Perplexity models

Perplexity's Sonar models are built for search-grounded answering: they retrieve from the live web and cite sources as part of the response. Zeplik carries Sonar Pro Search at the head of the line, with Sonar Reasoning Pro, Sonar Deep Research and the base Sonar model behind it.

Ask a Perplexity model now

All 5 Perplexity models

Pricing at a glance

Frequently asked questions

Which Perplexity models can I use on Zeplik?

Zeplik carries 5 Perplexity models: Sonar Pro Search, Sonar Reasoning Pro, Sonar Pro, Sonar Deep Research and Sonar. They all run in the same chat, so you do not need a separate Perplexity account or API key.

How much do Perplexity models cost on Zeplik?

Output tokens run from 12.0 to 180 credits per million depending on which Perplexity model you pick (raw provider rates $1.00 to $15.00 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.

Which Perplexity model has the largest context window?

Sonar Pro Search, at 200K tokens (200,000). The context window covers the conversation plus any documents you attach.

Do Perplexity models support images and tool calling?

4 of the 5 accept image input, and none support tool calling.

Do I need a paid plan to use Perplexity models on Zeplik?

All 5 need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.

What is the newest Perplexity model on Zeplik?

Sonar Pro Search, released October 2025. Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis.

Other providers

• OpenAI (71)
• Qwen (41)
• Google (40)
• Mistral (21)
• Z.ai (19)
• Anthropic (18)
• DeepSeek (15)
• Meta (11)
• All models