> ## Documentation Index > Fetch the complete documentation index at: https://docs.near.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get platform-wide metrics for admin dashboards (Admin only) > Returns aggregated metrics across all organizations including: - Total users and organizations - Total requests and revenue - Top models by usage - Top organizations by spend ## OpenAPI ````yaml /api-reference/openapi.json get /v1/admin/platform/metrics openapi: 3.1.0 info: title: NEAR AI Cloud API description: >- NEAR AI Cloud API for private AI model inference and organization administration. contact: name: NEAR AI Team email: support@near.ai license: name: MIT version: 1.0.0 servers: - url: https://cloud-api.near.ai description: NEAR AI Cloud security: - session_token: [] - api_key: [] tags: - name: Chat description: Chat completion endpoints for AI model inference - name: Images description: Image generation endpoints - name: Audio description: Audio transcription endpoints - name: Rerank description: Document reranking endpoints - name: Score description: Text similarity scoring endpoints - name: Privacy description: Privacy classification (PII span detection) endpoints - name: Models description: Public model catalog and information - name: Responses description: >- Stateless response inference (`store: false` only). Raw request/response content, response items, and history are not persisted. Clients must include any prior context in each request. Every successful Responses inference makes exactly one Chat Completions call. Only custom `function` tools are supported. They are client-managed: Cloud returns `function_call` items but never executes them; a later `store: false` request replays the individual call (the raw item from output is accepted) with its matching `function_call_output`, alongside caller-managed message history and the same function tool definitions. The minimal replay path also accepts assistant `message` text parts of type `output_text`, but not reasoning or arbitrary full `response.output` items. Server-executed tools (`web_search`, `web_context_search`, `file_search`, `code_interpreter`, `computer`, and remote `mcp`) and image-generation/editing models are rejected. The separate `POST /mcp` endpoint continues to expose its `web_search` tool independently of Responses; use `/v1/images/*` for image generation/editing. Existing completed-response gateway attestation is preserved best-effort: when the signature write succeeds, `GET /v1/signature/resp_*` retrieves signatures over SHA-256 request/response digests, never raw content. Interrupted streams create no `resp_*` attestation record or legacy disconnect fallback. Conversations, response history, and file input are rejected. - name: Organizations description: Organization management - name: Organization Members description: Organization member and invitation management - name: Workspaces description: Workspace and API key management - name: Users description: User profile and token management - name: Invitations description: Token-based invitation handling - name: Usage description: Usage tracking and billing information - name: Reporting description: Read-only customer usage reporting - name: Billing description: Billing costs endpoint (HuggingFace integration) - name: Staking Farm description: House of Stake farm credit configuration and synchronization - name: Health description: Health check endpoints - name: Attestation description: Attestation and verification endpoints - name: Gateway description: Model gateway integration endpoints - name: Admin description: Administrative endpoints (admin access required) - name: Services description: Public platform services (e.g. web_search pricing) paths: /v1/admin/platform/metrics: get: tags: - Admin summary: Get platform-wide metrics for admin dashboards (Admin only) description: |- Returns aggregated metrics across all organizations including: - Total users and organizations - Total requests and revenue - Top models by usage - Top organizations by spend operationId: get_platform_metrics parameters: - name: start in: query description: Start of time range (ISO 8601). Defaults to 30 days ago. required: false schema: type: string - name: end in: query description: End of time range (ISO 8601). Defaults to now. required: false schema: type: string responses: '200': description: Platform metrics retrieved successfully content: application/json: schema: $ref: '#/components/schemas/PlatformMetrics' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - session_token: [] components: schemas: PlatformMetrics: type: object description: Platform-wide metrics for admin dashboard required: - period_start - period_end - generated_at - total_users - total_organizations - total_requests - total_consumed_usd - total_tokens - total_cache_read_tokens - new_users - new_organizations - active_organizations - paying_organizations - verifiable_consumed_usd - verifiable_requests - non_verifiable_consumed_usd - non_verifiable_requests - provider_error_or_timeout_rate - provider_usage - top_models - top_organizations properties: active_organizations: type: integer format: int64 description: Organizations that issued ≥1 request in the period generated_at: type: string format: date-time description: >- When this response was computed. The `total_users`/`total_organizations`/ `paying_organizations` fields are **current snapshots as of this time**, not period-bound like the rest. new_organizations: type: integer format: int64 description: Organizations created in the period new_users: type: integer format: int64 description: Users created in the period non_verifiable_consumed_usd: type: number format: double description: >- Consumed cost on non-verifiable models, USD (NOT necessarily third-party) non_verifiable_requests: type: integer format: int64 p95_ttft_ms: type: - number - 'null' format: double description: 95th percentile time-to-first-token across the platform (ms) paying_organizations: type: integer format: int64 description: >- Snapshot (as of `generated_at`): orgs with an active payment-type credit. NOTE: does not yet count postpaid/invoiced customers (see #704). period_end: type: string format: date-time period_start: type: string format: date-time provider_error_or_timeout_rate: type: number format: double description: >- Share of requests whose stop_reason ∈ {provider_error, timeout}, 0.0–1.0 provider_usage: $ref: '#/components/schemas/PlatformProviderUsage' top_models: type: array items: $ref: '#/components/schemas/TopModelMetrics' top_organizations: type: array items: $ref: '#/components/schemas/TopOrganizationMetrics' total_cache_read_tokens: type: integer format: int64 total_consumed_usd: type: number format: double description: >- Total **consumed usage cost** in USD over the period (inference only). NOT recognized revenue: grant/payment funding is not separable without per-request attribution (tracked in #704). total_organizations: type: integer format: int64 description: Snapshot (as of `generated_at`). total_requests: type: integer format: int64 total_tokens: type: integer format: int64 total_users: type: integer format: int64 description: Snapshot (as of `generated_at`). verifiable_consumed_usd: type: number format: double description: Consumed cost on verifiable (TEE-attested) models, USD verifiable_requests: type: integer format: int64 ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' PlatformProviderUsage: type: object required: - fallback - non_fallback - by_provider_type - by_provider_tier properties: by_provider_tier: type: array items: $ref: '#/components/schemas/ProviderTierUsage' by_provider_type: type: array items: $ref: '#/components/schemas/ProviderTypeUsage' fallback: $ref: '#/components/schemas/ProviderUsageTotals' non_fallback: $ref: '#/components/schemas/ProviderUsageTotals' TopModelMetrics: type: object description: Top model by request count required: - model_name - requests - revenue_usd properties: model_name: type: string requests: type: integer format: int64 revenue_usd: type: number format: double TopOrganizationMetrics: type: object description: Top organization by spend required: - organization_id - organization_name - requests - spend_usd properties: organization_id: type: string format: uuid organization_name: type: string requests: type: integer format: int64 spend_usd: type: number format: double ErrorDetail: type: object required: - message - type properties: code: type: - string - 'null' message: type: string param: type: - string - 'null' type: type: string ProviderTierUsage: type: object required: - requests - input_tokens - output_tokens - total_tokens - cache_read_tokens - consumed_cost_usd properties: cache_read_tokens: type: integer format: int64 consumed_cost_usd: type: number format: double input_tokens: type: integer format: int64 output_tokens: type: integer format: int64 provider_tier: type: - string - 'null' requests: type: integer format: int64 total_tokens: type: integer format: int64 ProviderTypeUsage: type: object required: - requests - input_tokens - output_tokens - total_tokens - cache_read_tokens - consumed_cost_usd properties: cache_read_tokens: type: integer format: int64 consumed_cost_usd: type: number format: double input_tokens: type: integer format: int64 output_tokens: type: integer format: int64 provider_type: type: - string - 'null' requests: type: integer format: int64 total_tokens: type: integer format: int64 ProviderUsageTotals: type: object required: - requests - input_tokens - output_tokens - total_tokens - cache_read_tokens - consumed_cost_usd properties: cache_read_tokens: type: integer format: int64 consumed_cost_usd: type: number format: double input_tokens: type: integer format: int64 output_tokens: type: integer format: int64 requests: type: integer format: int64 total_tokens: type: integer format: int64 securitySchemes: session_token: type: http scheme: bearer bearerFormat: JWT description: >- JWT access token for user authentication (Authorization: Bearer ). Create via POST /users/me/access_tokens. api_key: type: http scheme: bearer bearerFormat: api_key description: 'API key for programmatic access (Authorization: Bearer sk-)' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.