Perplexity models
llm11 can call 5 Perplexity models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $1.00 to $6.00 per million tokens. The newest is Sonar Pro Search, released 2025-10-30.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Sonar Pro Search | $3.00 | $15 | 200K | |
| Sonar Deep Research | $2.00 | $8.00 | 128K | |
| Sonar Pro | $3.00 | $15 | 200K | |
| Sonar Reasoning Pro | $2.00 | $8.00 | 128K | |
| Sonar | $1.00 | $1.00 | 127K |
Read from the live catalogue and refreshed daily. Prices are per million tokens.
Questions
- Which Perplexity models can I call through llm11?
- 5 today, listed with live prices on this page. The list follows the upstream catalogue, so a new Perplexity model appears here without anyone editing the page.
- What is the cheapest and the most expensive Perplexity model?
- By blended price, weighting three parts input to one part output: Sonar is cheapest at $1.00 per million tokens, and Sonar Pro is the most expensive at $6.00.
- What is the newest Perplexity model?
- Sonar Pro Search, released 2025-10-30. Call it with model set to perplexity/sonar-pro-search.