Perplexity
Sonar
Sonar from Perplexity: Fast web-grounded Sonar for current answers, citations, and lightweight retrieval.
- Context
- 128K
- Max output
- 4.1K
- Input / 1M tokens
- $1.00
- Output / 1M tokens
- $1.00
Accepts
- Text input
Produces
- Text output
AI model comparison
Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.
Sonar from Perplexity lists 128K context, 4.1K maximum output, $1.00 input per 1M tokens, $1.00 output per 1M tokens. Sonar Reasoning Pro from Perplexity lists 128K context, 4.1K maximum output, $2.00 input per 1M tokens, $8.00 output per 1M tokens. Compare the inputs, outputs and deployment options below to see which fits your workflow.
Perplexity
Sonar from Perplexity: Fast web-grounded Sonar for current answers, citations, and lightweight retrieval.
Accepts
Produces
Perplexity
Sonar Reasoning Pro from Perplexity: Web-grounded Sonar for multi-step research questions that need cited reasoning.
Accepts
Produces
At a glance
Compare the available figures below, then try both models on the work you need to do.
Sonar
Context capacity
Higher listed limit
Sonar:128K
Sonar Reasoning Pro:128K
Same value
Maximum output
Higher listed limit
Sonar:4.1K
Sonar Reasoning Pro:4.1K
Same value
Input price
Lower listed token rate
Sonar:$1.00
Sonar Reasoning Pro:$2.00
Sonar
Output price
Lower listed token rate
Sonar:$1.00
Sonar Reasoning Pro:$8.00
Sonar
Specifications
| Specification | Sonar | Sonar Reasoning Pro |
|---|---|---|
| Provider | Perplexity | Perplexity |
| Listed pricing route | Perplexity | Perplexity |
| Model family | sonar | sonar-reasoning |
| Accepted inputs | text | text, image |
| Produced outputs | text | text |
| Context window | 128K | 128K |
| Max output | 4.1K | 4.1K |
| Input price / 1M | $1.00Lower | $2.00 |
| Output price / 1M | $1.00Lower | $8.00 |
| Reasoning mode | Not documented | Documented |
| Tool calling | Not documented | Not documented |
| Image input | Not documented | Documented |
| Audio input | Not documented | Not documented |
| Structured output | Not documented | Not documented |
| License | Proprietary | Proprietary |
Workload guidance
Consider Sonar if you need a lower listed input rate or a lower listed output rate. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.
Explore each model’s features, API requirements and licence terms in the sources below.
Sonar
Perplexity
Profile updated Oct 13, 2026
Sonar Reasoning Pro
Perplexity
Profile updated Oct 13, 2026
Search by model or provider to explore another comparison.