perplexity
Perplexity: Sonar Deep Research
perplexity/sonar-deep-research
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
perplexity/sonar-deep-research is a research-oriented text-to-text model offered by Perplexity via the OpenRouter catalog. According to that listing, it is built for multi-step retrieval, synthesis, and reasoning across complex topics, autonomously searching, reading, and evaluating sources as it goes. The catalog reports a 128,000-token context window and marks reasoning as always on. It lists no benchmark results, and no independent model card was included in this source pack, so the capabilities described here are vendor-reported rather than independently measured.[1]
Strengths
- According to the OpenRouter listing, it targets multi-step research workflows that search, read, and reassess sources iteratively while refining their approach.[1]
- The catalog reports a 128,000-token context window and exposes parameters for web search options and reasoning traces, fitting long-document work.[1]
- Web search and internal reasoning are itemized as separate billing dimensions in the catalog, so retrieval-heavy usage can be tracked distinctly.[1]
Limitations
- All information comes from a single OpenRouter catalog entry; an independent model card was not available in this source pack.[1]
- The listing reports no benchmark results, so quality, speed, and reliability for a given workload remain unverified and need validation on your own tasks.[1]
- Reasoning is marked as mandatory and the model is text-only, so there is no reported way to disable reasoning usage or handle image inputs.[1]
Where to use it
- Editorial suggestion: in-depth research reports or literature reviews that require multi-source synthesis; confirm depth and citation quality on your own topics.[1]
- Editorial suggestion: competitive or market scans where iterative web searching is central, matching the capabilities the catalog describes.[1]
- Editorial suggestion: complex question-answering flows that can benefit from optional reasoning traces exposed through the include_reasoning parameter.[1]
Sources
- [1] OpenRouter catalog · Perplexity: Sonar Deep ResearchSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- perplexity/sonar-deep-research
- Creator
- perplexity
- Added to OpenRouter
- 07.03.2025
- Context length
- 128,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $8
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Perplexity | 128,000 | $2 | $8 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.