​
Overview

Deep Research is an advanced feature of Parallel’s Task API that enables comprehensive web research using natural language inputs. Available with pro and ultra processors, Deep Research transforms simple research queries into structured intelligence reports with comprehensive citations. When using pro and ultra processors, Deep Research automatically converts natural language intent into well-defined structured outputs, producing long-form, structured outputs for the input query. Parallel’s system will interpret the necessary information to retrieve from the web given the user’s intent, with automatically generated schemas.

​
Key Features

  • Advanced Processors With Deep Research we also release three new advanced Processors for the Parallel Task API, including ultra2x, ultra4x and ultra8x. View details on these Processors here.
  • Declarative Approach: Users specify what intelligence they need. Our system handles the complex orchestration of crawling, ranking, retrieval, and reasoning.
  • Auto-Generated Schema: No need to pre-define output structure - the system creates optimal JSON schemas based on your research domain.
  • Structured Intelligence with Verification: Parallel delivers structured outputs with granular calibrated verification built into every response.
Long-Running Tasks: Deep Research can take up to 15 minutes to complete. Use webhooks or server-sent events for real-time updates.

​
Auto Schema

Auto mode in the Task API output schema enables Deep Research functionality by ensuring that the system converts plain text input into well-structured outputs, without the need to specify desired output structure. This expands the available Schema types.
  • Dynamic Structure: The API automatically determines the most appropriate JSON structure for your research topic
  • Comprehensive Coverage: Conducts thorough research to find all relevant information
  • Post-Computed Schema: Output schema is generated after research completion, not before
  • Flexible Fields: Field names and nesting are optimized for the specific domain being researched
Auto schema mode is automatically enabled when using pro and ultra processors.

​
Creating a Deep Research Task

Deep Research accepts a plain-text string as input. The more specific and detailed your input, the better the research results:
Input Size Limit: Deep Research is optimized for concise research prompts and is not meant for long context input. Keep your input under 15,000 characters for optimal performance and results.

​
Sample Request

curl -X POST "https://api.parallel.ai/v1/tasks/runs" \
  -H "x-api-key: PARALLEL_API_KEY" \
  -H 'Content-Type: application/json' \
  --data-raw '{
  "input": "Create a comprehensive market research report on the HVAC industry in the USA including an analysis of recent M&A activity and other relevant details.",
  "processor": "ultra"
}'

​
Sample Response

Important: The response below shows the final completed result after Deep Research has finished. When you first create a task, you’ll receive an immediate response with "status": "running". You’ll need to poll the task or use webhooks to get the final structured research output shown below.
Below is a shortened sample response. The complete response contained 124 content fields, with 610 total citations for this Task. 
{
  "output": {
    "content": {
      "market_size_and_forecast": {
        "cagr": "6.9%",
        "market_segment": "U.S. HVAC Systems",
        "current_valuation": "USD 29.89 billion (2024)",
        "forecasted_valuation": "USD 54.02 billion",
        "forecast_period": "2025-2033"
      },
      "company_profiles": [
        {
          "company_name": "Carrier Global Corporation",
          "stock_ticker": "CARR",
          "revenue": "$22.5 billion (FY2024)",
          "market_capitalization": "$63.698 billion (July 1, 2025)",
          "market_position": "Global leader in intelligent climate and energy solutions",
          "recent_developments": "Acquisition of Viessmann Climate Solutions for $13 billion"
        },
        {
          "company_name": "Daikin Industries, Ltd.",
          "stock_ticker": "DKILY",
          "revenue": "¥4,752.3 billion (FY2024)",
          "market_position": "Japan's leading HVAC manufacturer and top global player",
          "recent_developments": "Multiple acquisitions to strengthen supply capabilities"
        }
      ],
      "recent_mergers_and_acquisitions": {
        "acquiring_company": "Carrier Ventures",
        "target_company": "ZutaCore",
        "deal_summary": "Strategic investment in liquid cooling systems for data centers",
        "date": "February 2025"
      },
      "growth_opportunities": "Data center cooling, building retrofits, electrification, healthcare applications, and enhanced aftermarket services",
      "market_segmentation_analysis": {
        "dominant_segment": "Residential",
        "dominant_segment_share": "39.8% (in 2024)",
        "fastest_growing_segment": "Commercial",
        "fastest_growing_segment_cagr": "7.4% (from 2025 to 2033)"
      },
      "publicly_traded_hvac_companies": [
        {
          "company_name": "Carrier Global Corporation",
          "stock_ticker": "CARR"
        },
        {
          "company_name": "Daikin Industries, Ltd.",
          "stock_ticker": "DKILY"
        },
        {
          "company_name": "Johnson Controls International plc",
          "stock_ticker": "JCI"
        }
      ]
    },
    "basis": [
      {
        "field": "market_size_and_forecast.current_valuation",
        "reasoning": "Market size data sourced from Grand View Research industry analysis report, which provides comprehensive market valuation for the U.S. HVAC systems market in 2024.",
        "citations": [
          {
            "url": "https://www.grandviewresearch.com/industry-analysis/us-hvac-systems-market",
            "excerpts": [
              "The U.S. HVAC systems market size was estimated at USD 29.89 billion in 2024"
            ],
            "title": "U.S. HVAC Systems Market Size, Share & Trends Analysis Report"
          }
        ],
        "confidence": "high"
      },
      {
        "field": "company_profiles.0.revenue",
        "reasoning": "Carrier Global Corporation's 2024 revenue figures are directly reported in their financial communications and investor relations materials.",
        "citations": [
          {
            "url": "https://monexa.ai/blog/carrier-global-corporation-strategic-climate-pivot-CARR-2025-07-02",
            "excerpts": [
              "Carrier reported **2024 revenues of $22.49 billion**, a modest increase of +1.76% year-over-year"
            ],
            "title": "Carrier Global Corporation: Strategic Climate Pivot"
          }
        ],
        "confidence": "high"
      },
      {
        "field": "recent_mergers_and_acquisitions",
        "reasoning": "Carrier Ventures' strategic investment in ZutaCore represents recent M&A activity focused on next-generation cooling technologies for data centers.",
        "citations": [
          {
            "url": "https://finance.yahoo.com/news/10-biggest-hvac-companies-usa-142547989.html",
            "excerpts": [
              "Strategic investment activity by Carrier Ventures in companies specializing in liquid cooling systems"
            ],
            "title": "10 Biggest HVAC Companies in the USA"
          }
        ],
        "confidence": "medium"
      }
    ],
    "run_id": "trun_646e167d826747e1b4690e58d2b9941e",
    "status": "completed",
    "created_at": "2025-01-30T20:12:18.123456Z",
    "completed_at": "2025-01-30T20:25:41.654321Z",
    "processor": "ultra",
    "warnings": null,
    "error": null,
    "taskgroup_id": null
  }
}
Deep Research returns a structured JSON response with an auto-generated schema. The response includes the content and the basis, as with other Task API executions. The key difference is that the basis object in an auto mode output contains Nested FieldBasis.

​
Nested FieldBasis

Deep Research provides granular citations at the field level, allowing for in-place references in report-style outputs. The Basis object maps each output field (including nested fields) with supporting evidence. This ensures that every output, including nested output fields, has citations, excerpts, confidence levels and reasoning. For nested fields, the basis uses slash notation for indexing:
  • key_players.0 for the first item in a key players array
  • industry_overview.growth_cagr for nested object fields
  • market_trends.2.description for nested arrays with objects

​
Example: Market Research Assistant

Here’s how to build a market research tool with Deep Research, showing different approaches for handling the async nature of the Task API: 
from parallel import Parallel

client = Parallel(api_key="PARALLEL_API_KEY")

# Execute research task (handles polling internally)
run_result = client.task_run.execute(
    input="Create a comprehensive market research report on the renewable energy storage market in Europe, focusing on battery technologies and policy impacts",
    processor="ultra"
)

print(f"Research completed! Output has {len(run_result.output.basis)} structured fields")
for field in run_result.output.basis[:3]:
    print(f"- {field.field}: {len(field.citations)} citations")