Documentation Index
Fetch the complete documentation index at: https://exa.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Date: March 4, 2026
What’s New
- Greatly improved performance for Exa Deep workloads.
- Latency ranges:
deep: 4 to 12 secondsdeep-reasoning: 12 to 50 seconds
- New search type:
deep-reasoningfor higher-effort reasoning tasks. - 20% lower price for regular
deepsearch. - Structured outputs for Deep using output schemas. Built to provide web grounded fields perfect for enrichments.
- New request schema controls:
type,description, andpropertiesonoutputSchema(output_schemain Python SDK). - New synthesized response fields:
output.contentandoutput.grounding.
Structured Outputs
For deep search variants (deep, deep-reasoning), you can define the output shape using:
outputSchemain JavaScript/TypeScript and RESToutput_schemain Python
typedescriptionproperties
Deep Output Response Shape
Deep responses now include:output.contentfor synthesized text or structured JSONoutput.groundingfor field-level citations and confidence

