← Model list
Perplexity Sonar Deep Research
perplexity·perplexity/sonar-deep-research-3·GA·Closed·sonar-deep-research series
Sonar search model for current answers, retrieval, and citation-backed chat
At a glance
Official price$2.00 / $8.00 per 1M
Cache read — · Perplexity
Lowest paid$2.00 / $8.00
Perplexity First-party · 1× spread
Context128,000
⚠ Providers report 127,000–128,000; the table below is authoritative
Output limit32,768
Capabilities
✓ ReasoningTool useStructured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff2025-01
Released / updated2025-02-01 / 2025-09-01
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 3 providers3 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| PerplexityOfficial sonar-deep-research | First-party | $2.00 | $8.00 | — | — | 128,000 | 32,768 | |
| Helicone sonar-deep-research | Gateway | $2.00 | $8.00 | — | — | 127,000 ⚠ | 4,096 | |
| Kilo Gateway perplexity/sonar-deep-research | Gateway | $2.00 | $8.00 | — | — | 128,000 | 25,600 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Perplexity · Official$800.00
2Helicone$800.00
3Kilo Gateway$800.00
The cheapest paid channel is official.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = minimaleffort = loweffort = mediumeffort = higheffort = none
Related models
GPT OSS 120Bcheaper alternative$1.00 / $4.20Kimi K2.6cheaper alternative$0.95 / $4.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended