Perplexity

Sonar

DeprecatedProprietary128K context

Summary

Sonar is a proprietary language model from Perplexity, released on 1 Jan 2024. It accepts text and generates text, with a 128K-token context window and up to 4K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $1 per million input tokens and $1 per million output tokens (OpenRouter), across 2 providers we track. Perplexity has deprecated this model.

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

Last verified 19 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperPerplexity
Release date1 Jan 2024 [models.dev]
StatusDeprecated [models.dev]
WeightsProprietary (API only) [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output4K tokens [models.dev]
Knowledge cutoff1 Sept 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Sonar API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Vercel AI Gateway
perplexity/sonar
$0.25$2.50–127Kmodels.dev, 19 Nov 2026
OpenRouter
perplexity/sonar
$1$1–127KOpenRouter, 19 Nov 2026

Frequently asked questions

What is the context window of Sonar?

Sonar has a context window of 128,000 tokens (128K) and can generate up to 4,096 tokens in a single response, according to models.dev.

How much does the Sonar API cost?

Sonar is listed from $1 per million input tokens and $1 per million output tokens (OpenRouter). Prices last verified 19 Nov 2026.

Is Sonar open source?

No. Sonar is a proprietary model; Perplexity has not released its weights. It is available through APIs including Vercel AI Gateway, OpenRouter.

When was Sonar released?

Perplexity released Sonar on 1 Jan 2024, according to models.dev.

Which providers offer Sonar?

We track Sonar on 2 providers: Vercel AI Gateway, OpenRouter.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GPT-4o miniOpenAI18 Jul 2024128K$0.15$0.60Closed
Mistral LargeMistral AI26 Feb 2024128K$2$6Closed
DeepSeek V3DeepSeek26 Dec 2024128K$0.32$0.89Closed
Qwen PlusAlibaba (Qwen)25 Jan 20241M$0.26$0.78Closed
Claude 3 HaikuAnthropic13 Mar 2024200K––Closed
Qwen Plus Character (Japanese)Alibaba (Qwen)Jan 20248K$0.50$1.40Closed

Change history

  • Status changed from active to deprecated
  • No longer listed on perplexity

Sources