modelgrep
P

Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Reasoning
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
30
237th fastest
Latency
38.9s
first token
Input price
$2.00
248th cheapest
Context
128K

How it compares

Faster than19%
of all ranked models
Cheaper than17%
of all ranked models

Overview

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Perplexity$2.00$8.00

Specifications

Context window128K
Max output
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Sonar Deep Research FAQ

How much does Sonar Deep Research cost?

Sonar Deep Research costs $2.00 per million input tokens and $8.00 per million output tokens via OpenRouter, making it 248th cheapest of 298 paid models.

How fast is Sonar Deep Research?

Sonar Deep Research generates around 30 tokens per second with 38.9s time-to-first-token (p50), the 237th fastest tracked model.

What is Sonar Deep Research's context window?

Sonar Deep Research supports a 128K-token context window. It accepts text input.

Compare head-to-head