perplexity

Perplexity: Sonar Deep Research

Sonar Deep Research from Perplexity is a powerful AI model designed for handling extensive text inputs, capable of managing up to 128,000 tokens in context and generating up to 115,200 completion tokens. It supports reasoning tasks, making it suitable for complex problem-solving scenarios. However, this model does not offer structured output or integrated tools, limiting its flexibility in certain applications. While Sonar Deep Research is a robust choice for those needing extensive text processing and reasoning capabilities, its high price point of $2.0 per million input tokens and $8.0 per million output tokens might make it less attractive compared to more cost-effective alternatives until independent benchmark data becomes available.

Quality Score
71/100
price + capability + benchmarks
Input Price
$2.00
per 1M tokens · checked 2026-09-04
Output Price
$8.00
per 1M tokens · checked 2026-09-04
Context Window
128,000
tokens
Model ID
perplexity/sonar-deep-research
Vendor
perplexity
Released
March 2025
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
115,200 tokens
Tool Calling
not supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $2.00/M input and $8.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.07
Classify 1,000 customer emails 500k in / 50k out $1.40
A month of a busy support chatbot 5M in / 2M out $26.00

Similar models

Quick answers

How much does Perplexity: Sonar Deep Research cost?
$2.00 per million input tokens and $8.00 per million output tokens.
What is Perplexity: Sonar Deep Research's context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does Perplexity: Sonar Deep Research support tool calling?
It supports a reasoning mode.
Can Perplexity: Sonar Deep Research process images?
No, it is text-only on the input side.