Skip to content
FluxCDNFluxCDN
esc

Perplexity: Sonar Reasoning Pro

Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT).

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 for every request. Besides the tokens, each request is charged the search fee below, per plan, in Toman at today's rate.

PlanPer request
Free1,802
Pro1,728
Max1,654

Capabilities

  • Text
  • Vision
  • Reasoning

What it takes and gives

Accepts
  • Text
  • Image
Creates
  • Text

Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.

Call it

Pass perplexity/sonar-reasoning-pro 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)