Sonar Deep Research
Perplexity released 2025-03-07
No independent quality score.
No benchmark we track has measured this model. That is not the same as measuring it and finding it wanting — we simply cannot rank it, so we do not.
Every price dimension
| Input | $2.00/M |
|---|---|
| Output | $8.00/M |
| Reasoning | $3.00/M |
| Web search | $0.005/call |
Reasoning tokens are billed separately at $3.00/M, on top of output. On a reasoning-heavy workload this can be 40% of the bill and it does not appear in the advertised price.
Independent scores
No independent benchmark has measured this model.
Capability
| Context window | 128K |
|---|---|
| Input modes | text |
| Tool use | no |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | unrated |
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...