Get your usage
Returns what your org used in each period from start until end,
a UTC day unless granularity says otherwise, by meter and location,
and by inference model and key when groupBy names them, from the
hours closed so far. Compute counts
while an instance's status is running: vCPUs and memory for a CPU
size, GPUs for a spot GPU size, and nothing for a size whose
reservation is paid for. Disks count from the instance's first
running until it fails or its delete is asked for, so a create
that never runs costs nothing, a dedicated IPv4 address
while it is held, and egress as the bytes the instance sends. An
hour closes 15 minutes after it ends and never changes after, so the
totals are final up to closedThrough. Inference counts each
request's tokens in the hour it finished: uncached input, cached
input and output, each a meter of its own. A period, meter and
location with no use is left out. Any valid credential can read it.
AuthorizationBearer <cc_...>An API key of your org, sent as Authorization: Bearer cc_.... Keys
start with cc_ and are otherwise opaque. Treat a key as a password:
anyone holding it can act with its scopes until it expires or is
revoked. Each operation's security requirement lists the scopes it
needs; an empty list means any valid key. The MCP server at /mcp
accepts agent keys and no other kind.
start?stringThe first UTC day to return. Without it, the first day of the current month.
dateend?stringThe UTC day after the last to return, at most 93 days after
start. Without it, tomorrow.
dategranularity?stringHow long each item's period is: a UTC day, the default, an
hour, or a UTC month cut to start and end. By the hour, end
is at most 31 days after start. Open set: another value is refused
with a 400 that lists the values this version takes.
"day"groupBy?array<string>What to sum by besides the period, meter and location: model, the
inference model a request named, and inferenceKey, the inference
key it was made with. Use that is not inference has neither, and
comes without them. Open set: another value is refused with a 400
that lists the values this version takes.
items <= 2meter?array<>Only these meters.
items <= 16location?array<>Only these locations.
items <= 16model?array<>Only inference with these models, by the id a request names.
items <= 16inferenceKey?array<>Only inference with these inference keys.
items <= 16pageSize?integerThe most items to return.
1 <= value <= 1000010000pageToken?stringThe nextPageToken of the previous page, unchanged. Send the same
filters with it.
1 <= length <= 2048Api-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 <= 500What your org used in each period, by meter and location.
application/json- response
What your org used in each period from start until end.
start*stringThe first UTC day.
dateend*stringThe UTC day after the last.
dateclosedThrough?stringThe end of the last closed hour: the totals up to it are final, and use after it is not counted yet. Absent before any hour is closed.
date-timeitems*array<>Each period's use of each meter in each location, and of each
model and key that groupBy names, by period, then meter,
location, model and key.
nextPageToken?NextPageTokenPass it back as pageToken for the next page. Absent on the last page.
curl -X GET 'https://api.cloud.confidential.ai/v1/usage?start=2026-10-01&end=2026-11-01&granularity=day&groupBy=model&meter=output_tokens&location=us-west-1&model=example%2Fmodel-70b&inferenceKey=ik-7k2m9q4x1bfa&pageSize=10000&pageToken=eyJjIjoiMjAyNi0xMC0yMlQxNzowMjoxMVoiLCJpIjoiaS03azJtOXE0eDFiZmEifQ' \ -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'{ "start": "2026-10-26", "end": "2026-10-28", "closedThrough": "2026-10-27T23:00:00Z", "items": [ { "date": "2026-10-26", "periodStart": "2026-10-26T00:00:00Z", "periodEnd": "2026-10-27T00:00:00Z", "meter": "vcpu_hours", "location": "us-west-1", "quantity": 12.5, "unit": "vCPU-hours" }, { "date": "2026-10-26", "periodStart": "2026-10-26T00:00:00Z", "periodEnd": "2026-10-27T00:00:00Z", "meter": "memory_gib_hours", "location": "us-west-1", "quantity": 50, "unit": "GiB-hours" }, { "date": "2026-10-26", "periodStart": "2026-10-26T00:00:00Z", "periodEnd": "2026-10-27T00:00:00Z", "meter": "storage_gib_hours", "location": "us-west-1", "quantity": 68.75, "unit": "GiB-hours" }, { "date": "2026-10-26", "periodStart": "2026-10-26T00:00:00Z", "periodEnd": "2026-10-27T00:00:00Z", "meter": "dedicated_ipv4_hours", "location": "us-west-1", "quantity": 6.25, "unit": "address-hours" }, { "date": "2026-10-26", "periodStart": "2026-10-26T00:00:00Z", "periodEnd": "2026-10-27T00:00:00Z", "meter": "egress_gb", "location": "us-west-1", "quantity": 1.204, "unit": "GB" }, { "date": "2026-10-27", "periodStart": "2026-10-27T00:00:00Z", "periodEnd": "2026-10-28T00:00:00Z", "meter": "vcpu_hours", "location": "us-west-1", "quantity": 46, "unit": "vCPU-hours" } ]}Get your limits GET
Returns the org's quotas, with what is in use against each, and the caller's explicitly configured limits, which only an agent credential has in this version. An org's quotas cap its live on-demand instances and their vCPUs, stopped ones included, and not GPU instances, which are reserved or spot, and its instances with a dedicated IPv4, GPU instances included; one with no quota, such as the platform's own, has `inUse` and no `limit`. Creates still need available host resources. `org.clusters` is present only for an org with managed Kubernetes. It also says whether the caller counts as an agent, whose GPU reservations wait for an owner's approval. Any valid credential can read it. Plan a create from it, rather than retrying one that returned `403 quota_exceeded`.
List your usage by instance GET
Returns what each of your org's instances used from `start` until `end`, one line per instance, meter and UTC month, or hour with `granularity=hour`: the lines your usage, and your bill, add up to. Lines come oldest first, then by instance and meter. Each counts as `GET /v1/usage` describes, and is final up to `closedThrough`. Hours closed before `linesFrom` have no lines; `GET /v1/usage` has their totals.