Standard Sonar model for search-augmented generation.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Standard Sonar model for search-augmented generation. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Sonar on OffRail 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.
Sonar supports a context window of up to 130,000 tokens on its largest provider deployment.
Sonar is served by Perplexity through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Sonar supports strict JSON output schema, but not tool calling.
Sonar was released on January 1, 2025.