LLM Reference
OpenRouter

Sonar on OpenRouter

Sonar · Perplexity Labs

Serverless

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Sonar on OpenRouter?

OpenRouter offers Sonar with pay-as-you-go pricing at $1.00/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Compare Sonar across 3 providers to find the best fit for your use case
Input / 1M
$1.00
Output / 1M
$1.00
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: perplexity/sonar
Model ID
perplexity/sonar

Request example

Curated snippets for this provider are not sourced yet. Use OpenRouter documentation with model ID perplexity/sonar.

Gotchas

  • Use provider model ID "perplexity/sonar", not the LLMReference slug "sonar".

Compare Sonar Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenRouter$1.00$1.00
Perplexity Labs$1.00$1.00
Vercel AI Gateway

Pricing

TypePrice (per 1M)
Input tokens$1.00
Output tokens$1.00

Capabilities

Structured Outputs

About Sonar

Lightweight, cost-effective Perplexity search model with grounding and citations. Request fees: $5-$12/1K requests depending on search context depth (Low/Medium/High).

FAQ

What does Sonar cost on OpenRouter?

On OpenRouter, Sonar costs $1 per 1M input tokens and $1 per 1M output tokens.

What is the context window for Sonar on OpenRouter?

Sonar supports a 127k token context window on OpenRouter.

How does OpenRouter compare to other Sonar providers?

Sonar is available from 3 providers. The cheapest input pricing is $1/1M tokens from OpenRouter.

What API model ID do I use for Sonar on OpenRouter?

Use the model ID perplexity/sonar when calling OpenRouter's API.

Who created Sonar?

Sonar was created by Perplexity Labs as part of the Sonar model family.

Is Sonar open source?

Sonar is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2025-01-27
Context127k
ArchitectureDecoder Only