You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

Sonar-pro by Perplexity is a model with native web search: it finds information on the internet and builds answers based on sources. It has a 200,000 token context window and accepts images and documents. Suitable for research, market overviews, fact-checking, and working with long documents.

Sonar-pro generates up to 8,000 tokens per response, which is enough for a detailed overview, analytical report, or in-depth topic analysis with links. If you need a longer document, break the task into parts and assemble the text using sequential queries in one dialogue.

A dedicated reasoning mode is not specified in our data, so we cannot promise it. However, the model relies on sources found online and can explain its thought process if you ask it in the prompt to break down the task step-by-step and explain its conclusions.

There is no mention of function calling or structured JSON output in our data, so you should test this behavior in your scenario. Connection is via the unified OpenAI-compatible BotHub API: you can specify the response format in the prompt and switch to another model if needed without rewriting the integration.

Images and documents are confirmed input formats: attach a screenshot, diagram, PDF, or report and ask it to analyze the content along with a web search. Audio and video are not mentioned in our data, so please choose a specialized model in BotHub for working with recordings.

The language of prompts and responses is not fixed in our data, so it is best to evaluate it with your own task: send a few typical queries and compare the result with another model in the same window. The BotHub interface is in Russian, with payment via Russian cards, and access without VPN or foreign cards.