Perplexity models

Perplexity runs an AI answer engine and offers developer APIs for search, embeddings and agents. Its Agent API serves Perplexity's own Sonar model next to third-party models from OpenAI, Anthropic, Google and xAI, with built-in tools such as web search. The Agent API replaced the older Sonar Chat Completions API, whose support ended on September 27, 2026.

1 model trackedData checked October 10, 2026

Lineup

Model	Status	Weights	Tier	Context	Input / 1M	Output / 1M	Released
SonarSonar	Current	Closed	Efficient	—	$0.25	$2.50	Jan 2025

The lowest-priced current model is Sonar at $0.25 input and $2.50 output per million tokens. The most capable tier in the lineup is efficient, led by Sonar.

Frequently asked questions

What models does Perplexity offer?

As of October 10, 2026, we track 1 Perplexity model: Sonar. Status, prices and context windows for each are in the table on this page.

How do I access Perplexity models?

Through Perplexity's developer platform (docs.perplexity.ai), in the Perplexity app, and for many models through cloud marketplaces and inference providers listed on each model page.

Does Perplexity release open-weight models?

Some: smaller models such as embedding and utility models on Hugging Face; Sonar is API-only

Other providers

OpenAI Anthropic Google xAI Amazon (AWS)Meta Mistral AI DeepSeek Alibaba (Qwen)Microsoft (Phi)NVIDIA Moonshot AI Z.ai (Zhipu AI)MiniMax IBM Ai2 (Allen Institute for AI)

Still choosing a model?

Send us your use case and constraints. We'll come back with a shortlist and an evaluation plan you can run on your own data.

Free and vendor-neutral: no model provider pays for placement.
Your details go only to partners you agree to.