Skip to content
FluxCDNFluxCDN
esc

Perplexity: Sonar Deep Research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.

Input
720,776 Toman/M tokens
Output
2,883,104 Toman/M tokens
Context
128K
Max output
115K
Published
Mar 7, 2025
Maker
Perplexity

Free plan prices, in Toman at today's rate. Plans and prices

Price by plan

Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period.

PlanInputOutput
Free720,7762,883,104
Pro691,2362,764,944
Max661,6962,646,784

Search fee

This model searches the web several times for each answer. Besides the tokens, each search is charged the fee below, per plan, in Toman at today's rate; a single answer often runs dozens of searches.

PlanPer search
Free1,802
Pro1,728
Max1,654

Capabilities

  • Text
  • Reasoning

What it takes and gives

Accepts
  • Text
Creates
  • Text

Call it

Pass perplexity/sonar-deep-research as the model name, or let router/auto choose for you.

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.fluxcdn.cloud/api/v1",
    api_key=os.environ["FLUXCDN_API_KEY"],
)

resp = client.chat.completions.create(
    model="router/auto",
    messages=[{"role": "user", "content": "Hello"}],
)

print(resp.choices[0].message.content)