Sonar is an AI model by Perplexity. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
Cost Benchmarks
Context Benchmarks
Available from 9 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 3 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Perplexity Agent | $0.25 | $2.5 | $0.0625 | 128K | — |
| DevPass (LLM Gateway) | $1 | $1 | — | 130K | — |
| Eden AI | $1 | $1 | — | 127K | — |
| LLM Gateway | $1 | $1 | — | 130K | — |
| OpenRouter | $1 | $1 | — | 127K | Supported |
| Opper | $1 | $1 | — | 128K | — |
| Perplexity | $1 | $1 | — | 128K | Supported |
| SAP AI Core | $1 | $1 | — | 128K | — |
| Vercel AI Gateway | — | — | — | 127K | Supported |
Sonar — Frequently Asked Questions
How much does Sonar cost?
Sonar costs $1.0 per 1M input tokens and $1.0 per 1M output tokens. This is mid-range pricing for its capability level.
What is the context window of Sonar?
Sonar has a context window of 127K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Sonar?
Sonar was created by Perplexity. It is classified as a mid model in our catalogue.
Is Sonar open source?
No, Sonar is a proprietary model. It is available through Perplexity's API and compatible providers.