Assign team to business unit Assigns an existing team to the business unit. Returns 409 if the team is already assigned to a different business unit.

Create business unit Creates a new business unit. Names must be unique.

Create business unit governance Configures budget and/or rate limit governance for a business unit. At least one of budget or rate_limit is required. Returns 409 if the business unit already has governance configured (use PUT to update).

Create customer Creates a new customer.

Create team Creates a new team.

Create model config Creates a new model configuration with budget and rate limit settings.

Create pricing override Creates a new pricing override. The most specific matching scope always wins during cost resolution.

Create routing rule Creates a new CEL-based routing rule for intelligent request routing. Provider and model can be left empty to use the incoming request values.

Create virtual key Creates a new virtual key with the specified configuration.

Delete business unit Deletes a business unit. Any teams assigned to it are atomically unassigned as part of the deletion.

Delete business unit governance Removes all budget and rate limit governance from a business unit.

Delete customer Deletes a customer.

Delete team Deletes a team.

Delete model config Deletes a model configuration.

Delete pricing override Deletes a pricing override by ID.

Delete provider governance Removes governance settings (budget and rate limits) for a specific provider.

Delete routing rule Deletes a routing rule.

Delete virtual key Deletes a virtual key.

Get business unit Returns a specific business unit by ID, including governance and team count.

Get complexity analyzer config Returns the full complexity analyzer runtime config, including tier thresholds and editable keyword lists. Returns built-in defaults if none have been configured.

Get customer Returns a specific customer by ID.

Get team Returns a specific team by ID.

Get model config Returns a specific model configuration by ID.

Get routing rule Returns a specific routing rule by ID.

Get virtual key Returns a specific virtual key by ID.

Get virtual key quota Returns the overall budget and rate limit quota for the authenticated virtual key, as well as per-provider and per-model budgets and rate limits (with current usage). Each budget also carries the actual per-model usage for its current cycle. This is a self-service endpoint - no admin authentication required. The virtual key value itself (provided via header) is the credential.

List budgets Returns a list of all budgets. Use the from_memory query parameter to get data from in-memory cache.

List business unit teams Returns a paginated list of teams assigned to the business unit.

List business units Returns a paginated list of business units, each with its team count.

List customers Returns a list of all customers.

List teams Returns a list of all teams.

List model limits Returns a paginated list of model limits with their budget and rate limit settings.

List pricing overrides Returns all pricing overrides, optionally filtered by scope.

List provider governance Returns a list of all providers with their governance settings (budget and rate limits).

List rate limits Returns a list of all rate limits. Use the from_memory query parameter to get data from in-memory cache.

List routing rules Returns a list of all routing rules configured for intelligent request routing across providers.

List virtual keys Returns a list of all virtual keys with their configurations.

Remove team from business unit Unassigns a team from the business unit.

Reset complexity analyzer config Restores the built-in complexity analyzer runtime config defaults and hot-reloads the governance plugin.

Update business unit governance Updates budget and/or rate limit governance for a business unit. Passing an empty budget or rate_limit object removes that governance component.

Update complexity analyzer config Replaces the full complexity analyzer runtime config and hot-reloads the governance plugin. Tier thresholds must satisfy 0 < simple_medium < medium_complex < complex_reasoning < 1.

Update customer Updates an existing customer.

Update team Updates an existing team.

Update model config Updates an existing model configuration's budget and rate limit settings.

Update pricing override Updates an existing pricing override. Omitted fields are merged from the existing record. The patch field is always replaced in full when provided.

Update provider governance Updates governance settings (budget and rate limits) for a specific provider.

Update routing rule Updates an existing routing rule's configuration.

Update virtual key Updates an existing virtual key's configuration.