modelgrep
P

Perplexity: Sonar Reasoning Pro

perplexity/sonar-reasoning-pro

ReasoningVision
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
27
248th fastest
Latency
21.0s
first token
Input price
$2.00
247th cheapest
Context
128K

How it compares

Faster than15%
of all ranked models
Cheaper than17%
of all ranked models

Overview

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

Providers & pricing (1)

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

Specifications

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

Sonar Reasoning Pro FAQ

How much does Sonar Reasoning Pro cost?

Sonar Reasoning Pro costs $2.00 per million input tokens and $8.00 per million output tokens via OpenRouter, making it 247th cheapest of 298 paid models.

How fast is Sonar Reasoning Pro?

Sonar Reasoning Pro generates around 27 tokens per second with 21.0s time-to-first-token (p50), the 248th fastest tracked model.

What is Sonar Reasoning Pro's context window?

Sonar Reasoning Pro supports a 128K-token context window. It accepts text, image input.

Compare head-to-head