Sonar
Provider：Perplexity
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...
Key specs
- Context：127.1K
- Max output：114.4K
- Tokenizer：Other
- Released：2025-01-27
Token pricing
- Input price：$1.00 / 1M tokens
- Output price：$1.00 / 1M tokens
- Blended price：$1.00 / 1M tokens
Modalities
Text, Image
Use Cases
- Vision Understanding & Generation：Recognize data trends in charts, OCR scanned docs, analyze photos and produce structured reports.（≈ $0.0060/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0020/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low output price: cost-effective for high-output tasks (long-form generation, code synthesis).
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
- Multimodal (text+image): fit for image captioning, OCR, chart QA, vision-grounded reasoning.
FAQ
- What is the token pricing of Sonar? Input price $1.00 / 1M tokens, output price $1.00 / 1M tokens, blended about $1.00 / 1M tokens. Refer to Perplexity’s official page for the exact rate.
- What context window does Sonar support? Context window is 127.1K, max output about 114.4K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Sonar best for? Based on its capability and pricing, Sonar fits best: Vision Understanding & Generation, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Sonar support? Supports Text, Image modality.
- Is Sonar a free model? Sonar is billed per token, not a free model.
- Which provider offers Sonar? Sonar is offered by Perplexity.
More models from Perplexity
Full info：Sonar