From 0ca08e52d874b6ec1f2e848da11b8398a31bfa19 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Sat, 7 Feb 2026 13:07:20 +0530 Subject: [PATCH] Update opus 4.6 blog with adaptive thinking --- docs/my-website/blog/claude_opus_4_6/index.md | 403 ++++++++++++++++++ 1 file changed, 403 insertions(+) create mode 100644 docs/my-website/blog/claude_opus_4_6/index.md diff --git a/docs/my-website/blog/claude_opus_4_6/index.md b/docs/my-website/blog/claude_opus_4_6/index.md new file mode 100644 index 00000000000..0397f1288f7 --- /dev/null +++ b/docs/my-website/blog/claude_opus_4_6/index.md @@ -0,0 +1,403 @@ +--- +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 +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 +--- + +import Tabs from '@theme/Tabs'; +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. + +## Docker Image + +```bash +docker pull ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.80.0-stable.opus-4-6 +``` + +## Usage - Anthropic + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-6 + litellm_params: + model: anthropic/claude-opus-4-6 + api_key: os.environ/ANTHROPIC_API_KEY +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.80.0-stable.opus-4-6 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-6", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Azure + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-6 + litellm_params: + model: azure_ai/claude-opus-4-6 + api_key: os.environ/AZURE_AI_API_KEY + api_base: os.environ/AZURE_AI_API_BASE # https://.services.ai.azure.com +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e AZURE_AI_API_KEY=$AZURE_AI_API_KEY \ + -e AZURE_AI_API_BASE=$AZURE_AI_API_BASE \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.80.0-stable.opus-4-6 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-6", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Vertex AI + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-6 + litellm_params: + model: vertex_ai/claude-opus-4-6 + vertex_project: os.environ/VERTEX_PROJECT + vertex_location: us-east5 +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e VERTEX_PROJECT=$VERTEX_PROJECT \ + -e GOOGLE_APPLICATION_CREDENTIALS=/app/credentials.json \ + -v $(pwd)/config.yaml:/app/config.yaml \ + -v $(pwd)/credentials.json:/app/credentials.json \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.80.0-stable.opus-4-6 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-6", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Bedrock + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-6 + litellm_params: + model: bedrock/anthropic.claude-opus-4-6-v1:0 + aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID + aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY + aws_region_name: us-east-1 +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \ + -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.80.0-stable.opus-4-6 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```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 llm are you" + } + ] +}' +``` + + + + +## 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` + + +## Adaptive Thinking + +LiteLLM supports adaptive thinking through the `reasoning_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": "Solve this complex problem: What is the optimal strategy for..." + } + ], + "reasoning_effort": "high" +}' +``` + +## Effort Levels + +Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `output_config` 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" + } + ], + "output_config": { + "effort": "medium" + } + +}' +``` + +You can use reasoning effort plus output_config to have more control on the model. + +## 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. +