events.iterate.com

Event type

events.iterate.com/agent/token-usage-reported

Normalized token counts and the model's context window for a successful LLM request. The processor translates vendor usage dialects (input_tokens vs prompt_tokens) at source, so consumers — the state tally, cost views, and compaction — see one shape.

Payload schema

llmRequestOffsetinteger

The llm-request-requested event this request ran under — the same handle the settlement carries.

modelstring

The model that saw this exact request.

maxContextTokensinteger

The model's context window, so a consumer can judge fullness from the event alone.

inputTokensinteger

Total input tokens, including cached ones.

outputTokensinteger

Total output tokens, including reasoning ones.

cachedInputTokensintegeroptional

Prompt-cache hits, where the model reports them.

reasoningOutputTokensintegeroptional

Reasoning/thinking tokens, where the model reports them.

Raw JSON schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "llmRequestOffset": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991,
      "description": "The llm-request-requested event this request ran under — the same handle the settlement carries."
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "description": "The model that saw this exact request."
    },
    "maxContextTokens": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991,
      "description": "The model's context window, so a consumer can judge fullness from the event alone."
    },
    "inputTokens": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991,
      "description": "Total input tokens, including cached ones."
    },
    "outputTokens": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991,
      "description": "Total output tokens, including reasoning ones."
    },
    "cachedInputTokens": {
      "description": "Prompt-cache hits, where the model reports them.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "reasoningOutputTokens": {
      "description": "Reasoning/thinking tokens, where the model reports them.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "llmRequestOffset",
    "model",
    "maxContextTokens",
    "inputTokens",
    "outputTokens"
  ]
}