--- title: "set env - [OPTIONAL] replace with your anthropic key" description: "import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';" type: skill canonical_url: https://claudary.paisolsolutions.com/skills/index-45 source: "Claudary" difficulty: intermediate author: "Claude Code Knowledge Pack" date: 2026-07-10T11:25:27.375Z license: CC-BY-4.0 attribution: "set env - [OPTIONAL] replace with your anthropic key — Claudary (https://claudary.paisolsolutions.com/skills/index-45)" --- # set env - [OPTIONAL] replace with your anthropic key import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; ## Overview --- slug: anthropic_advanced_features title: "Day 0 Support: Claude 4.5 Opus (+Advanced Features)" date: 2025-11-25T10:00:00 authors: - 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 --- import Tabs from '@theme/Tabs'; 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 | |---------|-----------------| | Tool Search | Claude Opus 4.5, Sonnet 4.5 | | Programmatic Tool Calling | Claude Opus 4.5, Sonnet 4.5 | | Input Examples | Claude Opus 4.5, Sonnet 4.5 | | Effort Parameter | Claude Opus 4.5 only | Supported Providers: [Anthropic](../../docs/providers/anthropic), [Bedrock](../../docs/providers/bedrock), [Vertex AI](../../docs/providers/vertex_partner#vertex-ai---anthropic-claude), [Azure AI](../../docs/providers/azure_ai). ## Usage ```python import os from litellm import completion # set env - [OPTIONAL] replace with your anthropic key os.environ["ANTHROPIC_API_KEY"] = "your-api-key" messages = [{"role": "user", "content": "Hey! how's it going?"}] ## OPENAI /chat/completions API format response = completion(model="claude-opus-4-5-20251101", messages=messages) print(response) ``` **1. Setup config.yaml** ```yaml model_list: - model_name: claude-4 ### RECEIVED MODEL NAME ### litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input model: claude-opus-4-5-20251101 ### MODEL NAME sent to `litellm.completion()` ### api_key: "os.environ/ANTHROPIC_API_KEY" # does os.getenv("ANTHROPIC_API_KEY") ``` **2. Start the proxy** ```bash litellm --config /path/to/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-4", "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ```bash curl --location 'http://0.0.0.0:4000/v1/messages' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "model": "claude-4", "max_tokens": 1024, "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ## Usage - Bedrock :::info LiteLLM uses the boto3 library to authenticate with Bedrock. For more ways to authenticate with Bedrock, see the [Bedrock documentation](../../docs/providers/bedrock#authentication). ::: ```python import os from litellm import completion os.environ["AWS_ACCESS_KEY_ID"] = "" os.environ["AWS_SECRET_ACCESS_KEY"] = "" os.environ["AWS_REGION_NAME"] = "" ## OPENAI /chat/completions API format response = completion( model="bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0", messages=[{ "content": "Hello, how are you?","role": "user"}] ) ``` **1. Setup config.yaml** ```yaml model_list: - model_name: claude-4 ### RECEIVED MODEL NAME ### litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input model: bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0 ### MODEL NAME sent to `litellm.completion()` ### aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY aws_region_name: os.environ/AWS_REGION_NAME ``` **2. Start the proxy** ```bash litellm --config /path/to/config.yaml ``` **3. Test it!** ```bash curl --location 'http://0.0.0.0:4000/chat/completions' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "model": "claude-4", "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ```bash curl --location 'http://0.0.0.0:4000/v1/messages' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "model": "claude-4", "max_tokens": 1024, "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ```bash curl --location 'http://0.0.0.0:4000/bedrock/model/claude-4/invoke' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello, how are you?"}] }' ``` ```bash curl --location 'http://0.0.0.0:4000/bedrock/model/claude-4/converse' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "messages": [{"role": "user", "content": "Hello, how are you?"}] }' ``` ## Usage - Vertex AI ```python from litellm import completion import json ## GET CREDENTIALS ## RUN ## # !gcloud auth application-default login - run this to add vertex credentials to your env ## OR ## file_path = 'path/to/vertex_ai_service_account.json' # Load the JSON file with open(file_path, 'r') as file: vertex_credentials = json.load(file) # Convert to JSON string vertex_credentials_json = json.dumps(vertex_credentials) ## COMPLETION CALL response = completion( model="vertex_ai/claude-opus-4-5@20251101", messages=[{ "content": "Hello, how are you?","role": "user"}], vertex_credentials=vertex_credentials_json, vertex_project="your-project-id", vertex_location="us-east5" ) ``` **1. Setup config.yaml** ```yaml model_list: - model_name: claude-4 ### RECEIVED MODEL NAME ### litellm_params: model: vertex_ai/claude-opus-4-5@20251101 vertex_credentials: "/path/to/service_account.json" vertex_project: "your-project-id" vertex_location: "us-east5" ``` **2. Start the proxy** ```bash litellm --config /path/to/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-4", "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ```bash curl --location 'http://0.0.0.0:4000/v1/messages' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data ' { "model": "claude-4", "max_tokens": 1024, "messages": [ { "role": "user", "content": "what llm are you" } ] } ' ``` ## Usage - Azure Anthropic (Azure Foundry Claude) LiteLLM funnels Azure Claude deployments through the `azure_ai/` provider so Claude Opus models on Azure Foundry keep working with Tool Search, Effort, streaming, and the rest of the advanced feature set. Point `AZURE_AI_API_BASE` to `https://.services.ai.azure.com/anthropic` (LiteLLM appends `/v1/messages` automatically) and authenticate with `AZURE_AI_API_KEY` or an Azure AD token. ```python import os from litellm import completion # Configure Azure credentials os.environ["AZURE_AI_API_KEY"] = "your-azure-ai-api-key" os.environ["AZURE_AI_API_BASE"] = "https://my-resource.services.ai.azure.com/anthropic" response = completion( model="azure_ai/claude-opus-4-1", messages=[{"role": "user", "content": "Explain how Azure Anthropic hosts Claude Opus differently from the public Anthropic API."}], max_tokens=1200, temperature=0.7, stream=True, ) for chunk in response: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True) ``` **1. Set environment variables** ```bash export AZURE_AI_API_KEY="your-azure-ai-api-key" export AZURE_AI_API_BASE="https://my-resource.services.ai.azure.com/anthropic" ``` **2. Configure the proxy** ```yaml model_list: - model_name: claude-4-azure litellm_params: model: azure_ai/claude-opus-4-1 api_key: os.environ/AZURE_AI_API_KEY api_base: os.environ/AZURE_AI_API_BASE ``` **3. Start LiteLLM** ```bash litellm --config /path/to/config.yaml ``` **4. Test the Azure Claude route** ```bash curl --location 'http://0.0.0.0:4000/chat/completions' \\ --header 'Content-Type: application/json' \\ --header 'Authorization: Bearer $LITELLM_KEY' \\ --data '{ "model": "claude-4-azure", "messages": [ { "role": "user", "content": "How do I use Claude Opus 4 via Azure Anthropic in LiteLLM?" } ], "max_tokens": 1024 }' ``` ## Tool Search {#tool-search} This lets Claude work with thousands of tools, by dynamically loading tools on-demand, instead of loading all tools into the context window upfront. ### Usage Example ```python import litellm import os # Configure your API key os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Define your tools with defer_loading tools = [ # Tool search tool (regex variant) { "type": "tool_search_tool_regex_20251119", "name": "tool_search_tool_regex" }, # Deferred tools - loaded on-demand { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather in a given location. Returns temperature and conditions.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "Temperature unit" } }, "required": ["location"] } }, "defer_loading": True # Load on-demand }, { "type": "function", "function": { "name": "search_files", "description": "Search through files in the workspace using keywords", "parameters": { "type": "object", "properties": { "query": {"type": "string"}, "file_types": { "type": "array", "items": {"type": "string"} } }, "required": ["query"] } }, "defer_loading": True }, { "type": "function", "function": { "name": "query_database", "description": "Execute SQL queries against the database", "parameters": { "type": "object", "properties": { "sql": {"type": "string"} }, "required": ["sql"] } }, "defer_loading": True } ] # Make a request - Claude will search for and use relevant tools response = litellm.completion( model="anthropic/claude-opus-4-5-20251101", messages=[{ "role": "user", "content": "What's the weather like in San Francisco?" }], tools=tools ) print("Claude's response:", response.choices[0].message.content) print("Tool calls:", response.choices[0].message.tool_calls) # Check tool search usage if hasattr(response.usage, 'server_tool_use'): print(f"Tool searches performed: {response.usage.server_tool_use.tool_search_requests}") ``` 1. Setup config.yaml ```yaml model_list: - model_name: claude-4 litellm_params: model: anthropic/claude-opus-4-5-20251101 api_key: os.environ/ANTHROPIC_API_KEY ``` 2. Start the proxy ```bash litellm --config /path/to/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-4", "messages": [{ "role": "user", "content": "What's the weather like in San Francisco?" }], "tools": [ # Tool search tool (regex variant) { "type": "tool_search_tool_regex_20251119", "name": "tool_search_tool_regex" }, # Deferred tools - loaded on-demand { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather in a given location. Returns temperature and conditions.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "Temperature unit" } }, "required": ["location"] } }, "defer_loading": True # Load on-demand }, { "type": "function", "function": { "name": "search_files", "description": "Search through files in the workspace using key --- Source: [Claudary](https://claudary.paisolsolutions.com/skills/index-45) · https://claudary.paisolsolutions.com