# Perplexity Sonar Deep Research

> Perplexity Sonar Deep Research is a proprietary language model from Perplexity, released on 1 Feb 2025. It accepts text and generates text, with a 128K-token context window and up to 33K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $2 per million input tokens and $8 per million output tokens (Perplexity API), across 2 providers we track.

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

## Specifications

- **Developer:** Perplexity
- **Release date:** 1 Feb 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Max output:** 33K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/perplexity/models/sonar-deep-research.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Perplexity API | $2 | $8 | – | 128K |
| OpenRouter | $2 | $8 | – | 128K |

## FAQ

### What is the context window of Perplexity Sonar Deep Research?

Perplexity Sonar Deep Research has a context window of 128,000 tokens (128K) and can generate up to 32,768 tokens in a single response, according to models.dev.

### How much does the Perplexity Sonar Deep Research API cost?

Through Perplexity API, Perplexity Sonar Deep Research costs $2 per million input tokens and $8 per million output tokens. Prices last verified 4 Oct 2026.

### Is Perplexity Sonar Deep Research open source?

No. Perplexity Sonar Deep Research is a proprietary model; Perplexity has not released its weights. It is available through APIs including Perplexity API, OpenRouter.

### When was Perplexity Sonar Deep Research released?

Perplexity released Perplexity Sonar Deep Research on 1 Feb 2025, according to models.dev.

### Which providers offer Perplexity Sonar Deep Research?

We track Perplexity Sonar Deep Research on 2 providers: Perplexity API, OpenRouter.

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