latestOpenAPI 3.1.02026-08-226994571.1 MB

1e929292ddd5

budget management

New Budget

Create a new budget object. Can apply this to teams, orgs, end-users, keys.

Parameters:

  • budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
  • budget_id: Optional[str] - The id of the budget. If not provided, a new id will be generated.
  • max_budget: Optional[float] - The max budget for the budget.
  • soft_budget: Optional[float] - The soft budget for the budget.
  • max_parallel_requests: Optional[int] - The max number of parallel requests for the budget.
  • tpm_limit: Optional[int] - The tokens per minute limit for the budget.
  • rpm_limit: Optional[int] - The requests per minute limit for the budget.
  • model_max_budget: Optional[dict] - Specify max budget for a given model. Example: {"openai/gpt-4o-mini": {"max_budget": 100.0, "budget_duration": "1d", "tpm_limit": 100000, "rpm_limit": 100000}}
  • budget_reset_at: Optional[datetime] - Datetime when the initial budget is reset. Default is now.
post/budget/new

Request body

budget_idstring nullable

The unique budget id.

max_budgetnumber nullable

Requests will fail if this budget (in USD) is exceeded.

soft_budgetnumber nullable

Requests will NOT fail if this is exceeded. Will fire alerting though.

max_parallel_requestsinteger nullable

Max concurrent requests allowed for this budget id.

tpm_limitinteger nullable

Max tokens per minute, allowed for this budget id.

rpm_limitinteger nullable

Max requests per minute, allowed for this budget id.

budget_durationstring nullable

Max duration budget should be set for (e.g. '1hr', '1d', '28d')

model_max_budgetobject nullable

Max budget for each model (e.g. {'gpt-4o': {'max_budget': '0.0000001', 'budget_duration': '1d', 'tpm_limit': 1000, 'rpm_limit': 1000}})

budget_reset_atstring date-time nullable

Datetime when the budget is reset

Response

Successful Response

{"stackTrail":"paths:/budget/new:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}