Perplexity: finance_search Agent API tool returns OHLCV, balance sheets, transcripts, and analyst estimates in a single call
Perplexity finance_search is a new Agent API tool released in May 2026 that returns structured financial data for public companies — near-real-time prices, OHLCV ranges, pre-market and after-hours data, income statements, balance sheets, cash flow, earnings call transcripts, SEC filings, analyst estimates, and ETF constituents. The model decides which fields to fetch based on the prompt.
This article was generated using artificial intelligence from primary sources.
Perplexity added the finance_search tool to its Agent API in May 2026 — a structured financial data source covering all data types needed for quantitative analysis, equity research workflows, and automated M&A monitoring. The tool aligns with the recently launched Agent API multi-model support (Claude Opus 4.7, GPT-5.5, Grok 4.20 Reasoning).
What financial data categories does the tool cover?
Perplexity finance_search returns five data categories. Pricing: near-real-time prices, OHLCV (open-high-low-close-volume) ranges, pre-market and after-hours data. Financial statements: income statements, balance sheets, and cash flow statements at quarterly and annual resolution. Earnings: latest call transcripts, SEC filings, beat/miss history by quarter, forward guidance. Market analysis: analyst estimates, top gainers/losers, ownership details, corporate actions. Additional: ETF constituents and segment KPIs for public companies.
How does the model decide which fields to return?
The documentation explicitly states: “The model decides which fields to fetch based on your prompt, so a single call can return valuation, earnings, and context together.” The approach eliminates the classic multi-step process where an agent first queries valuation, then earnings, then news — a single call returns all relevant fields tailored to the specific query.
What are presets and what are they for?
Perplexity offers three presets for common use cases: live quotes (current price + volume + key ratios), single-company historical lookups (multi-year financial trajectory), and multi-step cross-company research (peer comparison + sector analysis). Presets reduce prompt engineering overhead for standard queries.
How does it fit into the Perplexity Agent API strategy?
The tool follows the April changelog (published May 13 in the digest) that expanded the Agent API with third-party models and n8n integration. Perplexity is positioning itself as an enterprise data tool competing with specialized platforms such as Bloomberg Terminal API, Refinitiv Eikon, and FactSet — but through an Agent API that lets the LLM combine finance_search with other Perplexity search tools (web search, paper search).
Implementation is activated through the Perplexity Agent API endpoint with the finance_search tool specification. Detailed documentation is available at docs.perplexity.ai/docs/agent-api/finance-search.
Frequently Asked Questions
- What specific financial data does finance_search return?
- The tool covers pricing (near-real-time, OHLCV, pre/after-hours), financial statements (income, balance sheet, cash flow, quarterly and annual), earnings (call transcripts, SEC filings, beat/miss history, forward guidance), market data (analyst estimates, gainers/losers, ownership, corporate actions), and ETF constituents.
- How does the Perplexity model decide which fields to fetch?
- The model automatically determines which data fields to retrieve based on the user's prompt — a single API call can return valuation, earnings, and context simultaneously, without requiring separate calls.
Related news
arXiv:2605.22681: CUSP benchmark shows frontier models cannot reliably predict scientific breakthroughs
arXiv:2605.22337: Meta-Soft introduces KV cache compression via composable meta-tokens and learnable orthogonal bases
arXiv:2605.22664: WorkstreamBench tests LLM agents on end-to-end spreadsheet tasks in finance — and frontier models fail