> ## Documentation Index > Fetch the complete documentation index at: https://docs.seneca.professionalaiagents.com/llms.txt > Use this file to discover all available pages before exploring further. # Export stored model responses > Download every model response stored on a completed or partial run as UTF-8 JSONL. Each line is one model. text is the complete stored response, or null. Save the file for your own analysis. Do not load the whole panel into an AI agent's context. To inspect one finding, use /responses and /responses/text instead. This read does not start research, call a provider, or charge credits. ## OpenAPI ````yaml https://seneca-research.fly.dev/v1/openapi.json get /v1/research/{run_id}/responses/export openapi: 3.1.0 info: title: Seneca Research API version: 0.1.0 description: >- Create a research run, poll it, then read the customer report. Original model text is a separate read: list /v1/research/{run_id}/responses, read one model at /v1/research/{run_id}/responses/text, or download the panel as JSONL from /v1/research/{run_id}/responses/export. Send Authorization: Bearer seneca_sk_… Narrative quickstart: https://seneca.professionalaiagents.com/api.md servers: - url: https://seneca-research.fly.dev description: Production security: [] paths: /v1/research/{run_id}/responses/export: get: tags: - public-api summary: Export stored model responses description: >- Download every model response stored on a completed or partial run as UTF-8 JSONL. Each line is one model. text is the complete stored response, or null. Save the file for your own analysis. Do not load the whole panel into an AI agent's context. To inspect one finding, use /responses and /responses/text instead. This read does not start research, call a provider, or charge credits. operationId: export_research_responses_v1_research__run_id__responses_export_get parameters: - name: run_id in: path required: true schema: type: string format: uuid title: Run Id responses: '200': description: >- UTF-8 JSONL attachment, one stored model response per line. The body is not a JSON array. Each line matches PublicModelResponseExportRecord. text is the complete persisted response, or null. headers: Content-Disposition: description: attachment; filename="seneca-{run_id}-responses.jsonl" schema: type: string content: application/x-ndjson: schema: $ref: '#/components/schemas/PublicModelResponseExportRecord' '401': description: >- authentication_required when the bearer token is missing or not a bearer token. invalid_api_key when the key is unknown, revoked, or expired. content: application/json: schema: $ref: '#/components/schemas/PublicErrorResponse' '404': description: run_not_found. Another workspace's run is also run_not_found. content: application/json: schema: $ref: '#/components/schemas/PublicErrorResponse' '409': description: >- responses_not_ready while the run is queued, running, or synthesizing. research_failed when the run finished without a completed or partial panel. content: application/json: schema: $ref: '#/components/schemas/PublicErrorResponse' '429': description: >- rate_limit_exceeded. Reads are limited to 120 requests per minute per key. content: application/json: schema: $ref: '#/components/schemas/PublicErrorResponse' '500': description: internal_error. The body does not include a traceback or a secret. content: application/json: schema: $ref: '#/components/schemas/PublicErrorResponse' security: - SenecaApiKey: [] x-codeSamples: - lang: javascript label: JavaScript source: | const response = await fetch( `https://seneca-research.fly.dev/v1/research/${runId}/responses/export`, { headers: { Authorization: `Bearer ${process.env.SENECA_API_KEY}` }, }, ) if (!response.ok) { throw new Error(await response.text()) } const jsonl = await response.text() const rows = jsonl .split("\n") .filter(Boolean) .map((line) => JSON.parse(line)) components: schemas: PublicModelResponseExportRecord: properties: model_id: type: string title: Model Id description: Model id stored on this run. A retired model keeps this id. display_name: anyOf: - type: string - type: 'null' title: Display Name description: >- Name frozen on the run's panel snapshot. Null when the snapshot has none. laboratory: anyOf: - type: string - type: 'null' title: Laboratory description: >- Laboratory name frozen on the panel snapshot. Null when the snapshot has none. status: type: string title: Status description: success, error, or timeout. input_tokens: anyOf: - type: integer - type: 'null' title: Input Tokens output_tokens: anyOf: - type: integer - type: 'null' title: Output Tokens text: anyOf: - type: string - type: 'null' title: Text description: >- Complete original response stored for this model. Null when no text was stored. This export does not apply the 32000-character window used by the single-model read. additionalProperties: false type: object required: - model_id - status title: PublicModelResponseExportRecord description: One JSONL line in a full-panel export. text is not windowed. PublicErrorResponse: properties: error: $ref: '#/components/schemas/PublicErrorObject' additionalProperties: false type: object required: - error title: PublicErrorResponse description: Error envelope returned by every /v1 failure. Documentation model only. PublicErrorObject: properties: code: type: string title: Code message: type: string title: Message details: additionalProperties: true type: object title: Details additionalProperties: false type: object required: - code - message title: PublicErrorObject securitySchemes: SenecaApiKey: type: http description: >- Workspace API key created while signed in on the Developers page. Send Authorization: Bearer seneca_sk_… A Clerk session token is not accepted. scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.