CATALOG

Models

Find the right model by capability, context and price. Compare options or try one in Chat.

Output / endpointExact metadata
7 of 647 modelsReference token prices are per million tokens.

pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...

by perplexityMar 16, 202632K context$0.03/M input$0/M outputText → Embeddings

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...

by perplexityMar 16, 202632K context$0.004/M input$0/M outputText → Embeddings
VisionReasoning

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

by perplexityMar 7, 2025128K context$2/M input$8/M outputText, Image → Text
Vision

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

by perplexityMar 7, 2025200K context$3/M input$15/M outputText, Image → Text
Reasoning

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

by perplexityMar 7, 2025128K context$2/M input$8/M outputText → Text
Vision

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...

by perplexityJan 27, 2025127.07K context$1/M input$1/M outputText, Image → Text