Sonar

Standard Sonar model for search-augmented generation.

130,000 context
Released January 1, 2025
Starting at $1.00/M input tokens
Starting at $1.00/M output tokens
Streaming
No ratings yetSign in to rate

Select Provider

All Providers for Sonar

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Perplexity
Context: 130k
Input
$1
/M tokens
Cache Read
/M tokens
Output
$1
/M tokens
+ $0.005 per request
Get Started

Frequently asked questions

What is Sonar?

Standard Sonar model for search-augmented generation. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Sonar cost?

Pricing for Sonar on LLM Gateway starts at $1.00 per million input tokens and $1.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Sonar?

Sonar supports a context window of up to 130,000 tokens on its largest provider deployment.

Which providers serve Sonar?

Sonar is served by Perplexity through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Sonar support tool calling and structured outputs?

Sonar supports structured JSON outputs, but not tool calling.

When was Sonar released?

Sonar was released on January 1, 2025.