Buy inference credits
Charges your org's saved card for amount of inference credits,
$5.00 to $999,999.99, on an invoice of its own, and returns the
purchase. It is paid, and its amount is in the balance, once
Stripe confirms the charge, usually before this call returns; it
is failed, with failure saying why, if the card is declined,
and nothing is charged. One still pending settles within a
minute. An org without a payment method answers
402 payment_required. One with a purchase still pending, or whose
inference is invoiced or not billed, answers 409 invalid_state.
A retry with the same Idempotency-Key
returns the same purchase. Only owners signed in to the console
can call it.
oauth2 org:writeAuthorizationBearer <token>A person's access token, sent as Authorization: Bearer <token>,
from the authorization code flow with PKCE (S256). A CLI on a
machine without a browser can use the device flow (RFC 8628) at
https://auth.confidential.ai/oauth2/device_authorization
instead. Ask for the resource https://api.cloud.confidential.ai
(RFC 8707): a token issued for any other resource, the MCP server's
included, is refused. A token acts for one person in one org, with
the scopes of the person's role there whatever the client asks for,
so ask the authorization server for none of the scopes below; they
are listed so that each operation can name the ones it needs.
Access tokens last minutes, and a refresh token is replaced at every
use.
Scope: org:write
Idempotency-Key*stringA unique key for this intent, such as a UUID. Reuse it for every
retry of the same request. A missing key returns
400 idempotency_key_required. See Idempotency above.
^[!-~]+$1 <= length <= 255Api-Version*stringThe API version the request is written against. This document
describes 2026-10-15. A missing header returns
400 api_version_required, and a version the API does not serve
returns 400 unsupported_api_version.
X-Correlation-ID?stringAn id of your own for this request, or for a group of requests, to
find them in our logs and yours. Logged with the request and returned
unchanged in X-Correlation-ID. The request id itself is always the
API's own, in X-Request-ID.
^[A-Za-z0-9._:-]+$1 <= length <= 128Org-Context?stringAdmin keys only: the id of the org to act in. Required with an admin
key, together with Access-Reason; with any other credential it
returns 400 invalid_request. Every request that carries it is
recorded in that org's operator-access log.
^org-[a-z0-9]([-a-z0-9]*[a-z0-9])?$5 <= length <= 63Access-Reason?stringAdmin keys only: why the operator is acting in the org, such as a
support ticket. Required with Org-Context. Recorded, verbatim, in
the org's operator-access log.
^[^\x00-\x1F\x7F]+$10 <= length <= 500application/json- body
amount*DollarAmountWhat to buy, $5.00 to $999,999.99.
^[0-9]{1,6}(\.[0-9]{2})?$The purchase.
application/json- response
A purchase of inference credits, charged to the saved card.
id*stringcurrency*stringamount*stringstatus*stringpending while Stripe charges the card, then paid, in the balance, or failed, charging nothing. Open set; accept values not listed.
failure?stringWhy a failed purchase was not charged.
automatic*booleanWhether auto-reload bought it.
createdBy?stringThe owner who bought it. Absent for a reload.
createdAt*stringdate-timesettledAt?stringdate-timecurl -X POST 'https://api.cloud.confidential.ai/v1/billing/inference-credits/purchases' \ -H 'Idempotency-Key: 0b9d6c1e-5f8a-4c2e-9a51-2f7e0c3d4b18' \ -H 'Api-Version: 2026-10-15' \ -H 'X-Correlation-ID: rollout-2026-10-22' \ -H 'Access-Reason: Support ticket 4821: customer asked why i-6d3f9h2k8mzr failed' \ -H 'Content-Type: application/json' \ -d '{ "amount": "25.00"}'{ "id": "icp-2n7c4v9z1hdq", "currency": "USD", "amount": "25.00", "status": "paid", "automatic": false, "createdBy": "user_alice", "createdAt": "2026-11-16T09:00:00Z", "settledAt": "2026-11-16T09:00:02Z"}List credit purchases GET
Lists your org's purchases of inference credits, newest first, bought by an owner or by auto-reload. Only people signed in to the console can read it.
Find GPU reservation offerings GET
Returns up to six priced offerings for whole GPUs of one model, for a term of at least seven days, starting as near to `start` as capacity allows. Each offering's price holds until its `expiresAt`. An empty list means nothing fits.