Perplexity: Sonar Deep Research

Sonar search model for autonomous research and citation-backed long-form reports

Model lab: Perplexity
Model family: sonar

Modalitiestext → text

Context window128,000

Maximum output32,768

InputUSD 1.6 / 1M tokens

OutputUSD 6.4 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to perplexity/sonar-deep-research.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "perplexity/sonar-deep-research"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Sonar Deep Research API Pricing

Type	Price information
Input	USD 1.6 / 1M tokens
Output	USD 6.4 / 1M tokens
Reasoning	USD 2.4 / 1M tokens

Performance

Performance trends

Throughput90.4 tok/sCurrent

Time to first token1.5 sCurrent

End-to-end latency6.9 sCurrent

Throughput

Current90.4 tok/s

Window average89.9 tok/s

Time to first token

Current1.5 s

Window average1.5 s

End-to-end latency

Current6.9 s

Window average7.5 s

Tail latency (P99)

Current17.9 s

Window average17.4 s

Prompt cache hit rate

Current19.3%

Window average24.5%

Error rate

Current2.1%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Sonar Deep Research Compare models

Model	Input price	Output price	Context window	Capabilities
Sonar Deep ResearchThis page	USD 1.6 / 1M tokens	USD 6.4 / 1M tokens	128,000	Text output · Reasoning
Sonar	USD 0.8 / 1M tokens	USD 0.8 / 1M tokens	128,000	Text output
Beam 1.0 501B A23B	USD 0.2 / 1M tokens	USD 0.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Ling 3.1 Flash	USD 0.06 / 1M tokens	USD 0.176 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Schematron V2 Small	USD 0.04 / 1M tokens	USD 0.184 / 1M tokens	128,000	Text output

Model specifications

Input: text
Output: text
Context window: 128,000
Maximum output: 32,768
Release date: 2025-02-01
Attachments: No
Reasoning: Yes
Tool calling: No
Temperature setting: No
Open weights: No

Frequently asked questions

What is Sonar Deep Research for?

Sonar search model for autonomous research and citation-backed long-form reports

What inputs and outputs does Sonar Deep Research support?

Recorded inputs: text; outputs: text.

How is Sonar Deep Research priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 1.6 / 1M tokens; Output USD 6.4 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Sonar Deep Research?

Current model records list Context window 128,000 tokens; Maximum output 32,768 tokens.

What model parameter does the Quickstart use?

The example uses perplexity/sonar-deep-research. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.