> ## Documentation Index
> Fetch the complete documentation index at: https://exa.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Financial Datasets

> Prices, fundamentals, earnings, filings, ownership, and news for US public-company stock tickers.

[Financial Datasets](https://financialdatasets.ai) delivers structured market
data for US public companies. Through Exa Connect it exposes ticker-based tools
for news, company facts, real-time and historical prices, valuation metrics,
financial statements, earnings, insider trades, institutional (13F) ownership,
and SEC filings — plus a fundamentals-based stock screener for discovering
tickers you don't already know.

## Use it for

* Tracking news and press coverage for specific tickers.
* Pulling real-time quotes and historical price history.
* Reading fundamentals: valuation metrics, income statements, balance sheets, and cash flow.
* Checking earnings results and beat/miss surprises.
* Inspecting insider trades and institutional ownership.
* Finding and reading SEC filings, including extracted item text (risk factors, MD\&A).
* Screening the US market by fundamental criteria (market cap, P/E, growth, margins).

## Data available

Each of the following is exposed as its own tool under the `financial_datasets`
provider; the agent selects whichever fits the task:

| Tool                    | What it returns                                                                    |
| ----------------------- | ---------------------------------------------------------------------------------- |
| Company news            | Recent news articles for a ticker.                                                 |
| Company facts           | Name, sector, industry, exchange, location, SEC CIK, SIC classification.           |
| Stock price snapshot    | Current real-time price, day change, and quote time.                               |
| Historical stock prices | OHLCV bars over a date range at day/week/month/year granularity.                   |
| Financial metrics       | Market cap, EV, P/E, P/B, P/S, EV/EBITDA, PEG, margins, ROE/ROA/ROIC, growth, EPS. |
| Financial statements    | Income statement, balance sheet, and cash flow from SEC filings.                   |
| Earnings                | Quarterly revenue and EPS with YoY change and beat/miss surprises.                 |
| Insider trades          | SEC Form 4 insider transactions (name, role, type, shares, value).                 |
| Institutional ownership | 13F institutional holders, shares, and reported value.                             |
| SEC filings             | Filing metadata and direct EDGAR links, optionally filtered by form type.          |
| SEC filing items        | Extracted text of specific 10-K/10-Q/8-K items (e.g. risk factors, MD\&A).         |
| Stock screener          | Companies matching fundamental filter criteria.                                    |

## Provider ID

Use this value in `dataSources`:

```text theme={null}
financial_datasets
```

## Example

Get recent news for NVIDIA and summarize key themes.

<CodeGroup>
  ```python Python theme={null}
  from exa_py import Exa

  exa = Exa()
  run = exa.agent.runs.create(
      query="Get recent news about NVIDIA (NVDA) and summarize the key themes.",
      data_sources=[{"provider": "financial_datasets"}],
      output_schema={
          "type": "object",
          "required": ["ticker", "articles"],
          "properties": {
              "ticker": {"type": "string"},
              "articles": {
                  "type": "array",
                  "maxItems": 10,
                  "items": {
                      "type": "object",
                      "required": ["title", "source", "date", "theme"],
                      "properties": {
                          "title": {"type": "string"},
                          "source": {"type": "string"},
                          "date": {"type": "string"},
                          "theme": {"type": "string", "description": "e.g. earnings, product launch, regulation"},
                      },
                  },
              },
          },
      },
  )
  run = exa.agent.runs.poll_until_finished(run.id)
  ```

  ```typescript TypeScript theme={null}
  import Exa from "exa-js";

  const exa = new Exa();
  const run = await exa.agent.runs.create({
    query: "Get recent news about NVIDIA (NVDA) and summarize the key themes.",
    dataSources: [{ provider: "financial_datasets" }],
    outputSchema: {
      type: "object",
      required: ["ticker", "articles"],
      properties: {
        ticker: { type: "string" },
        articles: {
          type: "array",
          maxItems: 10,
          items: {
            type: "object",
            required: ["title", "source", "date", "theme"],
            properties: {
              title: { type: "string" },
              source: { type: "string" },
              date: { type: "string" },
              theme: { type: "string", description: "e.g. earnings, product launch, regulation" },
            },
          },
        },
      },
    },
  });
  ```

  ```bash cURL theme={null}
  curl -s -X POST "https://api.exa.ai/agent/runs" \
    -H "Content-Type: application/json" \
    -H "x-api-key: $EXA_API_KEY" \
    -d '{
      "query": "Get recent news about NVIDIA (NVDA) and summarize the key themes.",
      "dataSources": [{ "provider": "financial_datasets" }],
      "outputSchema": {
        "type": "object",
        "required": ["ticker", "articles"],
        "properties": {
          "ticker": { "type": "string" },
          "articles": {
            "type": "array",
            "maxItems": 10,
            "items": {
              "type": "object",
              "required": ["title", "source", "date", "theme"],
              "properties": {
                "title": { "type": "string" },
                "source": { "type": "string" },
                "date": { "type": "string" },
                "theme": { "type": "string", "description": "e.g. earnings, product launch, regulation" }
              }
            }
          }
        }
      }
    }'
  ```
</CodeGroup>

## Pairs well with

* [Particle](/reference/agent-api/connect/particle): compare published coverage with podcast commentary.
* [Baselayer](/reference/agent-api/connect/baselayer): verify the underlying entity behind a ticker.
* [Fiber.ai](/reference/agent-api/connect/fiber): enrich a public company with private-market peers and leadership contacts.