perplexity
Perplexity: Sonar Pro Search
perplexity/sonar-pro-search
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
perplexity/sonar-pro-search is listed only in the OpenRouter catalog in this source pack; no independent model card was available. OpenRouter describes it as an OpenRouter-exclusive Pro Search mode and an agentic search system aimed at deeper reasoning and analysis. Catalog-reported capabilities include text and image inputs with text output, a listed 200,000-token context window, mandatory reasoning, web-search options, and structured outputs. Measured benchmark results were not included, so treat the capability claims as source-reported rather than validated performance.[1]
Strengths
- Catalog lists text-plus-image input with text output, which may help mixed-modal research prompts.[1]
- A 200,000-token context length is listed, alongside mandatory reasoning and controls such as include_reasoning, max_tokens, temperature, top_p and top_k.[1]
- structured_outputs and web_search_options are listed parameters, suggesting hooks for formatted answers and search-aware requests.[1]
Limitations
- Evidence is catalog-only: no independent model card, eval reports, usage examples or deployment notes were present in this source pack.[1]
- Benchmark fields are empty or null, so measured accuracy, latency, citation quality and reliability still need workload validation.[1]
- knowledgeCutoff and huggingFaceId are null; pricing includes a separate web_search component, so freshness, provenance and cost behavior should be checked before adoption.[1]
Where to use it
- Potentially suitable for search-augmented assistants that need deeper analysis, subject to validating answer quality and web-search costs.[1]
- May fit internal tools that combine image or document prompts with concise text briefings, if multimodal behavior meets requirements in testing.[1]
- Could be evaluated for structured research outputs where JSON-schema responses and search controls matter more than confirmed benchmark leadership.[1]
Sources
- [1] OpenRouter catalog · Perplexity: Sonar Pro SearchSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Specifications
- Model ID
- perplexity/sonar-pro-search
- Creator
- perplexity
- Added to OpenRouter
- 30.10.2025
- Context length
- 200,000
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $3 / out $15
- 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 | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| 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 | 200,000 | $3 | $15 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.