LLM ReferenceLLM Reference

Sonar

27 models2024–2025Up to 205K ctxFrom $0.2/1M input

About

The Sonar family of Large Language Models (LLMs), developed by Perplexity AI, marks a notable progression in terms of cost-efficiency, speed, and performance compared to predecessors like PPLX and Mixtral 5. These models are distinct for their ability to provide real-time internet access and deliver up-to-date information, which is a significant improvement over traditional LLMs 5. The Sonar family comprises different model configurations, such as "small" and "large" models, each tailored for specific tasks and featuring varying context window lengths 67. Built upon the foundation of the Llama 3.1 model, Sonar models are further refined with Perplexity's proprietary search capabilities to enhance accuracy and relevance 10. They offer both online and chat versions, catering to a wide range of applications that require either rapid responses or more extended conversational interactions 57. Additionally, these models are available through APIs, facilitating their integration into various applications seamlessly 67.

Specifications(27 models)

Sonar model specifications comparison
ModelReleasedContextParametersStructured Outputs
Sonar Reasoning2025-01Yes
Sonar2025-01131kYes
Sonar Pro2025-01205kYes
Perplexity sonar-small-chat2024-11Yes
Perplexity sonar-small-online2024-11Yes
Perplexity sonar-medium-chat2024-11Yes
Perplexity sonar-medium-online2024-11Yes
Sonar Small2024-10128k32BNo
Sonar Medium2024-10128k70BNo
Sonar Large2024-10128kNo
Perplexity Llama 3.1 Sonar2024-10200k70BNo
Perplexity Sonar Reasoning Pro2024-09131kYes
Perplexity Sonar Pro Search2024-08Yes
Perplexity Sonar Deep Research2024-08Yes

Available From(2 providers)

Pricing

Frequently Asked Questions

What is Sonar?
The Sonar family of Large Language Models (LLMs), developed by Perplexity AI, marks a notable progression in terms of cost-efficiency, speed, and performance compared to predecessors like PPLX and Mixtral 5. These models are distinct for their ability to provide real-time internet access and deliver up-to-date information, which is a significant improvement over traditional LLMs 5. The Sonar family comprises different model configurations, such as "small" and "large" models, each tailored for specific tasks and featuring varying context window lengths 67. Built upon the foundation of the Llama 3.1 model, Sonar models are further refined with Perplexity's proprietary search capabilities to enhance accuracy and relevance 10. They offer both online and chat versions, catering to a wide range of applications that require either rapid responses or more extended conversational interactions 57. Additionally, these models are available through APIs, facilitating their integration into various applications seamlessly 67.
How many models are in the Sonar family?
The Sonar family contains 27 models.
What is the latest Sonar model?
The latest model is Sonar Reasoning, released in 2025-01.
How much does Sonar cost?
Sonar models range from $0.2/1M to $3/1M input tokens depending on the model and provider.

Models(27)