Perplexity: Sonar Deep Research

Name: Sonar Deep Research API
Brand: Perplexity

stable

Sonar Deep Research is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

sonar-deep-researchsonarreleased Feb 1, 2025

Provider Quick start

Context

128K

tokens

Max output

32.8K

tokens

Input

$2.00

per 1M

Output

$8.00

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Perplexity

128K$2.00$8.00

Pricing

Item	Price	Unit
Input	$2.00	per 1M tokens
Output	$8.00	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: sonar-deep-research
Family: sonar
Status: stable
Knowledge: -
Released: Feb 1, 2025

Gateway Config

API: 2024-01-01
Auth: PERPLEXITY_API_KEY
Discovery: static
Provider type: static

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@perplexity/sonar-deep-research",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.perplexity.ai

Chat completions

https://api.perplexity.ai/chat/completions

Model

sonar-deep-research

Auth env

PERPLEXITY_API_KEY

Sonar Deep Research FAQ

How much does the Sonar Deep Research API cost?

Through Perplexity, Sonar Deep Research costs $2.00 per 1M input tokens and $8.00 per 1M output tokens.

What is the context window of Sonar Deep Research?

Sonar Deep Research accepts up to 128K tokens of context and returns up to 32.8K output tokens on Perplexity.

What can Sonar Deep Research do?

Sonar Deep Research supports chat and reasoning. It accepts text input.

How do I call Sonar Deep Research through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @perplexity/sonar-deep-research. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.