Perplexity: Sonar Pro
Perplexity's Sonar Pro is designed for handling extensive text and image inputs with a context length of 200,000 tokens; it supports both text and image modalities but lacks tools, reasoning capabilities, or structured output features. Despite its robust input capacity, this model does not offer the additional functionalities often sought in advanced AI applications. Given its pricing at $3.0 per million input tokens and $15.0 per million output tokens, Sonar Pro is more suitable for projects requiring large-scale text processing and image understanding within budget constraints. With a benchmark blended score of 13.9 across one independent source, it performs adequately but not outstandingly; thus, users should consider their specific needs carefully before shortlisting this model.
Benchmark results
Independent, published benchmarks. Blended score 13.9 across 1 benchmark, last refreshed 2026-07-21. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 15.3 |
- Model ID
- perplexity/sonar-pro
- Vendor
- perplexity
- Released
- March 2025
- Tokenizer
- Other
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 8,000 tokens
- Tool Calling
- not supported
- Structured Output
- not supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $3.00/M input and $15.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.11 |
| Classify 1,000 customer emails | 500k in / 50k out | $2.25 |
| A month of a busy support chatbot | 5M in / 2M out | $45.00 |
Similar models
Quick answers
- How much does Perplexity: Sonar Pro cost?
- $3.00 per million input tokens and $15.00 per million output tokens.
- What is Perplexity: Sonar Pro's context window?
- 200,000 tokens, roughly 300 pages of text in a single request.
- Can Perplexity: Sonar Pro process images?
- Yes, it accepts image input.