strands.models.model

Abstract base class for Agent model providers.

CacheConfig

@dataclass
class CacheConfig()

Defined in: src/strands/models/model.py:26

Configuration for prompt caching.

Attributes:

• strategy - Caching strategy to use.
  • “auto”: Automatically detect model support and inject cachePoint to maximize cache coverage
  • “anthropic”: Inject cachePoint in Anthropic-compatible format without model support check

Model

class Model(abc.ABC)

Defined in: src/strands/models/model.py:38

Abstract base class for Agent model providers.

This class defines the interface for all model implementations in the Strands Agents SDK. It provides a standardized way to configure and process requests for different AI model providers.

stateful

@property
def stateful() -> bool

Defined in: src/strands/models/model.py:46

Whether the model manages conversation state server-side.

Returns:

False by default. Model providers that support server-side state should override this.

update_config

@abc.abstractmethod
def update_config(**model_config: Any) -> None

Defined in: src/strands/models/model.py:56

Update the model configuration with the provided arguments.

Arguments:

• **model_config - Configuration overrides.

get_config

@abc.abstractmethod
def get_config() -> Any

Defined in: src/strands/models/model.py:66

Return the model configuration.

Returns:

The model’s configuration.

structured_output

@abc.abstractmethod
def structured_output(
        output_model: type[T],
        prompt: Messages,
        system_prompt: str | None = None,
        **kwargs: Any) -> AsyncGenerator[dict[str, T | Any], None]

Defined in: src/strands/models/model.py:76

Get structured output from the model.

Arguments:

• output_model - The output model to use for the agent.
• prompt - The prompt messages to use for the agent.
• system_prompt - System prompt to provide context to the model.
• **kwargs - Additional keyword arguments for future extensibility.

Yields:

Model events with the last being the structured output.

Raises:

• ValidationException - The response format from the model does not match the output_model

stream

@abc.abstractmethod
def stream(messages: Messages,
           tool_specs: list[ToolSpec] | None = None,
           system_prompt: str | None = None,
           *,
           tool_choice: ToolChoice | None = None,
           system_prompt_content: list[SystemContentBlock] | None = None,
           invocation_state: dict[str, Any] | None = None,
           **kwargs: Any) -> AsyncIterable[StreamEvent]

Defined in: src/strands/models/model.py:97

Stream conversation with the model.

This method handles the full lifecycle of conversing with the model:

1. Format the messages, tool specs, and configuration into a streaming request
2. Send the request to the model
3. Yield the formatted message chunks

Arguments:

• messages - List of message objects to be processed by the model.
• tool_specs - List of tool specifications to make available to the model.
• system_prompt - System prompt to provide context to the model.
• tool_choice - Selection strategy for tool invocation.
• system_prompt_content - System prompt content blocks for advanced features like caching.
• invocation_state - Caller-provided state/context that was passed to the agent when it was invoked.
• **kwargs - Additional keyword arguments for future extensibility.

Yields:

Formatted message chunks from the model.

Raises:

• ModelThrottledException - When the model service is throttling requests from the client.

_ModelPlugin

class _ModelPlugin(Plugin)

Defined in: src/strands/models/model.py:134

Plugin that manages model-related lifecycle hooks.

name

@property
def name() -> str

Defined in: src/strands/models/model.py:138

A stable string identifier for this plugin.

init_agent

def init_agent(agent: "Agent") -> None

Defined in: src/strands/models/model.py:156

Register model lifecycle hooks with the agent.

Arguments:

• agent - The agent instance to register hooks with.