# Finterm

Sourced financial data and research for trading agents.

Finterm gives coding agents ticker data bundles, SEC filing diffs, insider and institutional flows, options and sentiment, and multi-source research. In a June 23, 2026 example run, Ticker Deep Research fetched hundreds of links and filtered them into a deduplicated, source-labeled research packet.

Installing the CLI is free. Authenticated data commands require an active Finterm Pro subscription; every subscription starts with a 3-day free trial, card required. Current terms: https://app.finterm.ai/pricing.

## Install

```bash
npm install -g @finterm-ai/cli
finterm setup
finterm prime
```

Paste this instruction into your coding agent:

“Set up finterm.ai for me. Run `npm install -g @finterm-ai/cli`, then `finterm setup` to install the agent skills and `finterm prime` to load the current catalog. When `finterm auth login` opens a browser, ask me to authorize it. Then show me what Finterm can do.”

## Account and Auth

Paid data and research calls require Finterm Pro, activated by starting the 3-day free trial (card required) at https://app.finterm.ai/pricing.

- `finterm auth login` opens a browser for the human to authorize once; the CLI picks up the credential automatically. Headless environments can set `FINTERM_API_KEY` to a dashboard-minted key instead.
- A paid data or research call without Pro fails with HTTP 402, code `SUBSCRIPTION_REQUIRED`, carrying a machine-readable `error.upgrade_url` (https://app.finterm.ai/pricing). Agents: do not retry in a loop; relay the upgrade URL to your operator, then re-run after checkout. Access activates automatically.
- `finterm auth status` reports the account email and plan/trial state when access needs explaining.

## Example Workflow

Prompt: can you use finterm to compare available 10-Qs for the big cloud providers (google cloud, aws, microsoft) and show selected changes in AI investment and risk?

```bash
finterm tool sec_filing_diff GOOGL --base 2025:Q3 --compare 2026:Q1
finterm tool sec_filing_diff AMZN --base 2025:Q3 --compare 2026:Q1
finterm tool sec_filing_diff MSFT --base 2026:Q2 --compare 2026:Q3
```

The example answer surfaces four selected themes:

- Higher AI-related capital expenditures.
- AI infrastructure in risk disclosures.
- Multi-billion-dollar model-company investments.
- Data-center leases and credit backstops.
See the cited example at https://finterm.ai/#see-it.

## Prompts to Try

- Is this dip in NVDA being bought or sold by insiders? Pull Form 4 activity and the latest 13F holders, and net it out.
- Give me the bull and bear case on AMD’s data-center demand this quarter, from multiple sources, deduped and labeled primary or secondary.
- What’s the options market pricing into TSLA earnings, and where does sentiment sit versus its own trailing year?
- Diff Apple’s latest 10-K against last year’s and flag every new or softened risk factor.

## Docs

Full CLI and API reference: https://docs.finterm.ai (agent-readable index: https://docs.finterm.ai/llms.txt).

## Pricing

Preview price: $150/month for the first 1,000 users during the preview period. Standard price: $200/month.

Every subscription starts with a 3-day free trial, card required—trial and Pro activate together in one checkout. Upgrade URL: https://app.finterm.ai/pricing.

Sourced research outputs include links, timestamps, and caveats. Finterm does not provide investment advice.

## Published research and articles

- Breaking Down $1.65 Trillion of Big Tech AI Spending: https://finterm.ai/blog/big-tech-ai-spending-1-65-trillion.md (The $1.65 trillion figure is a multi-year stack of disclosed leases and purchase commitments, not cash already spent or current debt.)
- No, Big Tech Isn’t Hiding $1.65 Trillion of Debt: https://finterm.ai/blog/big-tech-hidden-debt-fact-check.md (SEC filings show about $430.0 billion of interest-bearing borrowings, not $1.65 trillion of hidden debt.)
- Fictional Example Company Research Brief: https://finterm.ai/blog/example-company-research.md (A fictional example demonstrating public evidence and local assets.)
- Introducing Finterm: https://finterm.ai/blog/introducing-finterm.md (A concise introduction to sourced financial research for coding agents.)