> ## Documentation Index
> Fetch the complete documentation index at: https://www.getmaxim.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# anthropic.Utils

> Utility functions and helpers for Anthropic integration.

[View module source on GitHub](https://github.com/maximhq/maxim-py/blob/main/maxim/logger/anthropic/utils.py)

## [AnthropicUtils](/sdk/python/references/logger/anthropic/utils)

```python theme={null}
class AnthropicUtils()
```

Utility class for Anthropic API integration with [Maxim](/sdk/python/references/maxim).

This class provides static utility methods for parsing and processing
Anthropic API requests and responses to integrate with [Maxim](/sdk/python/references/maxim)'s logging
and monitoring system. It handles message format conversion, parameter
extraction, and response standardization.

All methods are static and can be called directly on the class without
instantiation.

#### parse\_message\_param

```python theme={null}
@staticmethod
def parse_message_param(
        message: Iterable[MessageParam],
        override_role: Optional[str] = None) -> List[GenerationRequestMessage]
```

Parse Anthropic message parameters into [Maxim](/sdk/python/references/maxim) format.

This method converts Anthropic MessageParam objects into [Maxim](/sdk/python/references/maxim)'s
[GenerationRequestMessage](/sdk/python/references/logger/components/generation) format for consistent logging and tracking.
It handles various message formats including string content and
structured content blocks.

**Arguments**:

| Name      | Type                      | Description                              |
| --------- | ------------------------- | ---------------------------------------- |
| `message` | *Iterable\[MessageParam]* | Iterable of Anthropic message parameters |

to be parsed. Can contain strings, dicts, or MessageParam objects.

* `override_role` *Optional\[str]* - Optional role to override the message role.
  If provided, all messages will use this role instead of their original role.

**Returns**:

| Name                                                                                    | Description                                                              |
| --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------ |
| `List[[GenerationRequestMessage](/sdk/python/references/logger/components/generation)]` | List of parsed messages in [Maxim](/sdk/python/references/maxim) format, |

with role and content extracted and standardized.

**Notes**:

* String messages are treated as user messages by default
* Dict messages should have 'role' and 'content' keys
* Content blocks are flattened into text content
* Complex content structures are converted to string representation

#### get\_model\_params

```python theme={null}
@staticmethod
def get_model_params(max_tokens: int, **kwargs: Any) -> Dict[str, Any]
```

Extract and normalize model parameters for [Maxim](/sdk/python/references/maxim) logging.

This method extracts relevant model parameters from Anthropic API
calls and formats them for consistent logging in [Maxim](/sdk/python/references/maxim). It handles
common parameters like temperature, top\_p, and other generation settings.

**Arguments**:

| Name         | Type  | Description                                   |
| ------------ | ----- | --------------------------------------------- |
| `max_tokens` | *int* | Maximum number of tokens to generate.         |
| `**kwargs`   | *Any* | Additional keyword arguments that may contain |

model parameters such as temperature, top\_p, top\_k, system, etc.

**Returns**:

Dict\[str, Any]: Dictionary containing normalized model parameters
with non-None values only. Common parameters are extracted
explicitly while additional parameters are included as-is.

**Notes**:

* Only non-None parameters are included in the result
* System, metadata, temperature, top\_p, and top\_k are handled explicitly
* Additional parameters from kwargs are included if they have values

#### parse\_message\_stream

```python theme={null}
@staticmethod
def parse_message_stream(stream: List[MessageStreamEvent]) -> Dict[str, Any]
```

Parse a list of Anthropic stream events into standardized format.

This method processes a complete stream of MessageStreamEvent objects
and converts them into a standardized response format compatible with
OpenAI-style responses for consistent logging and processing.

**Arguments**:

| Name     | Type                        | Description                |
| -------- | --------------------------- | -------------------------- |
| `stream` | *List\[MessageStreamEvent]* | List of stream events from |

Anthropic's streaming API response.

**Returns**:

Dict\[str, Any]: Standardized response dictionary with the following structure:

* id: Unique identifier for the response
* created: Unix timestamp of creation
* choices: List with single choice containing message and finish\_reason
* usage: Token usage statistics (prompt, completion, total)

**Raises**:

* `ValueError` - If the stream list is empty.

**Notes**:

* Text content is extracted from content\_block\_delta events
* Token usage is extracted from message\_start events
* The response format mimics OpenAI's API for compatibility
* Finish reason is set to "stop" by default (Anthropic doesn't provide this directly)

#### parse\_message

```python theme={null}
@staticmethod
def parse_message(message: Any) -> Dict[str, Any]
```

Parse an Anthropic [Message](/sdk/python/references/models/prompt) response into standardized format.

This method converts an Anthropic [Message](/sdk/python/references/models/prompt) object into a standardized
response format compatible with OpenAI-style responses for consistent
logging and processing across different AI providers.

**Arguments**:

| Name      | Type  | Description                                                                                  |
| --------- | ----- | -------------------------------------------------------------------------------------------- |
| `message` | *Any* | Anthropic [Message](/sdk/python/references/models/prompt) object containing the API response |

with content, usage statistics, and metadata.

**Returns**:

Dict\[str, Any]: Standardized response dictionary with the following structure:

* id: [Message](/sdk/python/references/models/prompt) ID from Anthropic
* created: Unix timestamp of parsing time
* choices: List with single choice containing message and finish\_reason
* usage: Token usage statistics (input, output, total tokens)

**Notes**:

* Content blocks are flattened into a single text string
* Both structured content blocks and dict-based content are supported
* Token usage is extracted from the message's usage attribute
* Stop reason is mapped from Anthropic's stop\_reason or defaults to "stop"
* The response format mimics OpenAI's API for cross-provider compatibility