Helicone · Schema

CompletionUsage.CompletionTokensDetails

Breakdown of tokens used in a completion.

AI GatewaysAI MonitoringGatewaysLLM ObservabilityLLM RoutingPrompt Management

Properties

Name	Type	Description
accepted_prediction_tokens	number	When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
audio_tokens	number	Audio input tokens generated by the model.
reasoning_tokens	number	Tokens generated by the model for reasoning.
rejected_prediction_tokens	number	When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion token

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CompletionUsage.CompletionTokensDetails",
  "title": "CompletionUsage.CompletionTokensDetails",
  "description": "Breakdown of tokens used in a completion.",
  "properties": {
    "accepted_prediction_tokens": {
      "type": "number",
      "format": "double",
      "description": "When using Predicted Outputs, the number of tokens in the prediction that\nappeared in the completion."
    },
    "audio_tokens": {
      "type": "number",
      "format": "double",
      "description": "Audio input tokens generated by the model."
    },
    "reasoning_tokens": {
      "type": "number",
      "format": "double",
      "description": "Tokens generated by the model for reasoning."
    },
    "rejected_prediction_tokens": {
      "type": "number",
      "format": "double",
      "description": "When using Predicted Outputs, the number of tokens in the prediction that did\nnot appear in the completion. However, like reasoning tokens, these tokens are\nstill counted in the total completion tokens for purposes of billing, output,\nand context window limits."
    }
  },
  "type": "object",
  "additionalProperties": false
}