Sonar Deep Research
by Perplexity · Released Mar 2025
Context
128K tokens (~64 books)
Input $/1M
$2.00
Output $/1M
$8.00
Type
text
License
Proprietary
Benchmarks
0 tested
Data as of
About
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
sonar-deep-research
Specifications
- Typetext
- Context128K tokens (~64 books)
- ReleasedMar 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.012
Available On
Learn More
Share & Export
Frequently Asked Questions
Sonar Deep Research is a proprietary text AI model by Perplexity, released in March 2025. Context window: 128K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-10-05
- Sonar Deep Research by Perplexity. Not enough public benchmark scores to rank yet.
- List price $2.00 input · $8.00 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): Perplexity $2.00 in / $8.00 out.
How to cite · data as of 2026-10-05
Sonar Deep Research · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/sonar-deep-research
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP