Skip to main content
Each entry in requests is a group: one content plus a list of questions about it — so asking several questions about the same content sends that content only once, and a single call can still mix groups with different content.
/decide/batch requires the same API key header as /decide. See Authentication.

Request

Top-level latency_mode (batch only) chooses the accuracy/latency trade for the call:
  • quality (default) — each question gets its own backbone call
  • fast — the server may pack several questions about the same document into one call (materially faster, measurably less accurate; intended for triage-style workloads). Kinds that are not eligible for packing keep quality behavior. Available on Starter and Growth plans only.
Each question can carry its own optional grounding (grounding is not part of the group; sort questions still reject it).
To batch decisions about different content, add more groups:

Response

Batch responses are nested by group, then by question:
  • results: one item per group (matches requests 1:1)
  • results[i].answers: one item per question in that group’s questions, in order
  • results[i].answers[j].ok: success flag for that question (.result holds the decision, or .error the message)
  • meta.request_count: number of groups
  • meta.question_count: total questions across all groups (for reference; billing uses document count — see Pricing)
  • meta.latency_ms: internal serving latency for the whole batch call