BerriAI · Sameerlite · Feb 6, 2026 · Feb 6, 2026 · Feb 6, 2026 · Feb 6, 2026
diff --git a/docs/my-website/blog/claude_opus_4_6/index.md b/docs/my-website/blog/claude_opus_4_6/index.md
@@ -3,6 +3,10 @@ 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/
@@ -219,6 +223,156 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 </TabItem>
 </Tabs>
 
-## More Features Coming Soon
+## Compaction
+
+Litellm supports enabling compaction for the new claude-opus-4-6.
+
+### Enabling Compaction
+
+To enable compaction, add the `context_management` parameter with the `compact_20260112` edit type:
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-6",
+  "messages": [
+    {
+      "role": "user",
+      "content": "What is the weather in San Francisco?"
+    }
+  ],
+  "context_management": {
+    "edits": [
+      {
+        "type": "compact_20260112"
+      }
+    ]
+  },
+  "max_tokens": 100
+}'
+```
+All the parameters supported for context_management by anthropic are supported and can be directly added. Litellm automatically adds the `compact-2026-01-12` beta header in the request.
+
+
+### Response with Compaction Block
+
+The response will include the compaction summary in `provider_specific_fields.compaction_blocks`:
+
+```json
+{
+  "id": "chatcmpl-a6c105a3-4b25-419e-9551-c800633b6cb2",
+  "created": 1770357619,
+  "model": "claude-opus-4-6",
+  "object": "chat.completion",
+  "choices": [
+    {
+      "finish_reason": "length",
+      "index": 0,
+      "message": {
+        "content": "I don't have access to real-time data, so I can't provide the current weather in San Francisco. To get up-to-date weather information, I'd recommend checking:\n\n- **Weather websites** like weather.com, accuweather.com, or wunderground.com\n- **Search engines** – just Google \"San Francisco weather\"\n- **Weather apps** on your phone (e.g., Apple Weather, Google Weather)\n- **National",
+        "role": "assistant",
+        "provider_specific_fields": {
+          "compaction_blocks": [
+            {
+              "type": "compaction",
+              "content": "Summary of the conversation: The user requested help building a web scraper..."
+            }
+          ]
+        }
+      }
+    }
+  ],
+  "usage": {
+    "completion_tokens": 100,
+    "prompt_tokens": 86,
+    "total_tokens": 186
+  }
+}
+```
+
+### Using Compaction Blocks in Follow-up Requests
+
+To continue the conversation with compaction, include the compaction block in the assistant message's `provider_specific_fields`:
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-6",
+  "messages": [
+    {
+      "role": "user",
+      "content": "How can I build a web scraper?"
+    },
+    {
+      "role": "assistant",
+      "content": [
+        {
+          "type": "text",
+          "text": "Certainly! To build a basic web scraper, you'll typically use a programming language like Python along with libraries such as `requests` (for fetching web pages) and `BeautifulSoup` (for parsing HTML). Here's a basic example:\n\n```python\nimport requests\nfrom bs4 import BeautifulSoup\n\nurl = 'https://example.com'\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, 'html.parser')\n\n# Extract and print all text\ntext = soup.get_text()\nprint(text)\n```\n\nLet me know what you're interested in scraping or if you need help with a specific website!"
+        }
+      ],
+      "provider_specific_fields": {
+        "compaction_blocks": [
+          {
+            "type": "compaction",
+            "content": "Summary of the conversation: The user asked how to build a web scraper, and the assistant gave an overview using Python with requests and BeautifulSoup."
+          }
+        ]
+      }
+    },
+    {
+      "role": "user",
+      "content": "How do I use it to scrape product prices?"
+    }
+  ],
+  "context_management": {
+    "edits": [
+      {
+        "type": "compact_20260112"
+      }
+    ]
+  },
+  "max_tokens": 100
+}'
+```
+
+### Streaming Support
+
+Compaction blocks are also supported in streaming mode. You'll receive:
+- `compaction_start` event when a compaction block begins
+- `compaction_delta` events with the compaction content
+- The accumulated `compaction_blocks` in `provider_specific_fields`
+
+
+## Effort Levels
+
+Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `effort` parameter:
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-6",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Explain quantum computing"
+    }
+  ],
+  "effort": "max"
+}'
+```
+
+## 1M Token Context (Beta)
+
+Opus 4.6 supports 1M token context. Premium pricing applies for prompts exceeding 200k tokens ($10/$37.50 per million input/output tokens). LiteLLM supports cost calculations for 1M token contexts.
+
+## US-Only Inference
+
+Available at 1.1× token pricing. LiteLLM supports this pricing model.
 
-We're actively working on supporting new features for Claude Opus 4.6. Stay tuned for updates!
diff --git a/docs/my-website/docs/tutorials/claude_code_beta_headers.md b/docs/my-website/docs/tutorials/claude_code_beta_headers.md
@@ -0,0 +1,129 @@
+import Image from '@theme/IdealImage';
+
+# Claude Code - Fixing Invalid Beta Header Errors
+
+When using Claude Code with LiteLLM and non-Anthropic providers (Bedrock, Azure AI, Vertex AI), you may encounter "invalid beta header" errors. This guide explains how to fix these errors locally or contribute a fix to LiteLLM.
+
+## What Are Beta Headers?
+
+Anthropic uses beta headers to enable experimental features in Claude. When you use Claude Code, it may send beta headers like:
+
+```
+anthropic-beta: prompt-caching-scope-2026-01-05,advanced-tool-use-2025-11-20
+```
+
+However, not all providers support all Anthropic beta features. When an unsupported beta header is sent to a provider, you'll see an error.
+
+## Common Error Message
+
+```bash
+Error: The model returned the following errors: invalid beta flag
+```
+
+## How LiteLLM Handles Beta Headers
+
+LiteLLM automatically filters out unsupported beta headers using a configuration file:
+
+```
+litellm/litellm/anthropic_beta_headers_config.json
+```
+
+This JSON file lists which beta headers are **unsupported** for each provider. Headers not in the unsupported list are passed through to the provider.
+
+## Quick Fix: Update Config Locally
+
+If you encounter an invalid beta header error, you can fix it immediately by updating the config file locally.
+
+### Step 1: Locate the Config File
+
+Find the file in your LiteLLM installation:
+
+```bash
+# If installed via pip
+cd $(python -c "import litellm; import os; print(os.path.dirname(litellm.__file__))")
+
+# The config file is at:
+# litellm/anthropic_beta_headers_config.json
+```
+
+### Step 2: Add the Unsupported Header
+
+Open `anthropic_beta_headers_config.json` and add the problematic header to the appropriate provider's list:
+
+```json title="anthropic_beta_headers_config.json"
+{
+  "description": "Unsupported Anthropic beta headers for each provider. Headers listed here will be dropped. Headers not listed are passed through as-is.",
+  "anthropic": [],
+  "azure_ai": [],
+  "bedrock_converse": [
+    "prompt-caching-scope-2026-01-05",
+    "bash_20250124",
+    "bash_20241022",
+    "text_editor_20250124",
+    "text_editor_20241022",
+    "compact-2026-01-12",
+    "advanced-tool-use-2025-11-20",
+    "web-fetch-2025-09-10",
+    "code-execution-2025-08-25",
+    "skills-2025-10-02",
+    "files-api-2025-04-14"
+  ],
+  "bedrock": [
+    "advanced-tool-use-2025-11-20",
+    "prompt-caching-scope-2026-01-05",
+    "structured-outputs-2025-11-13",
+    "web-fetch-2025-09-10",
+    "code-execution-2025-08-25",
+    "skills-2025-10-02",
+    "files-api-2025-04-14"
+  ],
+  "vertex_ai": [
+    "prompt-caching-scope-2026-01-05"
+  ]
+}
+```
+
+### Step 3: Restart Your Application
+
+After updating the config file, restart your LiteLLM proxy or application:
+
+```bash
+# If using LiteLLM proxy
+litellm --config config.yaml
+
+# If using Python SDK
+# Just restart your Python application
+```
+
+The updated configuration will be loaded automatically.
+
+## Contributing a Fix to LiteLLM
+
+Help the community by contributing your fix! If your local changes work, please raise a PR with the addition of the header and we will merge it.
+
+
+## How Beta Header Filtering Works
+
+When you make a request through LiteLLM:
+
+```mermaid
+sequenceDiagram
+    participant CC as Claude Code
+    participant LP as LiteLLM
+    participant Config as Beta Headers Config
+    participant Provider as Provider (Bedrock/Azure/etc)
+
+    CC->>LP: Request with beta headers
+    Note over CC,LP: anthropic-beta: header1,header2,header3
+
+    LP->>Config: Load unsupported headers for provider
+    Config-->>LP: Returns unsupported list
+
+    Note over LP: Filter headers:<br/>- Remove unsupported<br/>- Keep supported
+
+    LP->>Provider: Request with filtered headers
+    Note over LP,Provider: anthropic-beta: header2<br/>(header1, header3 removed)
+
+    Provider-->>LP: Success response
+    LP-->>CC: Response
+```
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
@@ -129,6 +129,7 @@ const sidebars = {
             "tutorials/claude_mcp",
             "tutorials/claude_non_anthropic_models",
             "tutorials/claude_code_plugin_marketplace",
+            "tutorials/claude_code_beta_headers",
           ]
         },
         "tutorials/opencode_integration",

diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json
@@ -0,0 +1,30 @@
+{
+  "description": "Unsupported Anthropic beta headers for each provider. Headers listed here will be dropped. Headers not listed are passed through as-is.",
+  "anthropic": [],
+  "azure_ai": [],
+  "bedrock_converse": [
+    "prompt-caching-scope-2026-01-05",
+    "bash_20250124",
+    "bash_20241022",
+    "text_editor_20250124",
+    "text_editor_20241022",
+    "compact-2026-01-12",
+    "advanced-tool-use-2025-11-20",
+    "web-fetch-2025-09-10",
+    "code-execution-2025-08-25",
+    "skills-2025-10-02",
+    "files-api-2025-04-14"
+  ],
+  "bedrock": [
+    "advanced-tool-use-2025-11-20",
+    "prompt-caching-scope-2026-01-05",
+    "structured-outputs-2025-11-13",
+    "web-fetch-2025-09-10",
+    "code-execution-2025-08-25",
+    "skills-2025-10-02",
+    "files-api-2025-04-14"
+  ],
+  "vertex_ai": [
+    "prompt-caching-scope-2026-01-05"
+  ]
+}