End User Costs API

Get cost breakdown by model for a specific end-user

Returns cost aggregation grouped by AI model for the specified end-user. Call it with a GET request to /end-user-costs/{externalId}/by-model, authenticated with a restricted API key and the "costs:read" scope.

GET https://api.bearlumen.com/v1/end-user-costs/{externalId}/by-model

Returns cost aggregation grouped by AI model for the specified end-user. Requests count toward your per-API-key rate limit; sustained overruns return 429 with the standard error envelope.

Authentication and scopes

Authenticate with a restricted API key in the Authorization: Bearer <key> header. This endpoint requires the costs:read scope.

Parameters

Name	In	Type	Required	Description
`externalId`	path	`string`	Yes	End-user identifier you assigned when sending usage events (the user_id field on POST /usage-events). An end user exists only after at least one event referencing this identifier has been ingested; unknown identifiers return 404.
`start_date`	query	`string`	Yes	Start of date range (ISO 8601, inclusive).
`end_date`	query	`string`	Yes	End of date range (ISO 8601, exclusive).

Response example

Success response (200):

{
  "end_user_id": "eb77aa11-0001-7777-9a1b-2c3d4e5f6a01",
  "models": [
    {
      "cache_creation_cost": "1.86",
      "cache_creation_input_tokens": 88400,
      "cache_read_cost": "1.21",
      "cache_read_input_tokens": 403200,
      "event_count": 2,
      "input_cost": "507.03",
      "input_tokens": 729100,
      "model_slug": "gpt-4o",
      "output_cost": "253.26",
      "output_tokens": 182700,
      "percent_of_total": 40,
      "provider_slug": "unknown",
      "reasoning_cost": null,
      "reasoning_tokens": null,
      "total_cost": "763.36"
    },
    {
      "cache_creation_cost": null,
      "cache_creation_input_tokens": null,
      "cache_read_cost": null,
      "cache_read_input_tokens": null,
      "event_count": 2,
      "input_cost": "381.68",
      "input_tokens": 555300,
      "model_slug": "claude-3-5-sonnet",
      "output_cost": "190.84",
      "output_tokens": 138800,
      "percent_of_total": 30,
      "provider_slug": "unknown",
      "reasoning_cost": null,
      "reasoning_tokens": null,
      "total_cost": "572.52"
    },
    {
      "cache_creation_cost": null,
      "cache_creation_input_tokens": null,
      "cache_read_cost": null,
      "cache_read_input_tokens": null,
      "event_count": 1,
      "input_cost": "254.45",
      "input_tokens": 1183100,
      "model_slug": "gpt-4o-mini",
      "output_cost": "127.23",
      "output_tokens": 295800,
      "percent_of_total": 20,
      "provider_slug": "unknown",
      "reasoning_cost": null,
      "reasoning_tokens": null,
      "total_cost": "381.68"
    },
    {
      "cache_creation_cost": null,
      "cache_creation_input_tokens": null,
      "cache_read_cost": null,
      "cache_read_input_tokens": null,
      "event_count": 1,
      "input_cost": "127.23",
      "input_tokens": 883100,
      "model_slug": "gemini-2.0-flash",
      "output_cost": "63.61",
      "output_tokens": 220800,
      "percent_of_total": 10,
      "provider_slug": "unknown",
      "reasoning_cost": null,
      "reasoning_tokens": null,
      "total_cost": "190.84"
    }
  ],
  "total_cost": "1908.4"
}

Error codes

Errors return the standard error envelope with a code, message, and a correlationId you can quote to support.

Status	When it happens
`400`	Invalid request data. Check that required query parameters are present and that start_date and end_date are valid ISO 8601 dates.
`401`	Missing or invalid API key. Send your key as Authorization: Bearer YOUR_API_KEY.
`403`	API key lacks the costs:read scope. Create or update a key with the costs:read scope, then retry.
`404`	End user not found. The identifier must match the user_id value sent on at least one ingested usage event.
`429`	Rate limit exceeded. Retry after the time indicated by the Retry-After header (rate-limit state is also reported in the standard RateLimit-* headers, e.g. RateLimit-Reset).

Rate limits and retries

Rate limit exceeded. Retry after the time indicated by the Retry-After header (rate-limit state is also reported in the standard RateLimit-* headers, e.g. RateLimit-Reset).