Providers and ModelsExa

Exa Research

Exa Research
Exa · Research & Search
POST /v1/research

Asynchronous research task that explores the web, gathers sources, synthesizes findings, and returns cited answers for in-depth queries.

This model is deprecated and will be retired on 2026-06-26. After that date, requests to this model will fail. Migrate to a successor model before then.

At a glance

FieldValue
Model idexa-research
Input modalitiesText
Output modalitiesText
Context window-
Weight precision-
Featuresweb_search, reasoning
Native inferenceNo
NewNo
Supported endpointsPOST /v1/research, POST /v1/search
Deprecation date2026-06-26

Pricing

ChargeSpecRate
exa-research-fast (search)per search$0.013
exa-research (search)per search$0.013
exa-research-pro (search)per search$0.013
Page Read (standard)per page$0.013
Page Read (pro)per page$0.026
Reasoning Tokensper 1k tokens$0.013

Example request

$curl https://api.empiriolabs.ai/v1/research \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "exa-research", "query": "latest CRDT research papers 2026"}'

Parameters

ParameterTypeRequiredDefaultDescription
querystringyes-The natural-language query to search/research/answer.
research_modelenumno"exa-research"Pick the research depth tier. Fast = cheaper / lower depth. Pro = deeper. Default = balanced. · Allowed: exa-research, exa-research-pro, exa-research-fast
disable_formattingbooleannofalseSkip the EmpirioLabs Markdown formatting (citation [N] rewriting + References block). The raw upstream research output with plain [N] citations is returned; structured citations / sources still pass through.

Notes

Three tiers — exa-research-fast (lightest), exa-research (default), exa-research-pro (deepest). Long-running async — may take several minutes.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/exa-research.