Messages Types

The Messages API types are Pydantic models used by any_llm.api.messages() and any_llm.api.amessages().

Primary Types

MessageResponse

Full response from the Messages API.

Import: from any_llm.types.messages import MessageResponse

Field	Type	Description
id	str
type	str
role	str
content	list[MessageContentBlock]
model	str
stop_reason	str | None
usage	MessageUsage

MessageContentBlock

Content block in a Messages API response.

Import: from any_llm.types.messages import MessageContentBlock

Field	Type	Description
type	str	Block type: ‘text’, ‘tool_use’, or ‘thinking’
text	str | None	Text content (for type=‘text’)
id	str | None	Tool use ID (for type=‘tool_use’)
name	str | None	Tool name (for type=‘tool_use’)
input	dict[str, Any] | None	Tool input (for type=‘tool_use’)
thinking	str | None	Thinking content (for type=‘thinking’)

MessageUsage

Token usage information for Messages API.

Import: from any_llm.types.messages import MessageUsage

Field	Type	Description
input_tokens	int
output_tokens	int
cache_creation_input_tokens	int | None
cache_read_input_tokens	int | None

MessageStreamEvent

Server-sent event for Messages API streaming.

Import: from any_llm.types.messages import MessageStreamEvent

Field	Type	Description
type	str	Event type (message_start, content_block_start, content_block_delta, content_block_stop, message_delta, message_stop)
index	int | None	Content block index
content_block	MessageContentBlock | None	Content block (for content_block_start)
delta	dict[str, Any] | None	Delta update
message	MessageResponse | None	Full message (for message_start)
usage	MessageUsage | None	Usage information (for message_delta)

Internal Types

MessagesParams

Normalized parameters for the Anthropic Messages API, used internally to pass structured parameters from the public API to provider implementations.

Import: from any_llm.types.messages import MessagesParams

Field	Type	Description
model	str	Model identifier
messages	list[dict[str, Any]]	List of messages for the conversation
max_tokens	int	Maximum number of tokens to generate (required by Anthropic API)
system	str | None	System prompt
temperature	float | None	Controls randomness in the response (0.0 to 1.0)
top_p	float | None	Controls diversity via nucleus sampling
top_k	int | None	Only sample from the top K options for each subsequent token
stream	bool | None	Whether to stream the response
stop_sequences	list[str] | None	Custom text sequences that will cause the model to stop generating
tools	list[dict[str, Any]] | None	List of tools in Anthropic format ({name, description, input_schema})
tool_choice	dict[str, Any] | None	Controls which tool the model uses
metadata	dict[str, Any] | None	Request metadata
thinking	dict[str, Any] | None	Thinking/reasoning configuration