# Sonar

> 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 4 Oct 2026, the lowest listed API price is $1 per million input tokens and $1 per million output tokens (Perplexity API), across 3 providers we track.

Source page: https://www.aimodel.directory/models/sonar
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Perplexity
- **Release date:** 1 Jan 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Knowledge cutoff:** 1 Sept 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Vercel AI Gateway | $0.25 | $2.50 | – | 127K |
| Perplexity API | $1 | $1 | – | 128K |
| OpenRouter | $1 | $1 | – | 127K |

## FAQ

### 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?

Through Perplexity API, Sonar costs $1 per million input tokens and $1 per million output tokens. Prices last verified 4 Oct 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, Perplexity API, OpenRouter.

### When was Sonar released?

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

### Which providers offer Sonar?

We track Sonar on 3 providers: Vercel AI Gateway, Perplexity API, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Sonar", https://www.aimodel.directory/models/sonar