7. Knowing what it cost

Every non-streaming inference response — chat, responses, embeddings, rerank, classify, speech, transcription, images (generations and edits), moderation and the Anthropic drop-in — carries:

Why micro-cents and not dollars: a typical call costs a few thousand micro-cents — well under one cent. Any float-of-dollars encoding reports that as 0.00. Integer micro-cents is lossless and reconciles exactly against GET /v1/billing/costs.

0 is a real answer, not a missing one: a dedicated pod prices tokens at zero on purpose, because you are paying per GPU-hour instead.

Each ledger row from GET /v1/billing/costs carries cost_micro_cents, request_id and the token counts, so a call's header reconciles to its row by request_id to the unit. cost_cents on the same row is the whole-cent rounding and reads 0 for most single calls.

GET /v1/billing/costs is not paginated today: it returns your whole ledger and ignores limit. Fetch it once and index in memory; use GET /v1/usage for totals. The gateway mints the request_id it stamps on the row — reconcile by the X-Request-Id response header, never by an id you sent.

The gateway stamps, the client reads, and nothing re-derives a price.

Streaming has no cost header and cannot. The cost is known only when the terminal usage frame arrives, long after headers flush. HTTP trailers exist for this but the OpenAI and Anthropic SDKs cannot read them, so promising cost there would promise something most clients cannot collect. Streamed callers reconcile through X-Request-Id.