provider AI observabilityllm_analytics GET /api/llm_analytics/@me/spend/
@utdk/posthog /api/llm_analytics/@me/spend/
llm_analytics_personal_spend_list
Return a structured personal LLM spend analysis for the requesting user. Pass `date_from` / `date_to` (absolute like `2026-04-23` or relative like `-7d`) to bound the window — defaults to the last 30 days, max 90 days. The `product=<ai_product>` query param is required and scopes the tool / model / day / trace breakdowns to a single product; supported values: posthog_code. `by_product` is always returned for cross-product visibility. `by_day` returns a day-ascending spend series for the scoped product. Use `refresh=true` to bypass the 5-minute response cache.
date_from query
Start of the spend window. Accepts absolute dates (`2026-04-23`) or relative strings (`-7d`, `-1m`, etc.) — same parser used elsewhere in PostHog. Defaults to `-30d`. The window between `date_from` and `date_to` cannot exceed 90 days.
string
date_to query
End of the spend window. Accepts the same formats as `date_from`. Defaults to `now` when omitted.
stringnull
limit query
Maximum number of rows to return per breakdown (1-200, defaults to 50). Each breakdown returns up to this many rows ordered by cost descending. Per-breakdown `truncated: true` indicates more rows exist beyond the limit.
integer
product query required
Required `ai_product` key to scope the tool / model / trace breakdowns to a single product. Only the following products are currently supported: posthog_code.
string
refresh query
If true, bypass the result cache and re-run the underlying queries against ClickHouse.
boolean

Try it

Authentication
Configure credentials for PostHog API
llmAnalyticsPersonalSpendList
GET/api/llm_analytics/@me/spend/
Return a structured personal LLM spend analysis for the requesting user. Pass `date_from` / `date_to` (absolute like `2026-04-23` or relative like `-7d`) to bound the window — defaults to the last 30 days, max 90 days. The `product=<ai_product>` query param is required and scopes the tool / model / day / trace breakdowns to a single product; supported values: posthog_code. `by_product` is always returned for cross-product visibility. `by_day` returns a day-ascending spend series for the scoped product. Use `refresh=true` to bypass the 5-minute response cache.

Start of the spend window. Accepts absolute dates (`2026-04-23`) or relative strings (`-7d`, `-1m`, etc.) — same parser used elsewhere in PostHog. Defaults to `-30d`. The window between `date_from` and `date_to` cannot exceed 90 days.

End of the spend window. Accepts the same formats as `date_from`. Defaults to `now` when omitted.

Maximum number of rows to return per breakdown (1-200, defaults to 50). Each breakdown returns up to this many rows ordered by cost descending. Per-breakdown `truncated: true` indicates more rows exist beyond the limit.

required

Required `ai_product` key to scope the tool / model / trace breakdowns to a single product. Only the following products are currently supported: posthog_code.

If true, bypass the result cache and re-run the underlying queries against ClickHouse.

Configure credentials above to enable sending.

Code snippet
Updates live as you fill in the form above.

TypeScript

import posthog from '@utdk/posthog';

await posthog.llmAnalyticsPersonalSpendList({
  "date_from": "-30d",
  "limit": 50,
  "refresh": false
})