Perplexity: Sonar Deep Research
perplexity/sonar-deep-research
Sonar Deep Research is a Perplexity model that isn't ranked on the TryAii Score yet — no benchmark results on file. It lists at $2/$8 per million input/output tokens with a 128K-token context. It's reasonably quick at about 52 tokens/sec.
Prompt $/1M
$2.000
Completion $/1M
$8.000
Context
128,000 tok
Best provider
52 tok/s · Perplexity
Specs
- Model id
- perplexity/sonar-deep-research
- Display name
- Perplexity: Sonar Deep Research
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- deepseek-r1
- Context length
- 128,000
- Max completion
- 115,200
- Prompt $/1M
- $2.000
- Completion $/1M
- $8.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Perplexityfastest | 52 |
| perplexityfastest | — |