Sonar Reasoning
Perplexity • text
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Specifications
Context Window
127K tokens
Input Price/1M
—
Output Price/1M
—
Parameters
—
Benchmarks
Sonar Reasoning results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LiveCodeBench | 30.0 | 100.0 | — |
| SciCode | 23.0 | 100.0 | — |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 69.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 95.7 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 11.7 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 62.0 | 100.0 | Artificial Analysis official API |
| HLE | 7.0 | 100.0 | — |
Information
- Release date
- January 28, 2025
- Tool Calling
- ❌ Not supported
- Vision
- ✅ Supported
- Audio
- ❌ Not supported
Full Analysis: Sonar Reasoning
What is Sonar Reasoning?
Sonar Reasoning is an AI model developed by Perplexity, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Perplexity's cloud API. With a context window of 127K tokens, it is suitable for processing long documents such as contracts, books, and complete codebases.
Pricing & Costs in 2026
Sonar Reasoning does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check Perplexity's official website for up-to-date availability and pricing.
Benchmarks & Performance
Sonar Reasoning was evaluated on 7 different benchmarks, covering categories like Coding, Knowledge, Math, overall, Reasoning. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Sonar Reasoning specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, Sonar Reasoning competes directly with similarly capable models. Perplexity competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Sonar Reasoning?
Sonar Reasoning is an AI model developed by Perplexity. It is a text model.
How much does Sonar Reasoning cost?
Sonar Reasoning does not have public per-token pricing available at this time. Check Perplexity's official website for up-to-date information.
How does Sonar Reasoning compare with other models?
In available benchmarks, Sonar Reasoning scored: LiveCodeBench: 30/100, SciCode: 23/100, MMLU-Pro: 69/100. See the full table above for a detailed comparison.
Is Sonar Reasoning open source?
No, Sonar Reasoning is a proprietary model from Perplexity. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Sonar Reasoning best for?
Sonar Reasoning excels at multimodal tasks including text and vision. With its large context window, it handles long documents, codebases, and extended conversations.
Last updated: July 06, 2026 • View methodology →