Sonar Deep Research
About this model
Sonar Deep Research is an AI model from Perplexity, made available through the API on March 7, 2025. It can read up to 128,000 tokens in one request, roughly 240 pages of text, and write up to 115,200 tokens in a single answer.
Through the API it costs $2 per million input tokens and $8 per million output tokens. Its pricing sits in the middle of the market.
It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions.
Quality scores
Rankings →Not rated yet. Independent test results usually appear a few weeks after a model is released.
Where to use it
Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call Sonar Deep Research through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "perplexity/sonar-deep-research", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="perplexity/sonar-deep-research",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "perplexity/sonar-deep-research",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$3.40
- Summarise a 100-page document$0.108
- An app with 10,000 requests a day for a month$1,560
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
GPT-6.1 Sol ProOpenAI | $2 | $10 | 1.1M | Compare with ⇄ |
Claude Sonnet 5.5Anthropic | $2 | $10 | 1M | Compare with ⇄ |
Grok 4.7xAI | $2 | $6 | 500K | Compare with ⇄ |
Fugu MaxSakana AI | $2 | $6 | 1M | Compare with ⇄ |
Qwen3.8 Max (0902)Alibaba Qwen | $2 | $6 | 1M | Compare with ⇄ |
Gemini 3.1 Pro Preview Custom ToolsGoogle DeepMind | $2 | $12 | 1M | Compare with ⇄ |
News about Perplexity
See all →Frequently asked questions
- How much does Sonar Deep Research cost?
- Sonar Deep Research costs $2 per million input tokens and $8 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $3.40.
- What is the context window of Sonar Deep Research?
- Sonar Deep Research can read up to 128,000 tokens in one request, about 240 pages of text. It can write up to 115,200 tokens in a single answer.
- Is Sonar Deep Research open source?
- No. Sonar Deep Research is a closed model: its weights are not published, so you use it through Perplexity’s own apps and API, or through cloud providers.
- Who makes Sonar Deep Research?
- Sonar Deep Research is made by Perplexity. It became available through the API on March 7, 2025.
- Can Sonar Deep Research read images?
- No. Sonar Deep Research only accepts text as input.
- What are the alternatives to Sonar Deep Research?
- Models with a similar price from other companies include GPT-6.1 Sol Pro, Claude Sonnet 5.5 and Grok 4.7. You can compare them side by side on this page.