ai_tools",
+        },
+        {
+          type: "category",
+          label: "Python SDK",
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Python SDK",
+            description: "Tutorials using only the Python SDK — no proxy server required",
+            slug: "/tutorials/python_sdk"
+          },
+          items: [
+            "tutorials/gradio_integration",
+            "tutorials/provider_specific_params",
+            "tutorials/model_fallbacks",
+            "tutorials/fallbacks",
+          ],
+        },
+        {
+          type: "category",
+          label: "Provider Setup",
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Provider Setup",
+            description: "Connect LiteLLM to Azure OpenAI, HuggingFace, TogetherAI, local models, and more",
+            slug: "/tutorials/provider_tutorials"
+          },
+          items: [
+            "tutorials/azure_openai",
+            "tutorials/TogetherAI_liteLLM",
+            "tutorials/huggingface_tutorial",
+            "tutorials/huggingface_codellama",
+            "tutorials/finetuned_chat_gpt",
+            "tutorials/oobabooga",
+          ],
+        },
+        {
+          type: "category",
+          label: "Proxy: Admin & Access",
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Proxy: Admin & Access",
+            description: "User and team management, SSO, SCIM, and routing rules",
+            slug: "/tutorials/proxy_admin_access"
+          },
+          items: [
+            "tutorials/default_team_self_serve",
+            "tutorials/msft_sso",
+            "tutorials/scim_litellm",
+            "tutorials/tag_management",
+          ],
+        },
+        {
+          type: "category",
+          label: "Proxy: Features & Safety",
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Proxy: Features & Safety",
+            description: "Prompt caching, passthrough APIs, realtime, guardrails, and PII masking",
+            slug: "/tutorials/proxy_features_safety"
+          },
+          items: [
+            "tutorials/prompt_caching",
+            "tutorials/file_search_responses_api",
+            "tutorials/anthropic_file_usage",
+            "tutorials/gemini_realtime_with_audio",
+            "tutorials/litellm_proxy_aporia",
+            "tutorials/presidio_pii_masking",
+          ],
+        },
+        {
+          type: "category",
+          label: "Observability & Evaluation",
+          collapsed: true,
+          link: {
+            type: "generated-index",
+            title: "Observability & Evaluation",
+            description: "Logging, monitoring, benchmarking, and evaluation suites",
+            slug: "/tutorials/observability_evaluation"
+          },
+          items: [
+            "tutorials/elasticsearch_logging",
+            "tutorials/compare_llms",
+            "tutorials/litellm_Test_Multiple_Providers",
+            "tutorials/eval_suites",
+            "tutorials/lm_evaluation_harness",
+          ],
         },
       ],
     },
   ],
 };
 
-module.exports = sidebars;
+module.exports = { ...sidebars, ...learnSidebar };

docs/my-website/src/components/ControlPlaneArchitecture/ControlPlaneArchitecture.tsx

@@ -0,0 +1,95 @@
+import React from 'react';
+import styles from './styles.module.css';
+
+/* ────────────────────── Shared small pieces ────────────────────── */
+
+function InfraChip({ color, label }: { color: string; label: string }) {
+  const dotClass =
+    color === 'green'
+      ? styles.infraDotGreen
+      : color === 'blue'
+        ? styles.infraDotBlue
+        : styles.infraDotOrange;
+
+  return (
+    <span className={styles.infraChip}>
+      <span className={`${styles.infraDot} ${dotClass}`} />
+      {label}
+    </span>
+  );
+}
+
+/* ────────────────────── Architecture tab ────────────────────── */
+
+function ArchitectureView() {
+  return (
+    <div className={styles.diagram}>
+      {/* User */}
+      <div className={styles.userRow}>
+        <div className={styles.userIcon}>&#128100;</div>
+        <span className={styles.userLabel}>Admin</span>
+      </div>
+
+      <div className={styles.connectorDown} />
+
+      {/* Control Plane */}
+      <div className={`${styles.node} ${styles.nodeControlPlane}`}>
+        <div className={styles.nodeHeader}>
+          <span className={styles.nodeTitle}>Control Plane</span>
+          <span className={`${styles.badge} ${styles.badgeBlue}`}>UI</span>
+        </div>
+        <div className={styles.nodeSubtitle}>cp.example.com</div>
+        <div className={styles.infraRow}>
+          <InfraChip color="green" label="Own DB" />
+          <InfraChip color="orange" label="Own Redis" />
+          <InfraChip color="blue" label="Own Key" />
+        </div>
+      </div>
+
+      {/* Branch connector */}
+      <div className={styles.connectorBranch}>
+        <div className={`${styles.branchLeg} ${styles.branchLegLeft}`} />
+        <div className={`${styles.branchLeg} ${styles.branchLegRight}`} />
+      </div>
+
+      {/* Workers */}
+      <div className={styles.workersRow}>
+        <div className={`${styles.node} ${styles.nodeWorker} ${styles.nodeWorkerA}`}>
+          <div className={styles.nodeHeader}>
+            <span className={styles.nodeTitle}>Worker A</span>
+            <span className={`${styles.badge} ${styles.badgeGreen}`}>US East</span>
+          </div>
+          <div className={styles.nodeSubtitle}>worker-a.example.com</div>
+          <div className={styles.infraRow}>
+            <InfraChip color="green" label="Own DB" />
+            <InfraChip color="orange" label="Own Redis" />
+            <InfraChip color="blue" label="Own Key" />
+          </div>
+        </div>
+
+        <div className={`${styles.node} ${styles.nodeWorker} ${styles.nodeWorkerB}`}>
+          <div className={styles.nodeHeader}>
+            <span className={styles.nodeTitle}>Worker B</span>
+            <span className={`${styles.badge} ${styles.badgePurple}`}>EU West</span>
+          </div>
+          <div className={styles.nodeSubtitle}>worker-b.example.com</div>
+          <div className={styles.infraRow}>
+            <InfraChip color="green" label="Own DB" />
+            <InfraChip color="orange" label="Own Redis" />
+            <InfraChip color="blue" label="Own Key" />
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+}
+
+/* ────────────────────── Main component ────────────────────── */
+
+export default function ControlPlaneArchitecture() {
+  return (
+    <div className={styles.wrapper}>
+      <ArchitectureView />
+    </div>
+  );
+}

docs/my-website/src/components/ControlPlaneArchitecture/index.tsx

@@ -0,0 +1 @@
+export { default as ControlPlaneArchitecture } from './ControlPlaneArchitecture';

docs/my-website/src/components/ControlPlaneArchitecture/styles.module.css

@@ -0,0 +1,517 @@
+/* ── Custom properties ── */
+:root {
+  --cp-bg: #ffffff;
+  --cp-border: #e5e7eb;
+  --cp-text: #1a1a2e;
+  --cp-text-secondary: #6b7280;
+  --cp-text-muted: #9ca3af;
+  --cp-accent: #3b82f6;
+  --cp-accent-light: #dbeafe;
+  --cp-accent-glow: rgba(59, 130, 246, 0.15);
+  --cp-green: #10b981;
+  --cp-green-light: #d1fae5;
+  --cp-green-glow: rgba(16, 185, 129, 0.15);
+  --cp-orange: #f59e0b;
+  --cp-orange-light: #fef3c7;
+  --cp-purple: #8b5cf6;
+  --cp-purple-light: #ede9fe;
+  --cp-red: #ef4444;
+  --cp-red-light: #fee2e2;
+  --cp-card-bg: #f9fafb;
+  --cp-infra-bg: #f1f5f9;
+  --cp-infra-border: #cbd5e1;
+  --cp-connector: #d1d5db;
+  --cp-dot-size: 8px;
+}
+
+[data-theme='dark'] {
+  --cp-bg: #111827;
+  --cp-border: #374151;
+  --cp-text: #e5e7eb;
+  --cp-text-secondary: #9ca3af;
+  --cp-text-muted: #6b7280;
+  --cp-accent: #60a5fa;
+  --cp-accent-light: #1e3a5f;
+  --cp-accent-glow: rgba(96, 165, 250, 0.2);
+  --cp-green: #34d399;
+  --cp-green-light: #064e3b;
+  --cp-green-glow: rgba(52, 211, 153, 0.2);
+  --cp-orange: #fbbf24;
+  --cp-orange-light: #78350f;
+  --cp-purple: #a78bfa;
+  --cp-purple-light: #3b0764;
+  --cp-red: #f87171;
+  --cp-red-light: #451a1a;
+  --cp-card-bg: #1f2937;
+  --cp-infra-bg: #1e293b;
+  --cp-infra-border: #475569;
+  --cp-connector: #4b5563;
+}
+
+/* ── Wrapper ── */
+.wrapper {
+  margin: 1.5rem 0;
+  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+}
+
+/* ── Tab bar ── */
+.tabs {
+  display: flex;
+  gap: 0;
+  margin-bottom: 1.5rem;
+  border-bottom: 2px solid var(--cp-border);
+}
+
+.tab {
+  padding: 0.6rem 1.25rem;
+  font-size: 0.85rem;
+  font-weight: 600;
+  color: var(--cp-text-secondary);
+  background: none;
+  border: none;
+  border-bottom: 2px solid transparent;
+  margin-bottom: -2px;
+  cursor: pointer;
+  transition: color 0.2s, border-color 0.2s;
+}
+
+.tab:hover {
+  color: var(--cp-text);
+}
+
+.tabActive {
+  color: var(--cp-accent);
+  border-bottom-color: var(--cp-accent);
+}
+
+/* ── Architecture diagram ── */
+.diagram {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 0;
+}
+
+/* ── User icon ── */
+.userRow {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  margin-bottom: 0.5rem;
+}
+
+.userIcon {
+  width: 40px;
+  height: 40px;
+  border-radius: 50%;
+  background: var(--cp-accent-light);
+  border: 2px solid var(--cp-accent);
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  font-size: 1.1rem;
+}
+
+.userLabel {
+  font-size: 0.75rem;
+  color: var(--cp-text-secondary);
+  margin-top: 0.3rem;
+  font-weight: 500;
+}
+
+/* ── Connectors ── */
+.connectorDown {
+  width: 2px;
+  height: 28px;
+  background: var(--cp-connector);
+  position: relative;
+}
+
+.connectorDown::after {
+  content: '';
+  position: absolute;
+  bottom: -4px;
+  left: 50%;
+  transform: translateX(-50%);
+  width: 0;
+  height: 0;
+  border-left: 5px solid transparent;
+  border-right: 5px solid transparent;
+  border-top: 5px solid var(--cp-connector);
+}
+
+.connectorBranch {
+  display: flex;
+  align-items: flex-start;
+  justify-content: center;
+  position: relative;
+  width: 100%;
+  max-width: 700px;
+  height: 36px;
+}
+
+.connectorBranch::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 50%;
+  width: 2px;
+  height: 12px;
+  background: var(--cp-connector);
+  transform: translateX(-50%);
+}
+
+.connectorBranch::after {
+  content: '';
+  position: absolute;
+  top: 12px;
+  left: calc(25% + 12px);
+  right: calc(25% + 12px);
+  height: 2px;
+  background: var(--cp-connector);
+}
+
+.branchLeg {
+  position: absolute;
+  top: 12px;
+  width: 2px;
+  height: 24px;
+  background: var(--cp-connector);
+}
+
+.branchLeg::after {
+  content: '';
+  position: absolute;
+  bottom: -4px;
+  left: 50%;
+  transform: translateX(-50%);
+  width: 0;
+  height: 0;
+  border-left: 5px solid transparent;
+  border-right: 5px solid transparent;
+  border-top: 5px solid var(--cp-connector);
+}
+
+.branchLegLeft {
+  left: calc(25% + 12px);
+}
+
+.branchLegRight {
+  right: calc(25% + 12px);
+}
+
+/* ── Node cards ── */
+.node {
+  border: 2px solid var(--cp-border);
+  border-radius: 12px;
+  background: var(--cp-card-bg);
+  padding: 1rem 1.25rem;
+  text-align: center;
+  transition: border-color 0.3s, box-shadow 0.3s;
+  position: relative;
+}
+
+.nodeControlPlane {
+  border-color: var(--cp-accent);
+  box-shadow: 0 0 0 3px var(--cp-accent-glow);
+  min-width: 280px;
+}
+
+.nodeWorker {
+  min-width: 220px;
+}
+
+.nodeWorkerA {
+  border-color: var(--cp-green);
+  box-shadow: 0 0 0 3px var(--cp-green-glow);
+}
+
+.nodeWorkerB {
+  border-color: var(--cp-purple);
+  box-shadow: 0 0 0 3px rgba(139, 92, 246, 0.15);
+}
+
+[data-theme='dark'] .nodeWorkerB {
+  box-shadow: 0 0 0 3px rgba(167, 139, 250, 0.2);
+}
+
+.nodeHeader {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  gap: 0.5rem;
+  margin-bottom: 0.5rem;
+}
+
+.nodeIcon {
+  font-size: 1.1rem;
+}
+
+.nodeTitle {
+  font-size: 0.95rem;
+  font-weight: 700;
+  color: var(--cp-text);
+}
+
+.nodeSubtitle {
+  font-size: 0.75rem;
+  color: var(--cp-text-secondary);
+  margin-bottom: 0.75rem;
+}
+
+.badge {
+  display: inline-block;
+  font-size: 0.65rem;
+  font-weight: 600;
+  padding: 0.15rem 0.5rem;
+  border-radius: 9999px;
+  text-transform: uppercase;
+  letter-spacing: 0.04em;
+}
+
+.badgeBlue {
+  background: var(--cp-accent-light);
+  color: var(--cp-accent);
+}
+
+.badgeGreen {
+  background: var(--cp-green-light);
+  color: var(--cp-green);
+}
+
+.badgePurple {
+  background: var(--cp-purple-light);
+  color: var(--cp-purple);
+}
+
+/* ── Infrastructure chips ── */
+.infraRow {
+  display: flex;
+  gap: 0.4rem;
+  justify-content: center;
+  flex-wrap: wrap;
+  margin-top: 0.5rem;
+}
+
+.infraChip {
+  display: flex;
+  align-items: center;
+  gap: 0.3rem;
+  font-size: 0.7rem;
+  font-weight: 500;
+  color: var(--cp-text-secondary);
+  background: var(--cp-infra-bg);
+  border: 1px solid var(--cp-infra-border);
+  border-radius: 6px;
+  padding: 0.2rem 0.5rem;
+}
+
+.infraDot {
+  width: 6px;
+  height: 6px;
+  border-radius: 50%;
+  flex-shrink: 0;
+}
+
+.infraDotGreen {
+  background: var(--cp-green);
+}
+
+.infraDotBlue {
+  background: var(--cp-accent);
+}
+
+.infraDotOrange {
+  background: var(--cp-orange);
+}
+
+/* ── Workers row ── */
+.workersRow {
+  display: flex;
+  gap: 2rem;
+  justify-content: center;
+  flex-wrap: wrap;
+}
+
+/* ── Animated flow ── */
+.flowLabel {
+  font-size: 0.7rem;
+  color: var(--cp-accent);
+  font-weight: 600;
+  position: absolute;
+  white-space: nowrap;
+}
+
+/* ── Comparison view ── */
+.comparisonGrid {
+  display: grid;
+  grid-template-columns: 1fr 1fr;
+  gap: 1.5rem;
+  margin-top: 0.5rem;
+}
+
+.comparisonColumn {
+  border: 2px solid var(--cp-border);
+  border-radius: 12px;
+  padding: 1.25rem;
+  background: var(--cp-card-bg);
+}
+
+.comparisonColumnOld {
+  border-color: var(--cp-red);
+}
+
+.comparisonColumnNew {
+  border-color: var(--cp-green);
+}
+
+.comparisonTitle {
+  font-size: 0.9rem;
+  font-weight: 700;
+  color: var(--cp-text);
+  text-align: center;
+  margin-bottom: 1rem;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  gap: 0.4rem;
+}
+
+.comparisonTitleOld {
+  color: var(--cp-red);
+}
+
+.comparisonTitleNew {
+  color: var(--cp-green);
+}
+
+/* ── Mini diagram inside comparison ── */
+.miniDiagram {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.miniNode {
+  border: 1.5px solid var(--cp-border);
+  border-radius: 8px;
+  background: var(--cp-bg);
+  padding: 0.5rem 0.75rem;
+  text-align: center;
+  font-size: 0.75rem;
+  font-weight: 600;
+  color: var(--cp-text);
+  width: 100%;
+  max-width: 180px;
+}
+
+.miniNodeHighlight {
+  border-color: var(--cp-accent);
+  background: var(--cp-accent-light);
+}
+
+.miniNodeDanger {
+  border-color: var(--cp-red);
+  background: var(--cp-red-light);
+}
+
+.miniNodeSuccess {
+  border-color: var(--cp-green);
+  background: var(--cp-green-light);
+}
+
+.miniConnector {
+  width: 1.5px;
+  height: 16px;
+  background: var(--cp-connector);
+}
+
+.miniWorkersRow {
+  display: flex;
+  gap: 0.5rem;
+  justify-content: center;
+  width: 100%;
+}
+
+.miniWorkerStack {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 0.3rem;
+  flex: 1;
+  max-width: 140px;
+}
+
+.miniInfra {
+  font-size: 0.65rem;
+  color: var(--cp-text-muted);
+  font-weight: 500;
+}
+
+.miniInfraShared {
+  color: var(--cp-red);
+  font-weight: 600;
+}
+
+.miniInfraOwn {
+  color: var(--cp-green);
+  font-weight: 600;
+}
+
+/* ── Callout box ── */
+.callout {
+  display: flex;
+  align-items: flex-start;
+  gap: 0.6rem;
+  padding: 0.75rem 1rem;
+  border-radius: 8px;
+  margin-top: 1rem;
+  font-size: 0.8rem;
+  color: var(--cp-text);
+  line-height: 1.5;
+}
+
+.calloutDanger {
+  background: var(--cp-red-light);
+  border: 1px solid var(--cp-red);
+}
+
+.calloutSuccess {
+  background: var(--cp-green-light);
+  border: 1px solid var(--cp-green);
+}
+
+.calloutIcon {
+  font-size: 1rem;
+  flex-shrink: 0;
+  margin-top: 0.1rem;
+}
+
+/* ── Responsive ── */
+@media (max-width: 768px) {
+  .comparisonGrid {
+    grid-template-columns: 1fr;
+  }
+
+  .workersRow {
+    flex-direction: column;
+    align-items: center;
+  }
+
+  .nodeControlPlane {
+    min-width: auto;
+    width: 100%;
+    max-width: 300px;
+  }
+
+  .nodeWorker {
+    min-width: auto;
+    width: 100%;
+    max-width: 260px;
+  }
+
+  .connectorBranch {
+    display: none;
+  }
+}

docs/my-website/src/components/NavigationCards/index.js

@@ -0,0 +1,44 @@
+import React from 'react';
+import Link from '@docusaurus/Link';
+import styles from './styles.module.css';
+
+export default function NavigationCards({ items, columns = 2 }) {
+  return (
+    <div
+      className={styles.grid}
+      style={{ '--nav-columns': columns }}
+    >
+      {items.map((item, i) => {
+        const isExternal =
+          item.to && (item.to.startsWith('http://') || item.to.startsWith('https://'));
+        return (
+          <Link
+            key={i}
+            to={item.to}
+            className={styles.card}
+            target={isExternal ? '_blank' : undefined}
+            rel={isExternal ? 'noopener noreferrer' : undefined}
+          >
+            {item.icon && (
+              <div className={styles.icon}>{item.icon}</div>
+            )}
+            <div className={styles.title}>{item.title}</div>
+            {item.description && (
+              <div className={styles.description}>{item.description}</div>
+            )}
+            {item.listDescription && (
+              <ul className={styles.list}>
+                {item.listDescription.map((line, j) => (
+                  <li key={j}>{line}</li>
+                ))}
+              </ul>
+            )}
+            {isExternal && (
+              <span className={styles.externalIcon}>↗</span>
+            )}
+          </Link>
+        );
+      })}
+    </div>
+  );
+}

docs/my-website/src/components/NavigationCards/styles.module.css

@@ -0,0 +1,82 @@
+.grid {
+  display: grid;
+  grid-template-columns: repeat(var(--nav-columns, 2), 1fr);
+  gap: 0.75rem;
+  margin: 1.25rem 0;
+}
+
+@media (max-width: 768px) {
+  .grid {
+    grid-template-columns: 1fr;
+  }
+}
+
+.card {
+  position: relative;
+  display: flex;
+  flex-direction: column;
+  padding: 1rem 1.1rem;
+  border: 1px solid var(--ifm-color-emphasis-200);
+  border-radius: 6px;
+  text-decoration: none !important;
+  color: inherit !important;
+  background: var(--ifm-background-surface-color);
+  transition: border-color 0.15s ease, box-shadow 0.15s ease;
+}
+
+.card:hover {
+  border-color: var(--ifm-color-primary);
+  box-shadow: 0 0 0 1px var(--ifm-color-primary);
+  text-decoration: none !important;
+}
+
+[data-theme='dark'] .card {
+  background: var(--ifm-background-surface-color);
+  border-color: #2d3748;
+}
+
+[data-theme='dark'] .card:hover {
+  border-color: var(--ifm-color-primary);
+  box-shadow: 0 0 0 1px var(--ifm-color-primary);
+}
+
+.icon {
+  font-size: 1.4rem;
+  margin-bottom: 0.5rem;
+  line-height: 1;
+}
+
+.title {
+  font-size: 14px;
+  font-weight: 600;
+  margin-bottom: 0.35rem;
+  color: var(--ifm-heading-color);
+}
+
+.description {
+  font-size: 13px;
+  line-height: 1.5;
+  color: var(--ifm-color-emphasis-700);
+  margin-bottom: 0.5rem;
+}
+
+.list {
+  margin: 0.35rem 0 0 0;
+  padding-left: 1.1rem;
+  list-style: disc;
+}
+
+.list li {
+  font-size: 12.5px;
+  color: var(--ifm-color-emphasis-700);
+  line-height: 1.6;
+  margin-bottom: 0;
+}
+
+.externalIcon {
+  position: absolute;
+  top: 0.75rem;
+  right: 0.75rem;
+  font-size: 12px;
+  color: var(--ifm-color-emphasis-500);
+}

docs/my-website/src/css/custom.css

@@ -1,10 +1,16 @@
 /**
- * Any CSS included here will be global. The classic template
- * bundles Infima by default. Infima is a CSS framework designed to
- * work well for content-centric websites.
+ * Global CSS overrides for LiteLLM docs.
+ * Infima (Docusaurus CSS framework) variables + custom styling.
  */
 
-/* You can override the default Infima variables here. */
+/* =========================================
+   FONTS
+   ========================================= */
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap');
+
+/* =========================================
+   ROOT — Light Mode Variables
+   ========================================= */
 :root {
   --ifm-color-primary: #2e8555;
   --ifm-color-primary-dark: #29784c;
@@ -13,11 +19,22 @@
   --ifm-color-primary-light: #33925d;
   --ifm-color-primary-lighter: #359962;
   --ifm-color-primary-lightest: #3cad6e;
-  --ifm-code-font-size: 95%;
-  --docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.1);
+  --ifm-code-font-size: 85%;
+  --ifm-menu-color: #6b7280;
+  --docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.08);
+  --ifm-font-family-base: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+  --ifm-heading-font-weight: 600;
+  --ifm-font-size-base: 15px;
+  --ifm-line-height-base: 1.65;
+  --ifm-border-radius: 6px;
+  /* Wider reading column — reduces excessive whitespace on large monitors */
+  --ifm-container-width: 1380px;
+  --ifm-container-width-xl: 1560px;
 }
 
-/* For readability concerns, you should choose a lighter palette in dark mode. */
+/* =========================================
+   DARK MODE Variables
+   ========================================= */
 [data-theme='dark'] {
   --ifm-color-primary: #25c2a0;
   --ifm-color-primary-dark: #21af90;
@@ -26,10 +43,710 @@
   --ifm-color-primary-light: #29d5b0;
   --ifm-color-primary-lighter: #32d8b4;
   --ifm-color-primary-lightest: #4fddbf;
-  --docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.3);
+  --ifm-background-color: #0d1117;
+  --ifm-background-surface-color: #161b22;
+  --docusaurus-highlighted-code-line-bg: rgba(255, 255, 255, 0.07);
 }
 
-/* Levo logo sizing and theme switching */
+/* =========================================
+   TYPOGRAPHY
+   ========================================= */
+.theme-doc-markdown h1 {
+  font-size: 2.2rem;
+  letter-spacing: -0.02em;
+  line-height: 1.2;
+}
+
+.theme-doc-markdown h2 {
+  font-size: 1.6rem;
+  letter-spacing: -0.01em;
+  line-height: 1.3;
+}
+
+.theme-doc-markdown h3 {
+  font-size: 1.25rem;
+  line-height: 1.4;
+}
+
+.theme-doc-markdown p,
+.theme-doc-markdown ul,
+.theme-doc-markdown ol {
+  font-size: 0.9rem;
+}
+
+.theme-doc-markdown table {
+  font-size: 0.875rem;
+}
+
+.theme-doc-markdown td {
+  font-size: 0.85rem;
+}
+
+/* =========================================
+   NAVBAR
+   ========================================= */
+[data-theme='light'] .navbar {
+  background-color: #ffffff;
+  box-shadow: 0 1px 0 0 #e5e7eb;
+}
+
+[data-theme='dark'] .navbar {
+  background-color: var(--ifm-background-color);
+  border-bottom: 1px solid #21262d;
+  box-shadow: none;
+}
+
+.navbar__link {
+  font-weight: 400 !important;
+  font-size: 14px !important;
+  border-bottom: 2px solid transparent !important;
+  padding-bottom: 2px;
+}
+
+.navbar__link--active {
+  font-weight: 500 !important;
+  border-bottom: 2px solid var(--ifm-color-primary) !important;
+}
+
+@media (max-width: 1330px) {
+  .navbar__link {
+    font-size: 13px !important;
+  }
+}
+
+/* Three-column navbar: logo | center nav | right icons */
+@media (min-width: 997px) {
+  .navbar__inner {
+    display: flex !important;
+    align-items: center;
+    justify-content: space-between;
+  }
+
+  .navbar__brand-col {
+    display: flex;
+    align-items: center;
+    flex: 0 0 auto;
+    margin-left: 1rem;
+  }
+
+  .navbar__brand-col .navbar__brand {
+    font-size: 1.25rem;
+  }
+
+  .navbar__brand-col .navbar__logo {
+    height: 2rem;
+    width: auto;
+  }
+
+  .navbar__center-col {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    flex: 1;
+  }
+
+  .navbar__right-col {
+    display: flex;
+    align-items: center;
+    flex: 0 0 auto;
+    gap: 0.25rem;
+    margin-right: 2rem;
+  }
+}
+
+/* =========================================
+   ALERTS / ADMONITIONS
+   ========================================= */
+.alert {
+  padding: 0.75rem 1rem;
+  font-size: 14px;
+  border-radius: var(--ifm-border-radius);
+  border-left-width: 3px;
+}
+
+/* Light mode */
+.alert--info {
+  --ifm-alert-background-color: #f0f7ff !important;
+  --ifm-alert-border-color: #2264ab !important;
+}
+
+.alert--success {
+  --ifm-alert-background-color: #f0fff8 !important;
+  --ifm-alert-border-color: #09bda8 !important;
+}
+
+.alert--secondary {
+  --ifm-alert-background-color: #f8fafc !important;
+  --ifm-alert-border-color: #64748b !important;
+}
+
+.alert--danger {
+  --ifm-alert-background-color: #fff0f5 !important;
+  --ifm-alert-border-color: #e11d48 !important;
+}
+
+.alert--warning {
+  --ifm-alert-background-color: #fffbeb !important;
+  --ifm-alert-border-color: #d97706 !important;
+}
+
+/* Dark mode */
+[data-theme='dark'] .alert--info {
+  --ifm-alert-background-color: #0c1e30 !important;
+  --ifm-alert-border-color: #3b82f6 !important;
+  color: #bfdbfe !important;
+}
+
+[data-theme='dark'] .alert--success {
+  --ifm-alert-background-color: #022c22 !important;
+  --ifm-alert-border-color: #10b981 !important;
+}
+
+[data-theme='dark'] .alert--secondary {
+  --ifm-alert-background-color: #0f172a !important;
+  --ifm-alert-border-color: #475569 !important;
+}
+
+[data-theme='dark'] .alert--danger {
+  --ifm-alert-background-color: #2d0a14 !important;
+  --ifm-alert-border-color: #f43f5e !important;
+}
+
+[data-theme='dark'] .alert--warning {
+  --ifm-alert-background-color: #1c1200 !important;
+  --ifm-alert-border-color: #f59e0b !important;
+}
+
+/* =========================================
+   COLLAPSIBLE / DETAILS
+   ========================================= */
+details {
+  color: #1d232e;
+  background-color: #ffffff;
+  border: 1px solid #e9eef2 !important;
+  border-radius: var(--ifm-border-radius) !important;
+  padding: 0.75rem !important;
+  margin-bottom: 1rem !important;
+  margin-top: 1.5rem !important;
+  box-shadow: 0 1px 4px 0 rgba(0, 0, 0, 0.05) !important;
+}
+
+details summary {
+  font-weight: 600 !important;
+}
+
+details [class*='collapsibleContent'] {
+  border-top: 1px solid #e2e8f0 !important;
+}
+
+details [class*='collapsibleContent'] p,
+details [class*='collapsibleContent'] ul {
+  font-size: 13px !important;
+  line-height: 1.75;
+}
+
+[data-theme='dark'] details {
+  background-color: #1c2130 !important;
+  color: #e5e7eb !important;
+  border: 1px solid #2d3748 !important;
+  box-shadow: 0 1px 6px 0 rgba(0, 0, 0, 0.3) !important;
+}
+
+[data-theme='dark'] details summary {
+  color: #f3f4f6 !important;
+}
+
+[data-theme='dark'] details [class*='collapsibleContent'] {
+  border-top: 1px solid #2d3748 !important;
+}
+
+/* =========================================
+   TABS
+   ========================================= */
+.tabs-container > div {
+  padding: 1rem;
+  border: 1px solid #e2e8f0;
+  border-radius: var(--ifm-border-radius);
+}
+
+/* Remove styling from nested tabs containers */
+.tabs-container .tabs-container > div {
+  padding: 0;
+  border: none;
+  border-radius: 0;
+}
+
+[data-theme='dark'] .tabs-container > div {
+  border-color: #2d3748;
+}
+
+ul.tabs {
+  border-bottom: 1px solid #e2e8f0 !important;
+  column-gap: 0.5rem !important;
+}
+
+[data-theme='dark'] ul.tabs {
+  border-bottom-color: #2d3748 !important;
+}
+
+li.tabs__item {
+  padding: 0.5rem !important;
+  font-weight: 500 !important;
+  font-size: 14px !important;
+  border-bottom: 2px solid transparent !important;
+}
+
+li.tabs__item--active {
+  border-bottom: 2px solid var(--ifm-color-primary) !important;
+}
+
+/* =========================================
+   CODE BLOCKS
+   ========================================= */
+.prism-code {
+  border-radius: var(--ifm-border-radius);
+  font-size: 12.5px !important;
+  line-height: 1.6;
+}
+
+[data-theme='dark'] .prism-code {
+  border: 1px solid #21262d;
+}
+
+[class*='codeLineNumber']::before {
+  font-size: 12px !important;
+  display: flex !important;
+  align-items: center !important;
+  justify-content: center !important;
+}
+
+[class*='codeBlockTitle'] {
+  font-size: 13px !important;
+  font-weight: 500 !important;
+  padding: 0.5rem 1rem !important;
+  border-bottom: 1px solid #334155 !important;
+}
+
+.theme-code-block-highlighted-line {
+  background-color: rgba(0, 0, 0, 0.1) !important;
+}
+
+[data-theme='dark'] .theme-code-block-highlighted-line {
+  background-color: rgba(255, 255, 255, 0.06) !important;
+}
+
+.theme-code-block-highlighted-line > span {
+  background-color: transparent !important;
+}
+
+/* =========================================
+   SIDEBAR / MENU
+   ========================================= */
+.menu {
+  font-weight: 400;
+  padding: 0.5rem 0.25rem !important;
+  background-image: radial-gradient(rgba(0, 0, 0, 0.07) 1px, transparent 1px);
+  background-size: 24px 24px;
+}
+
+[data-theme='dark'] .menu {
+  background-image: radial-gradient(rgba(255, 255, 255, 0.04) 1px, transparent 1px);
+  background-size: 24px 24px;
+}
+
+.menu__link {
+  font-size: 14px;
+  padding: 0.22rem 0.75rem !important;
+  border-radius: 4px;
+}
+
+.menu__link--active {
+  font-weight: 600 !important;
+  background-color: rgba(46, 133, 85, 0.08) !important;
+}
+
+[data-theme='dark'] .menu__link--active {
+  background-color: rgba(37, 194, 160, 0.1) !important;
+}
+
+/* ─── Sidebar collapse arrows — uniform size & alignment ────── */
+
+/* 1. Categories WITHOUT a link prop:
+      The button itself holds the text + ::after arrow.
+      Make it flex so the arrow never wraps to a new line. */
+.menu__link--sublist-caret {
+  display: flex !important;
+  align-items: center !important;
+  justify-content: space-between !important;
+  gap: 0.5rem;
+  padding-right: 0.625rem !important;
+}
+
+.menu__link--sublist-caret::after {
+  content: '' !important;
+  display: block !important;
+  flex-shrink: 0 !important;
+  width: 1.25rem !important;
+  height: 1.25rem !important;
+  min-width: 1.25rem !important;
+  background: var(--ifm-menu-link-sublist-icon) center / 1.25rem 1.25rem no-repeat !important;
+  margin: 0 !important;
+}
+
+/* 2. Categories WITH a link prop:
+      A separate <a> + <button class="menu__caret"> sit in a flex row. */
+.menu__list-item-collapsible {
+  display: flex !important;
+  align-items: center !important;
+  border-radius: 4px;
+}
+
+.menu__list-item-collapsible > .menu__link {
+  flex: 1 1 auto;
+  min-width: 0; /* allow text to shrink/wrap without pushing arrow */
+}
+
+.menu__caret {
+  flex-shrink: 0 !important;
+  width: 2rem !important;
+  height: 2rem !important;
+  padding: 0 !important;
+  display: flex !important;
+  align-items: center !important;
+  justify-content: center !important;
+}
+
+.menu__caret::before {
+  content: '' !important;
+  display: block !important;
+  width: 1.25rem !important;
+  height: 1.25rem !important;
+  min-width: 1.25rem !important;
+  background: var(--ifm-menu-link-sublist-icon) center / 1.25rem 1.25rem no-repeat !important;
+}
+
+/* Top-level sidebar category labels */
+.theme-doc-sidebar-item-category-level-1
+  > .menu__list-item-collapsible
+  > .menu__link:first-of-type {
+  color: #111827;
+  font-weight: 600 !important;
+  font-size: 14px;
+}
+
+[data-theme='dark']
+  .theme-doc-sidebar-item-category-level-1
+  > .menu__list-item-collapsible
+  > .menu__link:first-of-type {
+  color: #f9fafb;
+  font-weight: 600 !important;
+  font-size: 14px;
+}
+
+.theme-doc-sidebar-item-category-level-1 {
+  margin-bottom: 0.25rem !important;
+}
+
+/* Consistent row height for all top-level items */
+.theme-doc-sidebar-item-category-level-1 > .menu__list-item-collapsible,
+.theme-doc-sidebar-item-category-level-1 > .menu__list-item-collapsible--active {
+  min-height: 2.5rem;
+  padding: 0 0.25rem !important;
+  background-color: transparent !important;
+  border-radius: 6px;
+}
+
+.theme-doc-sidebar-item-category-level-1 > .menu__list-item-collapsible:hover {
+  background-color: var(--ifm-menu-color-background-hover) !important;
+}
+
+/* Suppress the auto active-state background so all items look the same height */
+.menu__list-item-collapsible--active {
+  background-color: transparent !important;
+}
+
+.menu__list-item-collapsible--active:hover {
+  background-color: var(--ifm-menu-color-background-hover) !important;
+}
+
+/* Nested menu list */
+.menu__list .menu__list {
+  padding-left: 4px !important;
+}
+
+/* Nested sidebar border line */
+[class*='sidebar-item-'] ul:not(:first-child) {
+  margin-left: 16px !important;
+  border-left: 1px solid #e5e7eb;
+}
+
+[data-theme='dark'] [class*='sidebar-item-'] ul:not(:first-child) {
+  border-left-color: #2d3748;
+}
+
+/* ─── Sidebar link colour & hover fixes ─────────────────────── */
+
+/* Doc links: ensure a visible colour in both themes */
+.menu__link {
+  color: var(--ifm-menu-color);
+}
+
+.menu__link:hover {
+  color: var(--ifm-color-primary);
+  background-color: var(--ifm-menu-color-background-hover);
+  text-decoration: none;
+}
+
+/* External / type:"link" items — subtle right-arrow hint */
+.menu__list-item--collapsed ~ .menu__link[href^="http"],
+.menu__link[href^="http"] {
+  color: var(--ifm-menu-color);
+}
+
+[data-theme='dark'] .menu__link {
+  color: #9ca3af;
+}
+
+[data-theme='dark'] .menu__link:hover {
+  color: var(--ifm-color-primary);
+}
+
+/* =========================================
+   TABLE OF CONTENTS
+   ========================================= */
+.table-of-contents {
+  font-size: 13px;
+}
+
+.table-of-contents__link {
+  color: #6b7280;
+  line-height: 1.5;
+}
+
+.table-of-contents__link:hover {
+  color: var(--ifm-color-primary);
+}
+
+.table-of-contents__link--active {
+  font-weight: 600;
+  color: var(--ifm-color-primary);
+}
+
+[data-theme='dark'] .table-of-contents__link {
+  color: #9ca3af;
+}
+
+/* =========================================
+   IMAGES & MEDIA
+   ========================================= */
+img,
+video {
+  border-radius: var(--ifm-border-radius);
+}
+
+/* Prevent video iframes (Loom, YouTube, etc.) from overflowing the
+   content column and overlapping the right-hand TOC sidebar. */
+.theme-doc-markdown iframe {
+  max-width: 100%;
+}
+
+/* =========================================
+   FOOTER
+   ========================================= */
+.footer {
+  background: #0d1117;
+}
+
+.footer__copyright {
+  font-size: 13px;
+  color: #6b7280;
+}
+
+.footer__link-item {
+  color: #8b949e;
+  font-size: 14px;
+}
+
+.footer__link-item:hover {
+  text-decoration: none;
+  color: #c9d1d9;
+}
+
+.footer__title {
+  color: #f0f6fc;
+  font-size: 14px;
+  font-weight: 600;
+}
+
+.footer__bottom {
+  margin: 40px auto 10px auto;
+}
+
+/* =========================================
+   AVATAR
+   ========================================= */
+.avatar__name > a {
+  color: inherit;
+}
+
+/* =========================================
+   NAVBAR ICON LINKS (GitHub, Discord)
+   ========================================= */
+.header-github-link,
+.header-discord-link {
+  display: flex;
+  align-items: center;
+}
+
+.header-github-link:hover,
+.header-discord-link:hover {
+  opacity: 0.65;
+}
+
+/* Hide text label, show only the icon */
+.header-github-link::before,
+.header-discord-link::before {
+  content: '';
+  width: 22px;
+  height: 22px;
+  display: flex;
+}
+
+.header-github-link::before {
+  background: url("data:image/svg+xml,%3Csvg viewBox='0 0 24 24' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath d='M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12'/%3E%3C/svg%3E")
+    no-repeat center / contain;
+}
+
+[data-theme='dark'] .header-github-link::before {
+  background: url("data:image/svg+xml,%3Csvg viewBox='0 0 24 24' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath fill='white' d='M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12'/%3E%3C/svg%3E")
+    no-repeat center / contain;
+}
+
+/* Discord icon */
+.header-discord-link::before {
+  background: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 24 24'%3E%3Cpath fill='%23111' d='M20.317 4.37a19.791 19.791 0 0 0-4.885-1.515.074.074 0 0 0-.079.037c-.21.375-.444.864-.608 1.25a18.27 18.27 0 0 0-5.487 0 12.64 12.64 0 0 0-.617-1.25.077.077 0 0 0-.079-.037A19.736 19.736 0 0 0 3.677 4.37a.07.07 0 0 0-.032.027C.533 9.046-.32 13.58.099 18.057a.082.082 0 0 0 .031.057 19.9 19.9 0 0 0 5.993 3.03.078.078 0 0 0 .084-.028c.462-.63.874-1.295 1.226-1.994a.076.076 0 0 0-.041-.106 13.107 13.107 0 0 1-1.872-.892.077.077 0 0 1-.008-.128 10.2 10.2 0 0 0 .372-.292.074.074 0 0 1 .077-.01c3.928 1.793 8.18 1.793 12.062 0a.074.074 0 0 1 .078.01c.12.098.246.198.373.292a.077.077 0 0 1-.006.127 12.299 12.299 0 0 1-1.873.892.077.077 0 0 0-.041.107c.36.698.772 1.362 1.225 1.993a.076.076 0 0 0 .084.028 19.839 19.839 0 0 0 6.002-3.03.077.077 0 0 0 .032-.054c.5-5.177-.838-9.674-3.549-13.66a.061.061 0 0 0-.031-.03zM8.02 15.33c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.956-2.419 2.157-2.419 1.21 0 2.176 1.096 2.157 2.42 0 1.333-.956 2.418-2.157 2.418zm7.975 0c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.955-2.419 2.157-2.419 1.21 0 2.176 1.096 2.157 2.42 0 1.333-.946 2.418-2.157 2.418z'/%3E%3C/svg%3E")
+    no-repeat center / contain;
+}
+
+[data-theme='dark'] .header-discord-link::before {
+  background: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 24 24'%3E%3Cpath fill='white' d='M20.317 4.37a19.791 19.791 0 0 0-4.885-1.515.074.074 0 0 0-.079.037c-.21.375-.444.864-.608 1.25a18.27 18.27 0 0 0-5.487 0 12.64 12.64 0 0 0-.617-1.25.077.077 0 0 0-.079-.037A19.736 19.736 0 0 0 3.677 4.37a.07.07 0 0 0-.032.027C.533 9.046-.32 13.58.099 18.057a.082.082 0 0 0 .031.057 19.9 19.9 0 0 0 5.993 3.03.078.078 0 0 0 .084-.028c.462-.63.874-1.295 1.226-1.994a.076.076 0 0 0-.041-.106 13.107 13.107 0 0 1-1.872-.892.077.077 0 0 1-.008-.128 10.2 10.2 0 0 0 .372-.292.074.074 0 0 1 .077-.01c3.928 1.793 8.18 1.793 12.062 0a.074.074 0 0 1 .078.01c.12.098.246.198.373.292a.077.077 0 0 1-.006.127 12.299 12.299 0 0 1-1.873.892.077.077 0 0 0-.041.107c.36.698.772 1.362 1.225 1.993a.076.076 0 0 0 .084.028 19.839 19.839 0 0 0 6.002-3.03.077.077 0 0 0 .032-.054c.5-5.177-.838-9.674-3.549-13.66a.061.061 0 0 0-.031-.03zM8.02 15.33c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.956-2.419 2.157-2.419 1.21 0 2.176 1.096 2.157 2.42 0 1.333-.956 2.418-2.157 2.418zm7.975 0c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.955-2.419 2.157-2.419 1.21 0 2.176 1.096 2.157 2.42 0 1.333-.946 2.418-2.157 2.418z'/%3E%3C/svg%3E")
+    no-repeat center / contain;
+}
+
+/* =========================================
+   SEARCH BAR — hide from navbar (it lives in sidebar)
+   ========================================= */
+[class^='navbarSearchContainer'],
+[class*='navbarSearchContainer'] {
+  display: none !important;
+}
+
+/* =========================================
+   INKEEP AI CHAT BUTTON — minimal floating style
+   ========================================= */
+.ikp-chat-button__button {
+  width: 42px !important;
+  height: 42px !important;
+  border-radius: 50% !important;
+  box-shadow: 0 2px 8px rgba(0, 0, 0, 0.18) !important;
+  margin-right: 1rem !important;
+  margin-bottom: 1rem !important;
+}
+
+/* =========================================
+   NAVBAR — mobile fixes
+   ========================================= */
+
+/* On small screens: hide icon links (GitHub, Discord) and text links
+   from the right section. Keep only the color mode toggle.
+   All nav items remain accessible inside the hamburger drawer. */
+@media (max-width: 996px) {
+  /* Hide GitHub and Discord icon links */
+  .header-github-link,
+  .header-discord-link {
+    display: none !important;
+  }
+
+  /* Hide anchor links in the right section (e.g. Cost Map) */
+  .navbar__items--right > a.navbar__link {
+    display: none !important;
+  }
+
+  /* Keep the right section visible (color mode toggle lives here) */
+  .navbar__items--right {
+    display: flex !important;
+    flex: 0 0 auto;
+  }
+
+  /* Force navbar to stay on a single row, no wrapping */
+  .navbar__inner {
+    flex-wrap: nowrap !important;
+    align-items: center;
+  }
+
+  /* Keep hamburger and logo side by side (not stacked) */
+  .navbar__brand-col {
+    display: flex !important;
+    align-items: center;
+    gap: 0.5rem;
+  }
+
+  /* Ensure hamburger is always shown */
+  .navbar__toggle {
+    display: flex !important;
+  }
+}
+
+/* Hide theme toggle in mobile sidebar (slide-out drawer) */
+.navbar-sidebar .navbar-sidebar__brand [class*="toggle"] {
+  display: none !important;
+}
+
+/* =========================================
+   BASH / SHELL CODE BLOCKS
+   ========================================= */
+
+/* Subtle grey bash/shell blocks — light mode */
+[data-theme='light'] [class*='language-bash'] .prism-code,
+[data-theme='light'] [class*='language-sh'] .prism-code,
+[data-theme='light'] [class*='language-shell'] .prism-code,
+[data-theme='light'] [class*='language-zsh'] .prism-code {
+  background-color: #f3f4f6 !important;
+  border: 1px solid #d1d5db !important;
+  border-left: 3px solid #6b7280 !important;
+  color: #1f2937 !important;
+}
+
+[data-theme='light'] [class*='language-bash'] .prism-code span,
+[data-theme='light'] [class*='language-sh'] .prism-code span,
+[data-theme='light'] [class*='language-shell'] .prism-code span,
+[data-theme='light'] [class*='language-zsh'] .prism-code span {
+  color: #1f2937 !important;
+}
+
+/* Dark mode — slightly lighter than the default near-black */
+[data-theme='dark'] [class*='language-bash'] .prism-code,
+[data-theme='dark'] [class*='language-sh'] .prism-code,
+[data-theme='dark'] [class*='language-shell'] .prism-code,
+[data-theme='dark'] [class*='language-zsh'] .prism-code {
+  background-color: #1c2130 !important;
+  border: 1px solid #2d3748 !important;
+  border-left: 3px solid #4b5563 !important;
+}
+
+/* "$ " terminal prompt prefix on bash title bar */
+[class*='language-bash'] [class*='codeBlockTitle']::before,
+[class*='language-sh'] [class*='codeBlockTitle']::before,
+[class*='language-shell'] [class*='codeBlockTitle']::before,
+[class*='language-zsh'] [class*='codeBlockTitle']::before {
+  content: '$ ';
+  color: #6b7280;
+  font-weight: 700;
+}
+
+/* =========================================
+   LOGO (existing logo toggle logic)
+   ========================================= */
 .levo-logo-container {
   position: relative;
 }
@@ -42,7 +759,6 @@
   height: auto !important;
 }
 
-/* Show light logo by default, hide dark logo */
 .levo-logo-dark {
   display: none !important;
 }
@@ -51,7 +767,6 @@
   display: block !important;
 }
 
-/* In dark mode, hide light logo and show dark logo */
 [data-theme='dark'] .levo-logo-light {
   display: none !important;
 }
@@ -59,3 +774,23 @@
 [data-theme='dark'] .levo-logo-dark {
   display: block !important;
 }
+
+/* =========================================
+   DOC CONTENT — wider reading column
+   ========================================= */
+
+/* On large screens the default col--7 grid leaves too much dead space.
+   Expand the content column; the TOC column fills the remainder via flex. */
+@media (min-width: 1200px) {
+  .docItemCol {
+    --ifm-col-width: calc(8 / 12 * 100%) !important;
+    max-width: calc(8 / 12 * 100%) !important;
+  }
+}
+
+@media (min-width: 1600px) {
+  .docItemCol {
+    --ifm-col-width: calc(9 / 12 * 100%) !important;
+    max-width: calc(9 / 12 * 100%) !important;
+  }
+}

docs/my-website/src/theme/DocSidebar/index.js

@@ -0,0 +1,29 @@
+import React from 'react';
+import { useWindowSize } from '@docusaurus/theme-common';
+import DocSidebarDesktop from '@theme/DocSidebar/Desktop';
+import DocSidebarMobile from '@theme/DocSidebar/Mobile';
+import SearchBar from '@theme/SearchBar';
+import styles from './styles.module.css';
+
+export default function DocSidebar(props) {
+  const windowSize = useWindowSize();
+
+  const shouldRenderSidebarDesktop =
+    windowSize === 'desktop' || windowSize === 'ssr';
+
+  const shouldRenderSidebarMobile = windowSize === 'mobile';
+
+  return (
+    <>
+      {shouldRenderSidebarDesktop && (
+        <div className={styles.sidebarContainer}>
+          <div className={styles.searchBarContainer}>
+            <SearchBar />
+          </div>
+          <DocSidebarDesktop {...props} />
+        </div>
+      )}
+      {shouldRenderSidebarMobile && <DocSidebarMobile {...props} />}
+    </>
+  );
+}