We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Perplexity: Sonar Deep Research
perplexity/sonar-deep-researchTry Perplexity: Sonar Deep Research now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Perplexity: Sonar Deep Research at a glance
- Input price is 344% higher than the median of 434 Text models.
- Context window of 128,000 tokens, enough for long documents and multi-turn conversations.
- Supports reasoning effort control.
- A typical request (1,000 input / 500 output tokens) costs about $0.02.
About Perplexity: Sonar Deep Research
Perplexity: Sonar Deep Research is a research-focused text model from Perplexity, the company behind the Sonar family of search-grounded models. It was released by the provider on 7 March 2025. It is aimed at complex, multi-step research work rather than quick conversational replies, and it sits in the text category on api14, so it is intended for reading and writing text rather than for images or audio.
The model works by running multi-step retrieval, synthesis, and reasoning across a topic. Rather than answering from a single pass, it autonomously searches, reads, and evaluates sources, and refines its approach as it gathers material. It accepts text as input and returns text as output. The context window is 128,000 tokens, and the maximum output is 115,200 tokens, which leaves plenty of room for long, source-heavy reports.
Those capabilities point to a fairly specific set of uses. It suits questions that need evidence pulled from several places and then combined into one coherent answer: literature and market scans, background research on a company or technology, comparing positions across sources, and drafting long briefs where the reasoning has to be laid out. Because the model reads and weighs sources as part of the run, it is a reasonable fit when you want a written synthesis rather than a single factual lookup.
You call it through api14 using the OpenAI-compatible API with the model id "perplexity/sonar-deep-research". The request parameters it supports are frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, temperature, top_k, top_p, and web_search_options. Because the interface is OpenAI-compatible, you can point an existing OpenAI client at api14 and set the model to this id. The reasoning and include_reasoning parameters let you surface the model's reasoning output if you want it, and web_search_options gives you control over the retrieval side of the run.
Keep its focus in mind when you pick it. It is a research and synthesis model, so for low-latency chat, simple extraction, or high-volume classification, a lighter text model will usually be the better choice. If you need image or audio input, this model is not the one, since it only handles text.
How to call the Perplexity: Sonar Deep Research API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "perplexity/sonar-deep-research".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "perplexity/sonar-deep-research",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningtemperaturetop_ktop_pweb_search_optionsSpecifications
- Context length
- 128,000
- Max output
- 115,200
- Input
- text
- Output
- text
Requests on api14 · last 7 days
Perplexity: Sonar Deep Research: frequently asked questions
- How much does the Perplexity: Sonar Deep Research API cost?
- Perplexity: Sonar Deep Research costs Input $7.00 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Perplexity: Sonar Deep Research?
- Perplexity: Sonar Deep Research reads up to 128,000 tokens per request: prompt, history and documents together. It writes up to 115,200 output tokens per response.
- What can Perplexity: Sonar Deep Research do?
- Perplexity: Sonar Deep Research accepts text and returns text. It supports reasoning effort control.
- How do I call Perplexity: Sonar Deep Research from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "perplexity/sonar-deep-research". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Perplexity: Sonar Deep Research?
- Comparable Text models at a similar price: Pareto 26.9, OpenAI: o3, OpenAI: GPT-4.1. Each runs through the same API key, so switching is one string.
Perplexity: Sonar Deep Research community
New topicThis community has no topics yet. Open the first one about Perplexity: Sonar Deep Research.