Back
Perplexity: Sonar Reasoning
Other
Input: text
Output: text
Released: Jan 29, 2025•Updated: May 2, 2025
Sonar Reasoning is a reasoning model provided by Perplexity based on DeepSeek R1.
It allows developers to utilize long chain of thought with built-in web search. Sonar Reasoning is uncensored and hosted in US datacenters.
127,000 Token Context
Process and analyze large documents and conversations.
Hybrid Reasoning
Choose between rapid responses and extended, step-by-step processing for complex tasks.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| Perplexity | perplexity | 127K | - | $1.00/M | $5.00/M | 89.6 t/s | 1764 ms |
Standard Pricing
Input Tokens
$0.000001
per 1K tokens
Output Tokens
$0.000005
per 1K tokens
Request
$0.005
per request
Variable Pricing Tiers
search threshold
Threshold: high
Request: $0.012
search threshold
Threshold: medium
Request: $0.008
search threshold
Threshold: low
Request: $0.005