GET /v1/fund-letters/semantic

curl -X GET \
  -H "x-api-key: $SECAPI_API_KEY" \
  -H "secapi-version: 2026-03-19" \
  "https://api.secapi.ai/v1/fund-letters/semantic?q=risk+factors"

{
  "requestId": "req_2ZK8Q1W9F4M6P7R3"
}

Semantic (vector) search over letter content; hits carry similarity scores, matched chunks, and page anchors.

Audience: application and coding agent.

Coverage and source scope

Metered as fund_letter_semantic; paid plans only. Results are a relevance-ranked top-N (hasMore is always false). third_party-distribution letters return snippet-capped chunks (their /document is not distributable). On vector-engine failure the response degrades to lexical hits (score 0), reported via degradedState.

Canonical metadata

requestId
traceparent

Example request

curl -X GET \
  -H "x-api-key: $SECAPI_API_KEY" \
  -H "secapi-version: 2026-03-19" \
  "https://api.secapi.ai/v1/fund-letters/semantic?q=risk+factors"

Example response

{
  "requestId": "req_2ZK8Q1W9F4M6P7R3"
}

Give this prompt to your agent

Failure posture

treat non-2xx responses as contract-aware failures, not free-form errors
preserve requestId and traceparent in logs and downstream reports
if provenance or freshness metadata is present, return it unchanged so trust is not lost in the handoff

​Coverage and source scope

​Canonical metadata

​Example request

​Example response

​Give this prompt to your agent

​Failure posture

Coverage and source scope

Canonical metadata

Example request

Example response

Give this prompt to your agent

Failure posture