perplexity
Perplexity: Sonar
perplexity/sonar
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
perplexity/sonar is a Perplexity model listed in the OpenRouter catalog for text output from text and image inputs. The catalog describes it as lightweight, affordable, fast, and simple to use, with citations and customizable sources for question-and-answer integrations; these are source-reported traits rather than independently measured performance. Its listed context length is 127,072 tokens, and it exposes a web_search_options parameter. The supplied evidence is catalog-only, so production use should be validated on representative workloads.[1]
Strengths
- OpenRouter describes it as a lightweight, affordable, fast, and simple model for integrated question-answering features.[1]
- It accepts text and image inputs, produces text, and has a listed context length of 127,072 tokens.[1]
- The catalog reports citation support, customizable sources, and a web_search_options parameter.[1]
Limitations
- Only OpenRouter catalog evidence was supplied; an independent model card was not available in this source pack.[1]
- No benchmark results were provided, so quality, speed, cost, citation behavior, and image handling need workload-specific validation.[1]
- The catalog does not specify a knowledge cutoff or list reasoning support; neither should be assumed.[1]
Where to use it
- Potentially suitable for lightweight question-and-answer products where citations and source controls are useful.[1]
- Could be evaluated for text responses to prompts that combine text with image inputs.[1]
- May fit search-assisted drafting or support workflows, subject to testing its retrieval and citation behavior.[1]
Sources
- [1] OpenRouter catalog · Perplexity: SonarSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Specifications
- Model ID
- perplexity/sonar
- Creator
- perplexity
- Added to OpenRouter
- 27.01.2025
- Context length
- 127,072
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1 / out $1
- 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 | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| 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 | 127,072 | $1 | $1 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.