> ## Documentation Index > Fetch the complete documentation index at: https://docs.lumisreach.com/llms.txt > Use this file to discover all available pages before exploring further. # Start a Quick AI Phone Call > Has an AI agent call one or more phone numbers to accomplish a goal. No phone-number purchase is required — the call is placed from a shared LumisReach number on the LumisReach Official account, and that is the number the recipient sees. Configure voice, language, goal, opening line, retry attempts and maximum call length per request. Billing: $0.20 per initiated call (each retry counts) plus $0.20 per minute of conversation, charged to the wallet of the organization that owns the API key. Shared numbers have a daily volume ceiling (75 calls once warmed up) so carriers do not flag them; a job spreads across the pool and each destination reports the `from_number` it used. Returns 202 with a job id; poll `GET /v1/quick/actions/{id}` for per-number progress. Returns 409 when the shared pool has no daily volume left. ## OpenAPI ````yaml /openapi.json post /v1/quick/ai-calls openapi: 3.1.0 info: title: LumisReach v1 API version: 1.0.0 description: >- Programmatic access to the LumisReach voice platform — calls, numbers, caller trust, and brands. contact: name: LumisReach email: founders@lumisreach.com servers: - url: https://api.lumisreach.com/api security: - bearerAuth: [] tags: - name: Phone Numbers - name: Caller IDs - name: Enterprise Registration - name: Branded Calling - name: Calls - name: SMS - name: WebRTC - name: Reputation - name: Usage - name: Account - name: Documents - name: Quick Agent Actions - name: Sub-entities paths: /v1/quick/ai-calls: post: tags: - Quick Agent Actions summary: Start a Quick AI Phone Call description: >- Has an AI agent call one or more phone numbers to accomplish a goal. No phone-number purchase is required — the call is placed from a shared LumisReach number on the LumisReach Official account, and that is the number the recipient sees. Configure voice, language, goal, opening line, retry attempts and maximum call length per request. Billing: $0.20 per initiated call (each retry counts) plus $0.20 per minute of conversation, charged to the wallet of the organization that owns the API key. Shared numbers have a daily volume ceiling (75 calls once warmed up) so carriers do not flag them; a job spreads across the pool and each destination reports the `from_number` it used. Returns 202 with a job id; poll `GET /v1/quick/actions/{id}` for per-number progress. Returns 409 when the shared pool has no daily volume left. operationId: v1_quick_ai_calls_post parameters: - name: Idempotency-Key in: header required: false description: >- UUID — when present, deduplicates repeat submissions. See /api-reference/idempotency. schema: type: string requestBody: required: true content: application/json: schema: $schema: http://json-schema.org/draft-07/schema# type: object properties: to_numbers: minItems: 1 maxItems: 20 type: array items: type: string pattern: ^\+[1-9]\d{1,14}$ description: Destination in E.164 format description: One or more destinations in E.164 format goal: type: string minLength: 10 maxLength: 2000 description: >- What the AI should accomplish on the call. Drives the system prompt. instructions: type: string maxLength: 4000 opening_message: type: string maxLength: 500 voice: type: string maxLength: 120 voice_model_tier: type: string enum: - standard - mini language: default: en type: string maxLength: 10 retry_attempts: default: 1 type: integer minimum: 0 maximum: 5 retry_delay_minutes: default: 10 type: integer minimum: 1 maximum: 1440 max_call_duration_seconds: default: 600 type: integer minimum: 30 maximum: 1800 voicemail_enabled: default: true type: boolean voicemail_message: type: string maxLength: 600 record: default: true type: boolean contact_name: type: string maxLength: 120 required: - to_numbers - goal - language - retry_attempts - retry_delay_minutes - max_call_duration_seconds - voicemail_enabled - record additionalProperties: false responses: '200': description: Success content: application/json: schema: $schema: http://json-schema.org/draft-07/schema# type: object properties: data: type: object properties: id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ kind: type: string const: ai_call status: type: string from_number: type: string target_count: type: number status_url: type: string pricing: type: object properties: start_fee_usd: type: number per_minute_usd: type: number note: type: string required: - start_fee_usd - per_minute_usd - note additionalProperties: false required: - id - kind - status - from_number - target_count - status_url - pricing additionalProperties: false required: - data additionalProperties: false '400': description: Validation error content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '409': description: Conflict (incl. idempotency conflicts) content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' components: schemas: ErrorEnvelope: type: object properties: error: type: object required: - code - message properties: code: type: string message: type: string fields: type: object additionalProperties: type: string doc_url: type: string format: uri securitySchemes: bearerAuth: type: http scheme: bearer ````