> ## Documentation Index > Fetch the complete documentation index at: https://docs.opper.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get usage and cost > Calls, tokens and cost for the calling organization over a window of at most 31 days, or for one of its projects with `project_uuid`, optionally grouped by API key, model, provider or project and split into hourly or daily UTC buckets. The figures are the ones the platform's usage pages show. `count`, the token sums and `cost` cover model calls; `evals_cost` and `guards_cost` are what evaluations and guard or routing checks cost, and `total_cost` is all three. Grouped by `api_key_id`, each row carries the key's id and, while the key exists, its name; calls made without a key have neither. Grouped by `project`, each row carries the project's UUID and name. Grouped totals are ranked by `total_cost`, most first. Web search surcharges are not included. Requires the `usage:read` scope. ## OpenAPI ````yaml get /management/v1/usage openapi: 3.1.0 info: description: Schema-driven generative API that orchestrates LLM-powered workflows. title: Task API version: 3.0.0 servers: - description: Production url: https://api.opper.ai - description: Local development url: http://localhost:8080 security: - BearerAuth: [] tags: - description: Schema-driven function management and execution name: Functions - description: OpenAI-compatible chat completions name: Chat - description: OpenAI Responses API compatible endpoint name: Responses - description: Google-compatible interactions endpoint name: Interactions - description: Model registry and capabilities name: Models - description: Synchronous image generation name: Images - description: Text-to-speech and speech-to-text name: Audio - description: Asynchronous video generation name: Videos - description: Reusable file storage for media inputs and generated outputs name: Files - description: Async generation status and downloads name: Artifacts - description: OpenAI-compatible embeddings name: Embeddings - description: Recorded HTTP request/response generations name: Generations - description: System health and status name: System - description: Roundtable endpoint — fan out a query to multiple LLMs and combine results name: Roundtable - description: Web search, fetch, and other utility tools name: Tools - description: Caller identity, credits, and usage name: Account - description: >- Programmatic project and API-key management. Authenticates with an `op-mak-…` management token; available on the control_plane and enterprise plans. name: Management paths: /management/v1/usage: get: tags: - Management summary: Get usage and cost description: >- Calls, tokens and cost for the calling organization over a window of at most 31 days, or for one of its projects with `project_uuid`, optionally grouped by API key, model, provider or project and split into hourly or daily UTC buckets. The figures are the ones the platform's usage pages show. `count`, the token sums and `cost` cover model calls; `evals_cost` and `guards_cost` are what evaluations and guard or routing checks cost, and `total_cost` is all three. Grouped by `api_key_id`, each row carries the key's id and, while the key exists, its name; calls made without a key have neither. Grouped by `project`, each row carries the project's UUID and name. Grouped totals are ranked by `total_cost`, most first. Web search surcharges are not included. Requires the `usage:read` scope. operationId: getManagementUsage parameters: - description: >- Inclusive RFC 3339 start. Defaults to seven days before `to`. At most 31 days before `to`. in: query name: from schema: format: date-time type: string - description: Exclusive RFC 3339 end. Defaults to now. in: query name: to schema: format: date-time type: string - description: '`none` (default), `api_key_id`, `model`, `provider` or `project`.' in: query name: group_by schema: default: none enum: - none - api_key_id - model - provider - project type: string - description: >- `none` (default) for totals over the window, `hour` or `day` for a UTC series. in: query name: bucket schema: default: none enum: - none - hour - day type: string - description: >- Read one of the organization's projects instead of the whole organization. in: query name: project_uuid schema: format: uuid type: string responses: '200': content: application/json: schema: properties: data: items: properties: api_key_id: type: integer api_key_name: type: string bucket: description: >- Start of the UTC hour or day; absent when bucket=none. format: date-time type: string cache_creation_tokens: type: integer cache_read_tokens: type: integer cache_savings: type: number completion_tokens: type: integer cost: description: USD, model calls. type: number count: description: Model calls. type: integer duration_ms_sum: type: integer errors_other: type: integer errors_policy: type: integer errors_provider: type: integer errors_rate_limited: type: integer evals_cost: description: USD, evaluations. type: number group: description: >- The group's key: the API key id, model, provider or project UUID. Absent for calls with no value for the grouping. type: string guards_cost: description: USD, guard and routing checks. type: number last_called_at: description: Grouped by project only. format: date-time type: string project_name: type: string project_uuid: format: uuid type: string prompt_tokens: type: integer total_cost: description: USD, cost + evals_cost + guards_cost. type: number total_tokens: type: integer type: object type: array meta: properties: bucket: type: string currency: example: USD type: string from: format: date-time type: string group_by: type: string project_uuid: description: The project read, when `project_uuid` was given. format: uuid type: string to: format: date-time type: string total_count: type: integer type: object type: object description: Successful response '400': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Bad request '401': description: Unauthorized - missing or invalid API key '403': content: application/json: schema: properties: error: type: string required_scope: description: Present on the scope refusal. type: string type: object description: >- The token lacks the scope this endpoint requires (`required_scope` is returned). Presenting a runtime `op-…` key instead of a management `op-mak-…` token also lands here. '404': content: application/json: schema: properties: error: type: string type: object description: '`project_uuid` names no project of the calling organization.' '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Internal server error security: - ManagementBearer: [] components: schemas: ErrorResponse: properties: error: properties: code: type: string details: description: Any value message: type: string required: - code - message type: object meta: type: object required: - error type: object securitySchemes: BearerAuth: bearerFormat: API Key description: API key authentication. Pass your API key as a Bearer token. scheme: bearer type: http ManagementBearer: bearerFormat: Management API Key description: >- Management API authentication. Pass an `op-mak-…` management token as a Bearer token. Runtime `op-…` API keys are rejected with 403 — they belong on the data-plane endpoints. Mint a management key from the platform UI under Settings → API keys. scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.