> ## Documentation Index > Fetch the complete documentation index at: https://docs.getsales.io/llms.txt > Use this file to discover all available pages before exploring further. # Provider calls metrics > Period-bound spend, latency and reliability over the calls: credits_charged_sum (what did we spend on AI and enrichment this month), total_tokens_sum, avg_duration_ms, error_rate and cache_hit_rate. period {from, to} is required and capped at 90 days; filter is the search filter; group_by splits by operation, provider, model (the LLM spend axis), status, error_code, source_service, cache_hit or created_date (spend by day). Run budgets and receipts are playtables' credit ledger, not this meter. Contract: - MCP tool `get_provider_calls_metrics`, registry package `mcp.integrations/provider_calls`, mount `integrations.providers`. - Operation `metrics`, response envelope `metrics`. - Flags: read only. ## OpenAPI ````yaml /api-reference/integrations/openapi.yaml post /api/provider-calls/metrics openapi: 3.0.3 info: title: 'GetSales public contract: gs.service.integrations' description: >- The integrations service: the integration platform (the team's credentials for its own APIs and its CRM grants, the HTTP tools it defines over them, the execution log and the priced catalog of every outbound provider call) and the event plane (the platform-wide webhook subscriptions and the delivery state of each event). GENERATED. This document is projected from the Zod MCP tool registry in `product/mcp/gs.mcp` (one tool per public endpoint, 1:1). Do not edit it by hand; edit the tool definition and regenerate with `pnpm openapi:public`. Surface: the public `/api` contract of `gs.service.integrations`, 26 operations. This is the only OpenAPI document the platform publishes. Internal (`/internal`) and health endpoints are deliberately absent: they are not part of any contract, they can change without notice, and the service source is their only description. Conventions: - Auth is a bearer JWT, optionally narrowed by the `Team-SID` header. - Every success body is an MCP envelope: `success: true` plus one typed `operation` shape (`search`, `get`, `create`, `update`, `delete`, `metrics`, `group_by`, `action`), and a `meta` block with `trace_id` for support. - Every failure is the same `McpError` envelope with a code from a fixed 16-code taxonomy, so a client maps errors once. - Lists page with `page_size` (0 to 500, default 50) plus an opaque forward `cursor`; `page_size: 0` returns counts only. - On `GET` and `DELETE`, object-valued query parameters (`filter`, `sort`) travel as JSON text and array-valued ones repeat as `name[]=value`. - The MCP-only `_meta` field (usage analytics) never reaches the backend and is not part of this contract. version: '1.0' contact: name: GetSales url: https://getsales.io email: support@getsales.io license: name: Proprietary url: https://getsales.io/terms servers: - url: https://beta.getsales.io/integrations/v1 description: >- Production (the gateway path on the beta ring; the origin is provisioned per DEPLOY_MAP.md) security: - BearerJwt: [] TeamSid: [] tags: - name: custom_tools description: >- Registry package `mcp.integrations/custom_tools`, served on MCP mount `integrations.providers`. - name: provider_calls description: >- Registry package `mcp.integrations/provider_calls`, served on MCP mount `integrations.providers`. - name: provider_connections description: >- Registry package `mcp.integrations/provider_connections`, served on MCP mount `integrations.providers`. - name: webhook_logs description: >- Registry package `mcp.integrations/webhook_logs`, served on MCP mount `integrations.webhooks`. - name: webhooks description: >- Registry package `mcp.integrations/webhooks`, served on MCP mount `integrations.webhooks`. paths: /api/provider-calls/metrics: post: tags: - provider_calls summary: Provider calls metrics description: >- Period-bound spend, latency and reliability over the calls: credits_charged_sum (what did we spend on AI and enrichment this month), total_tokens_sum, avg_duration_ms, error_rate and cache_hit_rate. period {from, to} is required and capped at 90 days; filter is the search filter; group_by splits by operation, provider, model (the LLM spend axis), status, error_code, source_service, cache_hit or created_date (spend by day). Run budgets and receipts are playtables' credit ledger, not this meter. Contract: - MCP tool `get_provider_calls_metrics`, registry package `mcp.integrations/provider_calls`, mount `integrations.providers`. - Operation `metrics`, response envelope `metrics`. - Flags: read only. operationId: get_provider_calls_metrics requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GetProviderCallsMetricsRequest' responses: '200': description: '`metrics` success envelope.' content: application/json: schema: $ref: '#/components/schemas/GetProviderCallsMetricsResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: GetProviderCallsMetricsRequest: type: object description: Request body of `get_provider_calls_metrics`. properties: filter: type: object properties: sid: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: Call sid(s). operation: type: object properties: eq: type: string enum: - llm.generate - llm.embed - email.find - email.verify - http.request - crm.contact_upsert - crm.company_upsert - crm.associate - crm.properties_list - serp.search - audio.transcribe in: type: array items: type: string enum: - llm.generate - llm.embed - email.find - email.verify - http.request - crm.contact_upsert - crm.company_upsert - crm.associate - crm.properties_list - serp.search - audio.transcribe additionalProperties: false description: llm.generate, email.find, http.request, crm.*... provider: type: object properties: eq: type: string enum: - openai - anthropic - google - deepseek - xai - voyage - cohere - hunter - findymail - anymailfinder - emaillistverify - custom - hubspot - serper in: type: array items: type: string enum: - openai - anthropic - google - deepseek - xai - voyage - cohere - hunter - findymail - anymailfinder - emaillistverify - custom - hubspot - serper additionalProperties: false description: The adapter. model: type: object properties: eq: type: string in: type: array items: type: string is_null: type: boolean additionalProperties: false description: The model of llm and audio calls. provider_connection_sid: type: object properties: eq: type: string in: type: array items: type: string is_null: type: boolean additionalProperties: false description: >- Calls through one connection (is this key working); is_null true = platform-key calls. custom_tool_sid: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: One custom tool's calls. source_service: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: playtables | unibox | agents | api | app. tool_type: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: >- playtable_field, workflow_task, agent_run, custom_tool, dictation. tool_sid: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: 'One cell''s or one run''s attempts (with object_sid: one cell).' object_sid: type: object properties: eq: type: string in: type: array items: type: string additionalProperties: false description: What was called about one person or company. status: type: object properties: eq: type: string enum: - pending - in_progress - success - failed - retrying - cancelled ne: type: string enum: - pending - in_progress - success - failed - retrying - cancelled in: type: array items: type: string enum: - pending - in_progress - success - failed - retrying - cancelled additionalProperties: false description: success | failed | pending. error_code: type: object properties: eq: type: string enum: - auth_error - rate_limited - timeout - network_error - invalid_input - provider_error - not_found in: type: array items: type: string enum: - auth_error - rate_limited - timeout - network_error - invalid_input - provider_error - not_found is_null: type: boolean additionalProperties: false description: auth_error is the evidence behind a failed connection. cache_hit: type: object properties: eq: type: boolean additionalProperties: false description: true = served from the cache. idempotency_key: type: object properties: eq: type: string additionalProperties: false description: The call behind one exact charge. credits_charged: type: object properties: eq: type: number gte: type: number lte: type: number gt: type: number lt: type: number additionalProperties: false description: gt 0 = the paid subset. created_at: type: object properties: gte: type: string lte: type: string gt: type: string lt: type: string additionalProperties: false description: ISO 8601 bounds; a lower bound makes the scan bounded. description: >- Scopes the rows the metrics are computed over: the search filter operators. Omit for all rows. period: type: object properties: from: type: string description: ISO 8601 UTC window start (inclusive). to: type: string description: ISO 8601 UTC window end; at most 90 days after from. required: - from - to description: Required metrics window. group_by: type: string nullable: true enum: - operation - provider - model - status - error_code - source_service - cache_hit - created_date description: One split axis; omit for one total. required: - period GetProviderCallsMetricsResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - metrics metrics: type: object properties: filter: type: object additionalProperties: {} period: type: object properties: from: type: string to: type: string required: - from - to aggregated: type: object properties: counts: type: object additionalProperties: {} metrics: type: object properties: credits_charged_sum: type: number description: The spend of the window in credits. total_tokens_sum: type: number nullable: true description: LLM token volume; null when no llm rows are in scope. avg_duration_ms: type: number nullable: true description: Mean over rows with a duration. error_rate: type: number description: failed over total, 0..1. cache_hit_rate: type: number description: cache hits over the rows of cacheable operations, 0..1. required: - credits_charged_sum - total_tokens_sum - avg_duration_ms - error_rate - cache_hit_rate metrics: type: object properties: credits_charged_sum: type: number description: The spend of the window in credits. total_tokens_sum: type: number nullable: true description: LLM token volume; null when no llm rows are in scope. avg_duration_ms: type: number nullable: true description: Mean over rows with a duration. error_rate: type: number description: failed over total, 0..1. cache_hit_rate: type: number description: cache hits over the rows of cacheable operations, 0..1. required: - credits_charged_sum - total_tokens_sum - avg_duration_ms - error_rate - cache_hit_rate applied_filters: type: object additionalProperties: {} meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - operation - metrics - meta McpError: type: object properties: success: type: boolean enum: - false error: type: object properties: code: type: string enum: - validation_failed - nothing_to_update - not_found - relation_not_found - invalid_transition - limit_exceeded - payment_required - duplicate_rejected - conflict - delete_blocked - unauthorized - forbidden - rate_limited - internal_error - service_unavailable - not_implemented message: type: string recoverable: type: boolean suggestion: type: string field_errors: type: object additionalProperties: type: array items: type: object properties: rule: type: string message: type: string required: - rule - message blockers: type: array items: type: object properties: type: type: string description: >- Machine-readable blocker type (active_flow, pending_tasks, …). severity: type: string enum: - hard - soft description: >- hard = external action required; soft = acknowledge is enough. description: type: string entity_sid: type: string nullable: true count: type: integer resolution: type: string description: 'Hard: tool name to call. Soft: code for acknowledge[].' resolution_hint: type: string required: - type - severity - description - entity_sid - resolution - resolution_hint context: type: object additionalProperties: {} required: - code - message - recoverable meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - error responses: McpClientError: description: >- MCP error envelope. `error.code` is one of validation_failed, nothing_to_update, not_found, relation_not_found, invalid_transition, limit_exceeded, payment_required, duplicate_rejected, conflict, delete_blocked, unauthorized, forbidden, rate_limited, not_implemented. content: application/json: schema: $ref: '#/components/schemas/McpError' McpServerError: description: >- MCP error envelope with `error.code` internal_error or service_unavailable. content: application/json: schema: $ref: '#/components/schemas/McpError' securitySchemes: BearerJwt: type: http scheme: bearer bearerFormat: JWT description: >- Access token issued by gs.service.id. Its `access_identity` claim carries `team_sid`, `actor_sid` and `actor_type`, and that team scope is authoritative. TeamSid: type: apiKey in: header name: Team-SID description: >- Team scope for tokens that do not carry one. Ignored when the token already names a team. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.