Perplexity: Sonar Reasoning

Name: Sonar Reasoning API
Brand: Perplexity

deprecated

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

sonar-reasoningsonar

Provider Quick start

Context

127K

tokens

Max output

8.2K

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

127K$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-reasoning
Family: sonar
Status: deprecated
Knowledge: -
Released: -

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-reasoning",  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-reasoning

Auth env

PERPLEXITY_API_KEY

Sonar Reasoning FAQ

How much does the Sonar Reasoning API cost?

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

What is the context window of Sonar Reasoning?

Sonar Reasoning accepts up to 127K tokens of context and returns up to 8.2K output tokens on Perplexity.

What can Sonar Reasoning do?

Sonar Reasoning supports chat. It accepts text input.

How do I call Sonar Reasoning through Everstack?

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