Perplexity Sonar | EmpirioLabs AI Docs

Perplexity · Research & Search

POST /v1/chat/completions

Real-time web-connected search with accurate citations and customizable sources for up-to-date AI search integration in production apps.

At a glance

Field	Value
Model id	`perplexity-sonar`
Input modalities	Text, Image, Document
Output modalities	Text
Context window	127K
Weight precision	-
Features	web_search
Native inference	No
New	No
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1/search`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$2.40
Output	per 1M generated tokens	$2.40
Base Fee (Low Context)	per request	$0.012
Base Fee (Medium Context)	per request	$0.019
Base Fee (High Context)	per request	$0.029

Example request

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

Parameters

Parameter	Type	Required	Default	Description
`temperature`	number	no	`0.2`	Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2
`top_p`	number	no	`0.9`	Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1
`max_tokens`	number	no	`1024`	Maximum tokens in the response. · Range: 1 – 32768
`search_context_size`	enum	no	`"medium"`	Higher context gives better answers but increases the base fee per request. · Allowed: `low`, `medium`, `high`
`search_mode`	enum	no	`"default"`	Filter search results by source type. Academic = scholarly papers, SEC = financial filings. · Allowed: `default`, `academic`, `sec`
`search_domain_filter`	string	no	-	Comma-separated list of domains (allow with no prefix, deny with leading -)
`search_language_filter`	string	no	-	Comma-separated ISO 639-1 codes (2 letters). Max 10.
`search_after_date`	string	no	-	Use YYYY-MM-DD. Only include sources after this date.
`search_before_date`	string	no	-	Use YYYY-MM-DD. Only include sources before this date.
`search_recency_filter`	enum	no	`"none"`	Relative time filter. Cannot be combined with specific dates. · Allowed: `none`, `hour`, `day`, `week`, `month`, `year`
`last_updated_after_filter`	string	no	-	Use YYYY-MM-DD. Only include sources after this date.
`last_updated_before_filter`	string	no	-	Use YYYY-MM-DD. Only include sources before this date.
`country`	string	no	-	Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.
`region`	string	no	-	State or province name for location bias.
`city`	string	no	-	City name for location bias.
`latitude`	number	no	-	Latitude for location bias, in decimal degrees.
`longitude`	number	no	-	Longitude for location bias, in decimal degrees.
`return_images`	boolean	no	false	Include relevant images alongside the search results.
`image_domain_filter`	string	no	-	Comma-separated domains for image results. Prefix with ’-’ to exclude. Max 10.
`image_format_filter`	string	no	-	Comma-separated image file formats to allow (jpg, png, etc.).
`return_videos`	boolean	no	false	Include relevant videos alongside the search results.
`disable_formatting`	boolean	no	false	Skip the EmpirioLabs Markdown formatting (citation [N] rewriting + References block + Images / Videos blocks). The raw upstream answer with plain [N] citations is returned; structured search_results / citations still pass through where Perplexity emits them.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/perplexity-sonar.