> ## Documentation Index > Fetch the complete documentation index at: https://docs.fuseai.com/llms.txt > Use this file to discover all available pages before exploring further. # Start a Deep Research run > Starts an autonomous Deep Research run for the prompt and returns immediately with 202. Billing is per provider action inside the run, gated by the balance and capped by `effort` (low 1000, medium 2000 (default), high 5000 credits); the run always produces a markdown report (`reportMarkdown` on GET /business/research/runs/{runId}) and, when it surfaces people or companies, a result list (`resultListId`). Send an `X-Idempotency-Key` header of 8 to 200 characters to make retries safe: a replay returns the existing run instead of starting another (a key outside that length is rejected with 422; an empty header is treated as if none was sent). Poll GET /business/research/runs/{runId} until status is completed, failed or cancelled, or stream progress from GET /business/research/runs/{runId}/events. Prompts are limited to 2000 characters by the research engine. Rate limits: 30 requests per minute and 1000 per day on this endpoint, plus 5 run starts per minute and 100 per day in the research engine. Errors: - `422` `VALIDATION_FAILED` — `prompt` is missing or outside 4-2000 characters, `effort` is not low, medium or high, or the `X-Idempotency-Key` header was sent with a value outside 8-200 characters. - `429` `RATE_LIMITED` — Either this endpoint's quota (30 per minute, 1000 per day) or the research engine's own start quota (5 per minute, 100 per day) is exhausted; retry after the Retry-After / RateLimit-Reset seconds. Requires one of the following token scopes: research. ## OpenAPI ````yaml /openapi.json post /business/research/runs openapi: 3.1.0 info: title: Fuse Business API version: 1.0.0 description: >- External API for lists, campaigns, prospect search and contacts. Authenticate with your API token as HTTP Basic. All paths are under /api/v1. servers: - url: https://api.tryfuse.ai/api/v1 description: Production security: - basicAuth: [] tags: - name: Lists - name: Custom columns - name: Smart columns - name: Exports - name: Campaigns - name: Knowledge hubs - name: Analytics - name: Website intent - name: Account - name: Prospect search - name: Campaign steps - name: Scheduled sends - name: Campaign templates - name: Agents - name: Research - name: Company search - name: Saved searches - name: Folders - name: Contacts paths: /business/research/runs: post: tags: - Research summary: Start a Deep Research run description: >- Starts an autonomous Deep Research run for the prompt and returns immediately with 202. Billing is per provider action inside the run, gated by the balance and capped by `effort` (low 1000, medium 2000 (default), high 5000 credits); the run always produces a markdown report (`reportMarkdown` on GET /business/research/runs/{runId}) and, when it surfaces people or companies, a result list (`resultListId`). Send an `X-Idempotency-Key` header of 8 to 200 characters to make retries safe: a replay returns the existing run instead of starting another (a key outside that length is rejected with 422; an empty header is treated as if none was sent). Poll GET /business/research/runs/{runId} until status is completed, failed or cancelled, or stream progress from GET /business/research/runs/{runId}/events. Prompts are limited to 2000 characters by the research engine. Rate limits: 30 requests per minute and 1000 per day on this endpoint, plus 5 run starts per minute and 100 per day in the research engine. Errors: - `422` `VALIDATION_FAILED` — `prompt` is missing or outside 4-2000 characters, `effort` is not low, medium or high, or the `X-Idempotency-Key` header was sent with a value outside 8-200 characters. - `429` `RATE_LIMITED` — Either this endpoint's quota (30 per minute, 1000 per day) or the research engine's own start quota (5 per minute, 100 per day) is exhausted; retry after the Retry-After / RateLimit-Reset seconds. Requires one of the following token scopes: research. operationId: startResearchRun requestBody: required: true content: application/json: schema: type: object properties: prompt: type: string minLength: 4 maxLength: 2000 description: >- The research question or brief in plain text, 4 to 2000 characters. effort: type: string enum: - low - medium - high description: >- Research depth tier that sets the run's credit spend cap: low (1000 credits), medium (2000, the default when omitted) or high (5000). required: - prompt responses: '202': description: Success headers: RateLimit-Limit: schema: type: integer description: Requests permitted in the current window. RateLimit-Remaining: schema: type: integer description: Requests remaining in the current window. RateLimit-Reset: schema: type: integer description: Seconds until the current window resets. content: application/json: schema: type: object properties: run: type: object properties: runId: type: string status: type: string enum: - queued - planning - plan_review - running - generating_csv - uploading - completed - failed - cancelled required: - runId - status required: - run example: run: runId: 68a205cc9c41d20014b40888 status: queued '400': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '402': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '409': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '422': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: Error content: application/json: schema: $ref: '#/components/schemas/Error' security: - basicAuth: [] components: schemas: Error: type: object properties: error: type: object properties: code: type: string message: type: string param: type: - string - 'null' doc_url: type: - string - 'null' request_id: type: - string - 'null' required: - code - message required: - error securitySchemes: basicAuth: type: http scheme: basic description: >- Your API token (`af_…`) as the Basic-auth username, with an empty password. ````