Atlas / Models / Perplexity / Perplexity: Sonar Deep Research

Perplexity: Sonar Deep Research✓ Catalog verified

perplexity/sonar-deep-research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Input price
$2.00 /1M
Output price
$8.00 /1M
Context
128K
Modalities
text
Released
Mar 7, 2025
Tool calling
Atlas signal
87/100
01

Overview

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Access: available through the official Perplexity API. Context window: 128K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Sep 19, 2026
02

Specifications

API identifierperplexity/sonar-deep-research
ProviderPerplexity
Model typeText LLM
Context window128K catalog
Input modalitiestext
Output modalitiestext
ReleasedMar 7, 2025
Instruction formatdeepseek-r1
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningtemperaturetop_ktop_pweb_search_options
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for perplexity/sonar-deep-research as published in the catalog.

$2.00
Input /1M
$8.00
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$0.000002$2.00 / 1MPer input token
Completion tokens$0.000008$8.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search fee$0.005$0.005000Per search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$2.6Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Perplexity: Sonar Deep Research
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
79signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Perplexity: Sonar Deep Research through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="perplexity/sonar-deep-research",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Perplexity: Sonar Deep Research cost?

$2.00 per 1M input tokens and $8.00 per 1M output tokens on the official Perplexity API.

What is the context window of Perplexity: Sonar Deep Research?

Perplexity: Sonar Deep Research supports up to 128K tokens of context.

Does Perplexity: Sonar Deep Research support tool / function calling?

Perplexity: Sonar Deep Research does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Perplexity: Sonar Deep Research?

Use the official Perplexity API with the model id `perplexity/sonar-deep-research`. See the Quick start section above for code examples.