12 pages for modelusage.

Events Claude Developer Platform · in the page api/beta/sessions/events …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… List Events Claude Developer Platform · in the page api/beta/sessions/events/list …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… Stream Events Claude Developer Platform · in the page api/beta/sessions/events/stream …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… Threads Claude Developer Platform · in the page api/beta/sessions/threads …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… Events Claude Developer Platform · in the page api/beta/sessions/threads/events …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… List Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/list …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… Stream Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/stream …e: "span.outcome_evaluation_end"` - `usage: BetaManagedAgentsSpanModelUsage` Token usage for a single model request. - `cache_creation_input_tokens: number` Tokens used to… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …u read them. The `usage` field covers only the main agent loop. Use `modelUsage`, or `model_usage` in Python, for whole-tree token and cost accounting. See [Tracking costs and usage](/docs/en/agent-s… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …(`message.message.id`, `message.message.usage`), per-model cost via `modelUsage` on the result message, and a cumulative total on the result message. * **Python** provides per-step token breakdowns o… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …e = None structured_output: Any = None model_usage: dict[str, ModelUsage] | None = None permission_denials: list[Any] | None = None deferred_tool_use: DeferredToolUse | None = None… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …r; total_cost_usd: number; usage: NonNullableUsage; modelUsage: { [modelName: string]: ModelUsage }; permission_denials: SDKPermissionDenial[]; queued_turn_count?: number… Model configuration Claude Code CLI · in the page model-config …utput-format json` and `stream-json`; read the actual model from the `modelUsage` field of the [result message](/docs/en/headless#get-structured-output) instead. For example, start a session on Opus:…