Sonar Deep Research

perplexity/sonar-deep-research

Perplexity: Sonar Deep Research, released by Perplexity on 2025-01-27, processes text input and generates text output with a context window of 128 000 tokens. The model supports reasoning, does not support tools, is not open‑weights, and costs $2 per million input tokens and $8 per million output tokens.

  • reasoning

At a glance

providerperplexity
releasedJan 27, 2025
context128K
input / M$2

Specifications

What the API gives you

Context window
128K tokens
Max output
Input price
$2 / 1M tokens
Output price
$8 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Released
Jan 27, 2025

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.

Benchmarks

No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.