For the complete documentation index, see llms.txt. This page is also available as Markdown.

Depth

Depth is how much effort to spend on a request. It is the only quality dial, and it never names a model — internal models can change without breaking your integration.

ValueUse whenPapers consideredLatencyCost
standardinteractive UI, short questionsfewerfastestlowest
high_qualitytechnical questions needing careful readingmoremoderatehigher
deep_reviewagentic synthesis across the literaturemostminuteshighest
Valuemax_papers ceilingLatency p50 / p95Search credits
standard206 s / 15 s5
high_quality5020 s / 45 s15
deep_review20090 s / 240 s60

max_papers above a tier's ceiling is clamped, not rejected. deep_review is available on searches and chat messages, not on topic searches or extractions.

Choosing

Default to standard and escalate on demand — most user questions do not need a deep review, and depth is the largest single driver of both cost and latency. For deep_review, stream the result or use a webhook; do not block a request thread on it.

searches · chats · credit · streaming-deep-review

Last updated