> ## Documentation Index > Fetch the complete documentation index at: https://docs.querying.ai/llms.txt > Use this file to discover all available pages before exploring further. # Analyze answer claims and cited sources > Preserves the v2 result. Opt in with analysis.version=1 for question requirements, brand decisions and ownership/production metadata. citations may be empty only in opt-in mode. Analysis failure is explicit inside the result; COMPLETED does not imply analysis.status=ok. The temporary hold includes a payload-sized interpretation budget; actual metered token/fetch rates are unchanged. ## OpenAPI ````yaml post /v1/source-influence openapi: 3.1.0 info: title: querying.ai description: >- One API for every AI answer engine. Every task is asynchronous: submit, then collect the result via webhook or polling. version: 1.0.0 servers: - url: https://api.querying.ai description: Production security: - bearerAuth: [] paths: /v1/source-influence: post: tags: - Research summary: Analyze answer claims and cited sources description: >- Preserves the v2 result. Opt in with analysis.version=1 for question requirements, brand decisions and ownership/production metadata. citations may be empty only in opt-in mode. Analysis failure is explicit inside the result; COMPLETED does not imply analysis.status=ok. The temporary hold includes a payload-sized interpretation budget; actual metered token/fetch rates are unchanged. operationId: createSourceInfluence requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SourceInfluenceRequest' example: answer: Atlas is suitable for small teams. prompt: Which tool is suitable for small teams? citations: [] analysis: version: 1 entities: - id: atlas name: Atlas role: competitor responses: '200': description: >- Queued; poll /v1/async/task/{id}. Its response follows SourceInfluenceResult. content: application/json: schema: $ref: '#/components/schemas/AsyncResponse' '400': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '409': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '413': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '503': description: Request rejected; 422 includes invalid analysis metadata. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: SourceInfluenceRequest: type: object properties: answer: type: string minLength: 1 maxLength: 200000 citations: type: array maxItems: 25 items: $ref: '#/components/schemas/SourceInfluenceCitation' description: >- 1–25 in legacy mode; 0–25 with analysis.version=1. Total HTTP body ≤1 MiB. prompt: type: string maxLength: 200000 country: type: string engine: type: string maxLength: 64 brand: type: string maxLength: 200 competitors: type: array maxItems: 25 items: type: string maxLength: 200 analysis: $ref: '#/components/schemas/SourceAnalysisInput' idempotencyKey: type: string priority: type: integer webhook: type: object properties: url: type: string format: uri required: - url required: - answer - citations AsyncResponse: type: object required: - success - task - credits properties: success: type: boolean const: true task: $ref: '#/components/schemas/TaskMeta' credits: $ref: '#/components/schemas/Credits' ErrorResponse: type: object required: - success - error properties: success: type: boolean const: false error: $ref: '#/components/schemas/ErrorDetail' SourceInfluenceCitation: type: object properties: url: type: string format: uri maxLength: 2048 body: type: string maxLength: 300000 description: >- Exact source snapshot. A supplied body is never replaced with a current fetch. title: type: string kind: type: string enum: - inline - panel fetchedAt: type: string format: date-time relationship: $ref: '#/components/schemas/SourceRelationship' required: - url SourceAnalysisInput: type: object properties: version: type: integer const: 1 entities: type: array maxItems: 50 items: $ref: '#/components/schemas/SourceAnalysisEntity' answeredAt: type: string format: date-time required: - version TaskMeta: type: object required: - id - taskType - status - priority - createdAt properties: id: type: string format: uuid taskType: $ref: '#/components/schemas/TaskType' status: $ref: '#/components/schemas/TaskStatus' priority: type: integer createdAt: type: string format: date-time idempotencyKey: type: string description: >- Echoed back verbatim. **Omitted** — not null — when the caller supplied none. Credits: type: object description: >- Submit and polling envelopes preserve zero values. With billing enabled, account settlement uses the engine pricing policy; webhooks report the persisted charge. SOURCE_INFLUENCE is metered by actual model tokens and source fetches. properties: creditsToCharge: type: integer creditsCharged: type: - integer - 'null' ErrorDetail: type: object required: - code - message properties: code: type: string description: Stable, safe to branch on. enum: - MISSING_API_KEY - VALIDATION_ERROR - REGION_UNAVAILABLE - RESOURCE_ALREADY_EXISTS - PAYLOAD_TOO_LARGE - RESOURCE_NOT_FOUND - ENQUEUE_ERROR message: type: string description: For humans. May change. details: description: >- Field-level context. An array of `{field, message}` on `VALIDATION_ERROR`; an object on `RESOURCE_NOT_FOUND` (`{id}`) and `REGION_UNAVAILABLE`. Omitted when there is nothing to add. oneOf: - type: array items: type: object properties: field: type: string message: type: string - type: object additionalProperties: true timestamp: type: string format: date-time SourceRelationship: type: object properties: ownership: type: string enum: - own - competitor - third_party - unknown ownerEntityId: type: string production: type: string enum: - direct - commissioned - independent - unknown producerEntityId: type: string required: - ownership - production SourceAnalysisEntity: type: object properties: id: type: string pattern: ^[a-zA-Z0-9_-]{1,64}$ name: type: string maxLength: 200 role: type: string enum: - own - competitor - third_party - unknown aliases: type: array maxItems: 20 items: type: string domains: type: array maxItems: 20 items: type: string description: Hostname, matched only at domain boundaries; no scheme or path. brandId: type: string description: Product parent ID, with the same role. No nested products or cycles. required: - id - name - role TaskType: type: string description: >- The engine to query. `NAVER` is a deprecated alias for `NAVER_AI_BRIEF`. GOOGLE_AIO and GOOGLE_AIMODE are the unified names for GOOGLE and AIMODE; both spellings are accepted and responses echo the canonical GOOGLE / AIMODE. enum: - CHATGPT - PERPLEXITY - GEMINI - AIMODE - GOOGLE_AIMODE - GOOGLE - GOOGLE_AIO - NAVER_AI_BRIEF - NAVER_AI_TAB - NAVER - SOURCE_INFLUENCE - CITATION_ATTRIBUTION TaskStatus: type: string description: >- `PROCESSING` means a worker holds the task. `COMPLETED` and `FAILED` are terminal. enum: - QUEUED - PROCESSING - COMPLETED - FAILED securitySchemes: bearerAuth: type: http scheme: bearer description: 'Your API key, sent as `Authorization: Bearer `.' ````