Sonar Deep Research - Perplexity

A powerful research model capable of conducting exhaustive searches, synthesizing expert-level insights, and generating detailed reports.

Model Type: Deep Research / Reasoning
Use Case: Perfect for conducting exhaustive research into topics and generating reports with highly detailed analyses/insights.
Context Length: 128k

Key Features:

Exhaustive research across hundreds of sources
Expert-level subject analysis
Detailed report generation

Real-World Examples:

Writing white papers for industry thought leadership
Crafting highly detailed go-to-market (GTM) plans
Creating educational content for universities or training programs

Pricing

Metric	Cost
Input Tokens (Per Million)	$2
Output Tokens (Per Million)	$8
Citation Tokens (Per Million)	$2
Price per 1000 Search Queries	$5
Reasoning Tokens (Per Million)	$3

Test the Model

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sonar-deep-research",
  "messages": [
    {"role": "user", "content": "Provide an in-depth analysis of the impact of AI on global job markets over the next decade."}
  ],
  "max_tokens": 500
}'

Reasoning Effort Parameter

Control the computational effort dedicated to each query with the reasoning_effort parameter. This allows you to balance between speed and thoroughness while managing costs by directly impacting the amount of reasoning tokens consumed.

Options:

"low": Faster, simpler answers with reduced token usage
"medium": Balanced approach (default)
"high": Deeper, more thorough responses with increased token usage

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'accept: application/json' \
  --header 'Authorization: Bearer <token>' \
  --header 'content-type: application/json' \
  --data '{
    "model": "sonar-deep-research",
    "messages": [{"role": "user", "content": "What should I know before markets open today?"}],
    "stream": true,
    "reasoning_effort": "low"
  }'

Sample Response Metadata

{"id": "8b6b7969-a4ff-488d-a8b9-b3fca3698cce", 
"model": "sonar-deep-research", 
"created": 1747668848, 
"usage": {"prompt_tokens": 19, "completion_tokens": 498, "total_tokens": 517, "citation_tokens": 10175, "num_search_queries": 48, "reasoning_tokens": 95305}, 
"citations": ["https://www.indiatoday.in/technology/news/story/ai-could-shake-up-job-market-by-2030-mckinsey-reveals-list-of-sectors-that-will-be-impacted-2547147-2024-06-02", "https://etradeforall.org/news/future-of-jobs-report-2025-the-jobs-of-the-future-and-the-skills-you-need-to-get-them", "https://www.unleash.ai/future-of-work/pwc-hr-become-an-ai-disruptor-by-being-skills-first/", "https://vorecol.com/blogs/blog-automation-and-the-impact-on-the-workforce-10891", "https://edisonandblack.com/pages/over-97-million-jobs-set-to-be-created-by-ai.html", "https://www.ferolabs.com/insights/post/can-ai-create-manufacturing-jobs", "https://barrychaiken.com/archives/barrypchaiken/2025/04/1005", "https://www.mckinsey.com/featured-insights/future-of-work/jobs-lost-jobs-gained-what-the-future-of-work-will-mean-for-jobs-skills-and-wages", "https://www.marketingaiinstitute.com/blog/ai-impact-on-jobs", "https://www.ilo.org/meetings-and-events/generative-ai-and-jobs-global-analysis-potential-effects-job-quantity-and", "https://www.ilo.org/resource/article/how-reskilling-ai-could-unlock-new-and-better-jobs", "https://opentools.ai/news/ai-impact-unctad-predicts-automation-could-shake-40percent-of-jobs-and-widen-global-disparities", "https://www.mckinsey.com/mgi/our-research/generative-ai-and-the-future-of-work-in-america", "https://cfo.economictimes.indiatimes.com/news/85-of-2030-jobs-yet-to-be-invented-amid-rapid-industry-transformation-dell-report/120375527", "https://news.outsourceaccelerator.com/?p=75453", "https://accesspartnership.com/understanding-how-ai-impacts-jobs-and-skills-in-asean/", "https://mexicobusiness.news/cloudanddata/news/ai-may-impact-38-latin-america-works", "https://www.oecd.org/en/publications/artificial-intelligence-and-wage-inequality_bf98a45c-en.html", "https://www.goldmansachs.com/insights/articles/ai-may-start-to-boost-us-gdp-in-2027"], 
"object": "chat.completion", 
"choices": [{"index": 0, "finish_reason": "length", 
"message": {"role": "assistant", "content": "<think>\nOkay, so the user wants an in-depth analysis of how AI will impact global job markets over the next decade. Let me start by breaking down the query. They\u2019re looking for a comprehensive report, so I need to cover various aspects like job creation, displacement, sector-specific impacts, skills required, and regional differences. \n\nFirst, I should check the search results provided. There are 20 sources here, from McKinsey, World Economic Forum, ILO, Goldman Sachs, etc. Let me skim through them to identify key points. \n\nSource  mentions AI creating 69 million jobs by 2028. Source [1] says McKinsey predicts 12 million occupational transitions by 2030. Source [2] from the World Economic Forum talks about 170 million new jobs this decade. Source [3] from PwC compares AI to the industrial revolution, suggesting job creation might offset losses. Source [4] has conflicting numbers: 800 million jobs displaced but 555 million new ones created. Source [5] says 97 million new jobs by 2025. Source [6] focuses on manufacturing, saying AI can fill 2 million jobs by 2030. Source [7] is about healthcare jobs being both displaced and created. Source [8] from McKinsey again, automation affecting 15% of hours worked globally. Source [9] Brookings says 30% of workers could have half their tasks affected. Source [10] ILO study says AI will augment rather than replace jobs. Source [11] emphasizes reskilling. Source [12] UNCTAD report says 40% of jobs impacted, widening disparities. Source [13] McKinsey on US job shifts. Source [14] Dell report claims 85% of 2030 jobs not invented yet. Source [15] Africa\u2019s tech outsourcing could see 40% task disruption. Source [16] ASEAN skills changing 72% by 2030. Source [17] Latin America 38% jobs impacted. Source [18] OECD on wage inequality. Source [19] Goldman Sachs predicts US GDP boost from AI.\n\nSo, the main themes seem to be: job displacement vs creation, sectoral shifts (healthcare, STEM, manufacturing, administrative), regional differences (developed vs developing nations), skills transformation, and economic impacts like productivity and inequality. \n\nI need to structure the report into sections. Let\u2019s outline possible sections:\n\n1"}, 
"delta": {"role": "assistant", "content": ""}}]}%

Async API

For research-intensive tasks that may take longer to process, you can use the async API. This allows you to submit a request and retrieve the results later.

curl --location 'https://api.perplexity.ai/async/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
  "request": {
    "model": "sonar-deep-research",
    "messages": [
      {
        "role": "user",
        "content": "Provide an in-depth analysis of the impact of AI on global job markets over the next decade."
      }
    ]
  }
}'

Sample Response (Request Submission)

{
  "id": "784312ac-b8fd-405f-99fa-9bcbf48865bb",
  "model": "sonar-deep-research",
  "created_at": 1748565663,
  "started_at": null,
  "completed_at": null,
  "response": null,
  "failed_at": null,
  "error_message": null,
  "status": "CREATED"
}

curl --location 'https://api.perplexity.ai/async/chat/completions/784312ac-b8fd-405f-99fa-9bcbf48865bb' \
--header 'Authorization: Bearer <token>'

Async requests have a time-to-live (TTL) of 7 days. After this period, the request and its results will no longer be accessible.

A powerful research model capable of conducting exhaustive searches, synthesizing expert-level insights, and generating detailed reports.

Model Type: Deep Research / Reasoning
Use Case: Perfect for conducting exhaustive research into topics and generating reports with highly detailed analyses/insights.
Context Length: 128k

Key Features:

Exhaustive research across hundreds of sources
Expert-level subject analysis
Detailed report generation

Real-World Examples:

Writing white papers for industry thought leadership
Crafting highly detailed go-to-market (GTM) plans
Creating educational content for universities or training programs

Pricing

Metric	Cost
Input Tokens (Per Million)	$2
Output Tokens (Per Million)	$8
Citation Tokens (Per Million)	$2
Price per 1000 Search Queries	$5
Reasoning Tokens (Per Million)	$3

Test the Model

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sonar-deep-research",
  "messages": [
    {"role": "user", "content": "Provide an in-depth analysis of the impact of AI on global job markets over the next decade."}
  ],
  "max_tokens": 500
}'

Reasoning Effort Parameter

Options:

"low": Faster, simpler answers with reduced token usage
"medium": Balanced approach (default)
"high": Deeper, more thorough responses with increased token usage

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'accept: application/json' \
  --header 'Authorization: Bearer <token>' \
  --header 'content-type: application/json' \
  --data '{
    "model": "sonar-deep-research",
    "messages": [{"role": "user", "content": "What should I know before markets open today?"}],
    "stream": true,
    "reasoning_effort": "low"
  }'

Sample Response Metadata

{"id": "8b6b7969-a4ff-488d-a8b9-b3fca3698cce", 
"model": "sonar-deep-research", 
"created": 1747668848, 
"usage": {"prompt_tokens": 19, "completion_tokens": 498, "total_tokens": 517, "citation_tokens": 10175, "num_search_queries": 48, "reasoning_tokens": 95305}, 
"citations": ["https://www.indiatoday.in/technology/news/story/ai-could-shake-up-job-market-by-2030-mckinsey-reveals-list-of-sectors-that-will-be-impacted-2547147-2024-06-02", "https://etradeforall.org/news/future-of-jobs-report-2025-the-jobs-of-the-future-and-the-skills-you-need-to-get-them", "https://www.unleash.ai/future-of-work/pwc-hr-become-an-ai-disruptor-by-being-skills-first/", "https://vorecol.com/blogs/blog-automation-and-the-impact-on-the-workforce-10891", "https://edisonandblack.com/pages/over-97-million-jobs-set-to-be-created-by-ai.html", "https://www.ferolabs.com/insights/post/can-ai-create-manufacturing-jobs", "https://barrychaiken.com/archives/barrypchaiken/2025/04/1005", "https://www.mckinsey.com/featured-insights/future-of-work/jobs-lost-jobs-gained-what-the-future-of-work-will-mean-for-jobs-skills-and-wages", "https://www.marketingaiinstitute.com/blog/ai-impact-on-jobs", "https://www.ilo.org/meetings-and-events/generative-ai-and-jobs-global-analysis-potential-effects-job-quantity-and", "https://www.ilo.org/resource/article/how-reskilling-ai-could-unlock-new-and-better-jobs", "https://opentools.ai/news/ai-impact-unctad-predicts-automation-could-shake-40percent-of-jobs-and-widen-global-disparities", "https://www.mckinsey.com/mgi/our-research/generative-ai-and-the-future-of-work-in-america", "https://cfo.economictimes.indiatimes.com/news/85-of-2030-jobs-yet-to-be-invented-amid-rapid-industry-transformation-dell-report/120375527", "https://news.outsourceaccelerator.com/?p=75453", "https://accesspartnership.com/understanding-how-ai-impacts-jobs-and-skills-in-asean/", "https://mexicobusiness.news/cloudanddata/news/ai-may-impact-38-latin-america-works", "https://www.oecd.org/en/publications/artificial-intelligence-and-wage-inequality_bf98a45c-en.html", "https://www.goldmansachs.com/insights/articles/ai-may-start-to-boost-us-gdp-in-2027"], 
"object": "chat.completion", 
"choices": [{"index": 0, "finish_reason": "length", 
"message": {"role": "assistant", "content": "<think>\nOkay, so the user wants an in-depth analysis of how AI will impact global job markets over the next decade. Let me start by breaking down the query. They\u2019re looking for a comprehensive report, so I need to cover various aspects like job creation, displacement, sector-specific impacts, skills required, and regional differences. \n\nFirst, I should check the search results provided. There are 20 sources here, from McKinsey, World Economic Forum, ILO, Goldman Sachs, etc. Let me skim through them to identify key points. \n\nSource  mentions AI creating 69 million jobs by 2028. Source [1] says McKinsey predicts 12 million occupational transitions by 2030. Source [2] from the World Economic Forum talks about 170 million new jobs this decade. Source [3] from PwC compares AI to the industrial revolution, suggesting job creation might offset losses. Source [4] has conflicting numbers: 800 million jobs displaced but 555 million new ones created. Source [5] says 97 million new jobs by 2025. Source [6] focuses on manufacturing, saying AI can fill 2 million jobs by 2030. Source [7] is about healthcare jobs being both displaced and created. Source [8] from McKinsey again, automation affecting 15% of hours worked globally. Source [9] Brookings says 30% of workers could have half their tasks affected. Source [10] ILO study says AI will augment rather than replace jobs. Source [11] emphasizes reskilling. Source [12] UNCTAD report says 40% of jobs impacted, widening disparities. Source [13] McKinsey on US job shifts. Source [14] Dell report claims 85% of 2030 jobs not invented yet. Source [15] Africa\u2019s tech outsourcing could see 40% task disruption. Source [16] ASEAN skills changing 72% by 2030. Source [17] Latin America 38% jobs impacted. Source [18] OECD on wage inequality. Source [19] Goldman Sachs predicts US GDP boost from AI.\n\nSo, the main themes seem to be: job displacement vs creation, sectoral shifts (healthcare, STEM, manufacturing, administrative), regional differences (developed vs developing nations), skills transformation, and economic impacts like productivity and inequality. \n\nI need to structure the report into sections. Let\u2019s outline possible sections:\n\n1"}, 
"delta": {"role": "assistant", "content": ""}}]}%

Async API

For research-intensive tasks that may take longer to process, you can use the async API. This allows you to submit a request and retrieve the results later.

curl --location 'https://api.perplexity.ai/async/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
  "request": {
    "model": "sonar-deep-research",
    "messages": [
      {
        "role": "user",
        "content": "Provide an in-depth analysis of the impact of AI on global job markets over the next decade."
      }
    ]
  }
}'

Sample Response (Request Submission)

{
  "id": "784312ac-b8fd-405f-99fa-9bcbf48865bb",
  "model": "sonar-deep-research",
  "created_at": 1748565663,
  "started_at": null,
  "completed_at": null,
  "response": null,
  "failed_at": null,
  "error_message": null,
  "status": "CREATED"
}

curl --location 'https://api.perplexity.ai/async/chat/completions/784312ac-b8fd-405f-99fa-9bcbf48865bb' \
--header 'Authorization: Bearer <token>'

Async requests have a time-to-live (TTL) of 7 days. After this period, the request and its results will no longer be accessible.

​Pricing

​Test the Model

​Reasoning Effort Parameter

​Async API

Discussions

​Pricing

​Test the Model

​Reasoning Effort Parameter

​Async API

Pricing

Test the Model

Reasoning Effort Parameter

Async API

Pricing

Test the Model

Reasoning Effort Parameter

Async API