데이터 API / Exa / Agent
Poll a research Agent run.
Fetch an Agent run submitted by post_exa_agent_runs, by its jobId. Returns the same envelope — id, status, createdAt, completedAt, pricing, output, error. Repeat until status is completed, failed or cancelled; on success output carries text, structured and grounding. Reads a run only; it cannot start one.
파라미터
경로
jobIdstring필수The job id returned by the submit call.
요청 예시
curl -X GET "https://openapi.felo.ai/v1/beta/exa/agent/runs/{jobId}" \
-H "Authorization: Bearer $FELO_API_KEY"응답
응답 필드
idstring선택Job identifier. Use it with the corresponding Felo polling endpoint.
objectstring선택Always "integration_async_job".
endpointstring선택Provider operation identifier stored with the job. This metadata is not a Felo polling URL; use the documented Felo job path or Location header.
statusstring선택허용 값: queued · running · completed · failed · cancelled
Customer-facing lifecycle status. queued and running are non-terminal; completed, failed, and cancelled are terminal.
createdAtstring선택When the job was accepted.
completedAt선택When the job reached a terminal status. Null while the job is still queued or running.
pricingobject선택currencystring선택authorizedMicrosUSDinteger선택Provider authorization metadata in micro-USD. This is not a Felo credit hold or billing record.
finalMicrosUSD선택Provider settlement metadata in micro-USD, nullable before settlement. This is not the Felo charge.
billingModestring선택Provider job billing mode. Felo charges follow Felo billing records.
output선택Job result payload. Present only once status is completed. For Agent Runs this is the structured research result.
outputExpiredboolean선택True when the result has been retained past its retention window and is no longer retrievable.
error선택Present when status is failed. Null otherwise.