Finance Search

Retrieve structured financial and market data in the Agent API.

Overview

finance_search lets the model pull structured financial and market data for public companies, ETFs, and related instruments. The model decides which fields to fetch based on your prompt.

Use it when one answer needs more than one type of financial data, such as valuation, earnings, and context for the same company or list of companies.

Capabilities

Data area	What it includes
Company basics	Quotes, profiles, peers, and market metadata
Financials	Income statement, balance sheet, cash flow (quarterly and annual), key ratios
Valuation and pricing	Current/near-real-time pricing, 1-minute to 1-month OHLCV ranges, pre-market and after-hours data
Earnings	Last earnings call transcript, report filings, beat/miss history, guidance discussion
Segment and KPI tracking	Revenue/profit by segment, geography, ARPU, subscriber counts, GMV, and other operating metrics
Analyst coverage	Forward revenue and EPS estimates, cover count, historical estimate changes
Market activity	Top gainers, top losers, and most active symbols
Ownership and corporate actions	Insider activity, ticker-level metadata, splits, and related market events
ETF and index details	Top constituents, shares, weights, and market values

Coverage

finance_search coverage depends on the symbol, exchange, asset class, geography, and source data availability.

Coverage area	Current guidance
Ticker and symbol coverage	Publicly traded companies, ETFs, and related instruments when a supported symbol can be resolved.
Asset classes	Public equities and ETFs.

Market data may be delayed, incomplete, or unavailable for some symbols. finance_search is for informational use only and does not provide investment, legal, tax, or financial advice.

Quickstart

Add finance_search to the tools array. When you use model or models without an effort level, set max_steps to at least 3. If you omit it, the direct-model default is 1 step, which does not leave enough room to initialize and run finance_search.

Python

from perplexity import Perplexity

client = Perplexity()

response = client.responses.create(
    model="openai/gpt-5.6-sol",
    input="What's NVIDIA trading at right now, and what is its current P/E?",
    tools=[
        {"type": "web_search"},
        {"type": "finance_search"}
    ],
    max_steps=3
)

for item in response.output:
    if item.type == "message":
        print(item.content[0].text)

Response

{
  "completed_at": 1777644610,
  "created_at": 1777644610,
  "error": null,
  "id": "resp_d0476d0f-872d-492a-907e-1daa48eb9e32",
  "model": "openai/gpt-5.6-sol",
  "object": "response",
  "output": [
    {
      "categories": ["quote"],
      "results": [
        {
          "category": "quote",
          "content": "## NVDA Quote\nQuote field guide: `price` is the latest quote/current price...\n| symbol | name | timestamp | market_status | price | currency | change | changesPercentage | marketCap | pe | eps | volume | dayLow | dayHigh | yearLow | yearHigh | previousClose | open |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| NVDA | NVIDIA Corporation | 2026-05-01 14:10:07 UTC | open | 200.23 | USD | 0.66 | 0.33 | 4,866,492,706,948 | 40.86 | 4.90 | 28,725,330 | 199.15 | 203 | 110.82 | 216.83 | 199.57 | 201.28 |",
          "sources": [
            "https://www.perplexity.ai/finance/NVDA/historical-data",
            "https://www.perplexity.ai/finance/NVDA"
          ],
          "tickers": ["NVDA"]
        }
      ],
      "tickers": ["NVDA"],
      "type": "finance_results"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "NVIDIA (NVDA) is currently trading at **$200.23** per share, and its current P/E ratio is **40.86**.",
          "type": "output_text"
        }
      ],
      "id": "msg_b188058f-8225-4642-90e6-da7112f96b69",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed",
  "usage": {
    "cost": {
      "currency": "USD",
      "input_cost": 0.03028,
      "output_cost": 0.00126,
      "tool_calls_cost": 0.005,
      "total_cost": 0.03654
    },
    "input_tokens": 7570,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 63,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "tool_calls_details": {
      "finance_search": {
        "invocation": 1
      }
    },
    "total_tokens": 7633
  }
}

Example Prompts

• Full company brief: “Give me a complete NVIDIA snapshot: valuation, segment revenue for the latest quarter, and management’s latest commentary on margins guidance.”
• Compare companies in one request: “Compare Apple, Microsoft, and Alphabet on revenue growth, operating margin, and forward P/E for the latest fiscal year.”
• Earnings + reaction context: “Summarize Tesla’s last earnings call, include actual vs consensus, and describe how the stock and analyst targets moved after publication.”

Prompt Guidance

finance_search works best when the prompt states the outcome, not the data shape.

• Start with the business question first, then include the company or ticker.
• Add time windows when relevant (latest quarter, fiscal year to date, last 30 days).
• Let the tool decide which specific report fields to retrieve.

Recommended Configurations

Start with the configuration that matches the shape of the finance question.

Configuration	Best for	Latency	Quality	Cost
Live Market Data and Quotes	Real-time prices, quotes, and latest figures	Fast	Good	Low
Single-Company Historical Lookups	Basic historical financials for one company or ticker	Balanced	High	Medium
Multi-Step Financial Research	Cross-company comparisons and complex financial analysis	Thorough	Highest	High

Live Market Data and Quotes

Use this for time-sensitive answers that depend on real-time prices, quotes, or the latest market figures. It is the cheapest and fastest option while maintaining strong quality for live data lookups.

Python

from perplexity import Perplexity

client = Perplexity()

response = client.responses.create(
    model="openai/gpt-5.6-sol",
    input="What is Apple's most recent annual revenue, and what segments contributed most to year-over-year growth?",
    tools=[{"type": "finance_search"}],
    max_steps=3,
    max_output_tokens=1024
)

for item in response.output:
    if item.type == "message":
        print(item.content[0].text)

Response

{
  "id": "4a4fa036-b206-44db-91d1-e0d7cf8f8b1e",
  "results": [
    {
      "snippet": "It has also built out its subscription services to include music and video streaming, video games, fitness and cloud storage.\nThis segment alone generated $53 billion revenue in 2020, making it...",
      "title": "Apple Statistics (2026) - Business of Apps",
      "url": "https://www.businessofapps.com/data/apple-statistics/",
      "date": "2026-02-26",
      "last_updated": "2025-09-02"
    },
    {
      "snippet": "",
      "title": "Investor Relations - Apple",
      "url": "https://investor.apple.com/investor-relations/default.aspx",
      "date": null,
      "last_updated": "2026-04-17"
    },
    {
      "snippet": "In fiscal year 2025, Apple's revenue by segment (products & services) are as follows:\n**iPad:**$28.02 B **iPhone:**$209.59 B **Mac:**$33.71 B **Service:**$109.16 B **Wearables, Home and...",
      "title": "Apple Revenue Breakdown By Segment | Bullfincher",
      "url": "http://bullfincher.io/companies/apple/revenue-by-segment",
      "date": "2025-01-01",
      "last_updated": "2026-04-30"
    }
  ],
  "server_time": null
}

Single-Company Historical Lookups

Use this for a single company’s historical figures or basic questions that benefit from both structured finance data and web context. GPT-5.5 is strong at simple web search and token-efficient for historical lookups.

Python

from perplexity import Perplexity

client = Perplexity()

response = client.responses.create(
    model="openai/gpt-5.6-sol",
    input="What was Microsoft's total revenue in its most recently completed fiscal year, and how did it compare with the prior fiscal year according to Microsoft's annual report?",
    tools=[
        {"type": "web_search"},
        {"type": "finance_search"},
        {"type": "fetch_url"}
    ],
    max_steps=5,
    max_output_tokens=2048,
    reasoning={"effort": "low"}
)

for item in response.output:
    if item.type == "message":
        print(item.content[0].text)

Response

{
  "id": "resp_1be7ab7e-0dda-4949-9578-1462f9557a6b",
  "object": "response",
  "model": "openai/gpt-5.6-sol",
  "status": "completed",
  "created_at": 1777645563,
  "completed_at": 1777645563,
  "output": [
    {
      "type": "finance_results",
      "categories": ["financials"],
      "tickers": ["MSFT"],
      "results": [
        {
          "category": "financials",
          "tickers": ["MSFT"],
          "content": "## MSFT FY 2024\n| date | period | income_statement_total_revenues |\n| --- | --- | --- |\n| 2024-06-30 | 2024 FY | 245,122,000,000 |",
          "sources": [
            "https://www.perplexity.ai/finance/MSFT/financials?period=annual&category=INCOME_STATEMENT&fromYear=2024&toYear=2024"
          ]
        }
      ]
    },
    {
      "type": "finance_results",
      "categories": ["financials"],
      "tickers": ["MSFT"],
      "results": [
        {
          "category": "financials",
          "tickers": ["MSFT"],
          "content": "## MSFT FY 2025\n| date | period | income_statement_total_revenues |\n| --- | --- | --- |\n| 2025-06-30 | 2025 FY | 281,724,000,000 |",
          "sources": [
            "https://www.perplexity.ai/finance/MSFT/financials?period=annual&category=INCOME_STATEMENT&fromYear=2025&toYear=2025"
          ]
        }
      ]
    },
    {
      "type": "message",
      "id": "msg_99ccfbfd-bce8-4b9b-b412-b01ef45c7842",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Microsoft's revenue in its last completed fiscal year, **FY2025 ended June 30, 2025**, was **$281.724 billion**.\n\nCompared with the prior year, **FY2024 revenue was $245.122 billion**, so Microsoft revenue increased by:\n\n- **$36.602 billion**\n- **About 14.9% year over year**",
          "annotations": [],
          "logprobs": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 12522,
    "input_tokens_details": {
      "cached_tokens": 3840,
      "cache_read_input_tokens": 3840
    },
    "output_tokens": 500,
    "total_tokens": 13022,
    "cost": {
      "currency": "USD",
      "input_cost": 0.03473,
      "cache_read_cost": 0.00154,
      "output_cost": 0.01,
      "tool_calls_cost": 0.01,
      "total_cost": 0.05627
    },
    "tool_calls_details": {
      "finance_search": {
        "invocation": 2
      }
    }
  }
}

Multi-Step Financial Research

Use this for cross-company comparisons, longer historical investigations, and analysis that needs several tool calls across financial statements, filings, transcripts, and web sources. Opus performs best on complex multi-step reasoning when paired with the full tool suite.

Python

from perplexity import Perplexity

client = Perplexity()

response = client.responses.create(
    model="anthropic/claude-opus-5-5",
    input="Compare Apple, Microsoft, and Alphabet on revenue growth and operating margin trends over the last three fiscal years using their 10-K filings.",
    tools=[
        {"type": "web_search"},
        {"type": "finance_search"},
        {"type": "fetch_url"}
    ],
    max_steps=10,
    max_output_tokens=4096
)

for item in response.output:
    if item.type == "message":
        print(item.content[0].text)

Response

{
  "id": "fd226107-fb5a-4f0d-a9da-0db62b67ec60",
  "results": [
    {
      "snippet": "",
      "title": "Microsoft Annual Report 2025",
      "url": "https://www.microsoft.com/investor/reports/ar25/index.html",
      "date": "2020-06-30",
      "last_updated": "2026-05-18"
    },
    {
      "snippet": "",
      "title": "10-K - SEC.gov",
      "url": "https://www.sec.gov/Archives/edgar/data/789019/000095017024087843/msft-20240630.htm",
      "date": "2009-05-15",
      "last_updated": "2025-07-11"
    },
    {
      "snippet": "",
      "title": "Investor Relations - Apple",
      "url": "https://investor.apple.com/investor-relations/default.aspx",
      "date": null,
      "last_updated": "2026-04-17"
    }
  ],
  "server_time": null
}

Parameters

Parameter	Type	Required	Description
type	string	Yes	Must be "finance_search".

Response Shape

When finance_search runs, the response can include finance_results output items before the final assistant message. Each finance_results item includes the requested finance categories, ticker symbols, structured content, and source URLs when available. The final usage object includes token counts, cost details, and tool_calls_details.finance_search.invocation when tool-call usage is reported.

{
  "output": [
    {
      "type": "finance_results",
      "categories": ["quote"],
      "tickers": ["NVDA"],
      "results": [
        {
          "category": "quote",
          "tickers": ["NVDA"],
          "content": "Structured quote data returned by the finance search tool.",
          "sources": [
            "https://www.perplexity.ai/finance/NVDA"
          ]
        }
      ]
    },
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The answer generated from finance data."
        }
      ]
    }
  ],
  "usage": {
    "tool_calls_details": {
      "finance_search": {
        "invocation": 1
      }
    }
  }
}

Pricing

finance_search is billed at $5 per 1,000 invocations. Model token usage is billed separately according to Agent API token pricing.

Pricing follows the same pattern as other tool calls: pay for invocations plus model tokens. See Pricing.

Limits / Quotas

finance_search uses the same Agent API request flow as other tools. Limits depend on your account tier, request configuration, and the number of tool invocations needed to answer the prompt. See Rate Limits & Usage Tiers for tier-based request and token limits.

Limit area	What to expect
API rate limits	Agent API rate limits apply to requests that use finance_search.
Tool invocations	Each time the model calls finance_search, it counts as one billable tool invocation. Multi-company or multi-step prompts may require more than one invocation.
Step limits	With a direct model, set max_steps to at least 3 so finance_search can initialize and run. Use a higher value for multi-step requests that combine it with tools such as web_search and fetch_url.
Output limits	Large comparisons, long transcripts, and multi-year financial tables can hit max_output_tokens or response truncation settings.
Coverage limits	Some symbols, exchanges, regions, asset classes, or fields may be unavailable depending on source coverage and data freshness.

Next Steps

Web Search

Search the web for source-grounded context.

Fetch URL Content

Fetch full content from known URLs.

People Search

Search for professionals and employees.

Agent API Quickstart

Get started with the Agent API.