diff --git a/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md b/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md index 0b0f4a54167..051235bc74d 100644 --- a/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md +++ b/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md @@ -26,6 +26,13 @@ This guide covers Anthropic's latest model (Claude Opus 4.5) and its advanced fe --- +| 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 | + ## Usage @@ -222,6 +229,104 @@ curl --location 'http://0.0.0.0:4000/bedrock/model/claude-4/converse' \ +## 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" + } + ] + } +' +``` + + + + + + + ## Tool Search {#tool-search} ### Usage Example @@ -336,8 +441,6 @@ tools = [ ## Programmatic Tool Calling {#programmatic-tool-calling} -### Usage Example - ```python import litellm import json @@ -428,8 +531,6 @@ print("\nFinal answer:", final_response.choices[0].message.content) ## Tool Input Examples {#tool-input-examples} -### Usage Example - ```python import litellm @@ -755,82 +856,3 @@ This combination enables: 4. **Cost control** - Effort parameter optimizes token spend 5. **Full visibility** - Track all usage metrics ---- - -## Getting Started - -### Installation - -```bash -pip install litellm --upgrade -``` - -### Configuration - -```python -import os -import litellm - -# Set your API key -os.environ["ANTHROPIC_API_KEY"] = "your-api-key" - -# LiteLLM automatically handles beta headers for all features -``` - -### Supported Models - -| 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 Endpoints - -**Note**: All features are supported on the `/chat/completions` endpoint only. - -| 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 | - -### Provider Support - -All features work across: -- ✅ Standard Anthropic API -- ✅ Azure Anthropic -- ✅ Vertex AI Anthropic -- ✅ LiteLLM Proxy - ---- - -## Conclusion - -These advanced Anthropic features in LiteLLM enable you to build more sophisticated, efficient, and cost-effective AI applications: - -- **Tool Search** scales to thousands of tools -- **Programmatic Tool Calling** reduces latency and tokens -- **Input Examples** improve accuracy -- **Effort Parameter** controls costs - -All features work seamlessly together and are supported across all Anthropic providers through LiteLLM's unified interface. - -### Resources - -- [LiteLLM Documentation](https://docs.litellm.ai/) -- [Anthropic Tool Search Docs](https://docs.litellm.ai/docs/providers/anthropic_tool_search) -- [Anthropic Programmatic Tool Calling Docs](https://docs.litellm.ai/docs/providers/anthropic_programmatic_tool_calling) -- [Anthropic Input Examples Docs](https://docs.litellm.ai/docs/providers/anthropic_tool_input_examples) -- [Anthropic Effort Parameter Docs](https://docs.litellm.ai/docs/providers/anthropic_effort) - -### Get Started Today - -```bash -pip install litellm --upgrade -``` - -Happy building! 🚀 - diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f9cc8bfa067..e51e5bb4b2b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -24604,6 +24604,58 @@ "supports_tool_choice": true, "supports_vision": true }, + "vertex_ai/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-opus-4-5@20251101": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "vertex_ai/claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index b3dc11e206c..ff8766003c4 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -24605,6 +24605,58 @@ "supports_tool_choice": true, "supports_vision": true }, + "vertex_ai/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-opus-4-5@20251101": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "vertex_ai/claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07,