Providers and ModelsPerplexity

Perplexity-Deep-Research

Perplexity-Deep-Research

Provider: Perplexity
Category: Research & Search
Endpoint: POST /v1/search
Context window: 128K
Served from: —

Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.

At a glance

FieldValue
Model idperplexity-deep-research
Input modalitiestext
Output modalitiestext
Context window128K
Region—
Featuresweb_search, reasoning, deep_research
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
Input Tokensper 1k tokens$0.0048
Output Tokensper 1k tokens$0.019
Citation Tokensper 1k tokens$0.0048
Reasoning Tokensper 1k tokens$0.0072
Search Queriesper query$0.012

Example request

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

Parameters

ParameterTypeRequiredDefaultDescription
reasoning_effortenumno"high"Reasoning depth. · Allowed: low, medium, high
search_after_date_filterstringno—Publication date filter (MM/DD/YYYY).
search_before_date_filterstringno—Publication date filter (MM/DD/YYYY).
last_updated_after_filterstringno—Last-modified filter (MM/DD/YYYY).
last_updated_before_filterstringno—Last-modified filter (MM/DD/YYYY).
search_recency_filterenumno—Restrict to results from the last N. · Allowed: none, day, week, month, year
search_domain_filterstringno—Comma-separated allowlist. Prefix with - to deny.
return_citationsbooleannotrueInclude citations.
temperaturenumberno0.2Sampling temperature. · Range: 0 – 2
max_tokensnumberno16384Max output tokens. · Range: 1 – 65536
disable_formattingbooleannofalseReturn raw upstream response.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/perplexity-deep-research.