BetaMessageDeltaUsage Class — anthropic-sdk-python Architecture

Architecture documentation for the BetaMessageDeltaUsage class in beta_message_delta_usage.py from the anthropic-sdk-python codebase.

Class python AnthropicClient

Entity Profile

AnthropicClient→ BetaMessageDeltaUsage Class — anthropic-sdk-python Architecture

Dependency Diagram

graph TD
  f97f5e05_eb54_210b_8a35_62c38a15cbaf["BetaMessageDeltaUsage"]
  17ce5647_6f06_0676_a4a5_e378a3f57cb1["BaseModel"]
  f97f5e05_eb54_210b_8a35_62c38a15cbaf -->|extends| 17ce5647_6f06_0676_a4a5_e378a3f57cb1
  97dd8438_3d35_5356_8fdc_49ec321a6e2b["beta_message_delta_usage.py"]
  f97f5e05_eb54_210b_8a35_62c38a15cbaf -->|defined in| 97dd8438_3d35_5356_8fdc_49ec321a6e2b

Relationship Graph

Source Code

src/anthropic/types/beta/beta_message_delta_usage.py lines 12–37

class BetaMessageDeltaUsage(BaseModel):
    cache_creation_input_tokens: Optional[int] = None
    """The cumulative number of input tokens used to create the cache entry."""

    cache_read_input_tokens: Optional[int] = None
    """The cumulative number of input tokens read from the cache."""

    input_tokens: Optional[int] = None
    """The cumulative number of input tokens which were used."""

    iterations: Optional[BetaIterationsUsage] = None
    """Per-iteration token usage breakdown.

    Each entry represents one sampling iteration, with its own input/output token
    counts and cache statistics. This allows you to:

    - Determine which iterations exceeded long context thresholds (>=200k tokens)
    - Calculate the true context window size from the last iteration
    - Understand token accumulation across server-side tool use loops
    """

    output_tokens: int
    """The cumulative number of output tokens which were used."""

    server_tool_use: Optional[BetaServerToolUsage] = None
    """The number of server tool requests."""