Holds the estimated spend of a billable effect against every enforcing budget that scopes the request, and against the named actor's spend limits, under one handle.

POST

/v1/m/finops/admission/reserve

curl --request POST \
  --url https://example.com/v1/m/finops/admission/reserve \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "actor_ref": "example", "dims": { "agent_group_refs": [ "example" ], "agent_ref": "example", "api_key_ref": "example", "context_window": "example", "cost_center_ref": "example", "cost_type": "example", "gateway": "example", "identity_ref": "example", "inference_geo": "example", "model_ref": "example", "project": "example", "provider_ref": "example", "routine_ref": "example", "service_tier": "example", "session_ref": "example", "team": "example", "user_group_refs": [ "example" ], "workspace_ref": "example" }, "estimate_micro_usd": 1, "groups": [ "example" ], "idempotency_key": "example", "scope": "session_launch", "unreachable": "" }'

• this engine

Holds the estimated spend of a billable effect against every enforcing budget that scopes the request, and against the named actor’s spend limits, under one handle.

Authorizations

• bearerAuth
• browserSession

Parameters

Header Parameters

X-Olivares-Tenant

string format: uuid

Target tenant id; required when the principal can act in more than one tenant.

Request Body ^required

Media type application/json

object

actor_ref

When set, the spend limits of that actor are held as well as the budgets.

string

dims

object

agent_group_refs

Array<string>

agent_ref

string

api_key_ref

string

context_window

string

cost_center_ref

string

cost_type

string

gateway

string

identity_ref

string

inference_geo

string

model_ref

string

project

string

provider_ref

string

routine_ref

string

service_tier

string

session_ref

string

team

string

user_group_refs

Array<string>

workspace_ref

string

estimate_micro_usd

The amount to hold. Zero holds nothing and returns no handle, but a cap already past its limit still refuses it.

integer format: int64

groups

Directory group ids used to resolve the actor’s spend limits.

Array<string>

idempotency_key

required

Bound to the tenant, the scope and the payload. A retry with the same key and payload inside the replay window is answered with the hold the first call took; the same key with another payload is refused with 409.

string

>= 1 characters <= 256 characters

scope

required

string

Allowed values: session_launch model_gateway scheduled_job

unreachable

What a request answers when its admission cannot be established. Omitted, empty and unknown values mean deny. Allow admits with no hold.

string

default: deny

Allowed values: "" deny allow

Responses

200

OK

Media type application/json

object

Example ^generated

{}

400

Bad request

Media type application/json

object

Example ^generated

{}

401

Unauthenticated

Media type application/json

object

Example ^generated

{}

403

Forbidden

Media type application/json

object

Example ^generated

{}

404

Not found

Media type application/json

object

Example ^generated

{}

409

Conflict / setup required

Media type application/json

object

Example ^generated

{}

429

Rate limited

Media type application/json

object

Example ^generated

{}