Finterm
Sourced financial data for trading agents

The finance CLI for your trading agent.

Finterm is a CLI data layer for trading agents. Its commands return structured financial data and research that agents can inspect, cite, and reuse.

npm install -g @finterm-ai/cli
Works anywhere your agent can run a CLI. Not investment advice.
§ 01 · Features

Financial research structured for agent context.

Finterm combines financial data with filtered sources, calculated signals, filing diffs, and outputs designed for limited context windows.

Examples below use runs from June 23 and July 6, 2026. Each example states its historical or current comparison window.

Ticker data bundle

finterm bundle run ticker_data NVDA --delivery-mode inline_result

Creates the NVIDIA ticker_data run and returns the structured ticker snapshot inline.

The full ticker snapshot in one bundle: earnings, guidance, price reaction, ratios, options sentiment, short pressure, technicals, statements, and pre-earnings context.

Example run dated June 23, 2026. Data sections: Earnings, Guidance, Prices, Ratios, Options, Statements. Output facts: Earnings: actuals + surprise; Guidance: revenue + EPS; Prices: T-1 / T0 / T+5; Options: P/C + liquidity; Technicals: RSI · MACD · SMA.

SEC filing diffs

finterm tool sec_filing_diff NVDA --base 2026:Q3 --compare 2027:Q1

Compares NVIDIA filings section by section and returns the changed language.

Example comparison dated June 23, 2026. Changed filing lines: Item 7. MD&A — First Quarter FY2027 Summary; Revenue $57.0B · GM 73.4% · net income $31.9B · EPS $1.30 (Q3 FY2026); Revenue $81.6B · GM 74.9% · net income $58.3B · EPS $2.39 (Q1 FY2027, +85% YoY); Item 1A. Risk Factors — China export controls; ≈$50M H20 revenue under USG licenses to China-based customers (Aug 2025); H200 now carries a 25% U.S. import tariff; no Hopper shipments to China this quarter vs $4.6B a year ago; New: $18.6B into private cos/infra funds; up to $10B in Anthropic; equity stake in Intel pending approval. Summary: MD&A · 131% churn; Risk Factors · 60% churn; QA-checked.

Ticker Deep Research

finterm bundle run company_deep_research NVDA --company-name "NVIDIA Corporation" --param q=Q1 --param fy=2027 --param prev_q=Q3 --param prev_fy=2026 --delivery-mode summary_json

Runs the search, crawl, dedupe, and source-labeling pass for NVDA.

Fetches hundreds of links for a ticker, then filters AI slop, SEO spam, syndicated reprints, and off-topic results into a deduplicated research packet.

Example run dated June 23, 2026. 40 searches produced 742 unique URLs; 470 were kept and labeled, including 84 primary, 351 secondary, and 35 noise-tier results. 272 were dropped, including 27 AI-slop results, and 11 duplicate reprints were merged.

Options sentiment

finterm tool options_overview NVDA

Reads the live options chain into put/call flow, IV30, and expected moves.

Example run dated June 23, 2026. Neutral-bullish: Call-tilted flow · IV30 below realized vol. 58% call share of volume. P/C (vol): 0.72; IV30: 36.9%; Exp. move (1mo): ±8.7%.

Insider and 13F flows, netted

finterm tool insider_trades NVDA

Returns NVIDIA Form 4 insider transactions with the trailing 90-day open-market net.

Example run dated June 23, 2026. Open-market Form 4 · NVDA · 90d: $275.6 million net selling. Transactions: Form 4, M. Stevens · Director, Sell, −1.00M, −$221.1M; Form 4, A. Puri · EVP Ops, Sell, −270,134, −$49.2M; Form 4, C. Kress · CFO, Sell, −30,201, −$5.3M; Form 4, S. Gawel · PAO, Grant, +59,509, RSU; 13F, Rathbones Group, Hold, 6.05M, $1.05B.

Ticker sentiment

finterm tool ticker_sentiment NVDA

Scores seven components against NVDA’s own trailing year and returns the 0–100 composite.

Example run dated July 6, 2026. Score 14 out of 100, extreme fear; up from 6 a week ago · Δ5d +8.2; coverage 5/7. Subscores: Trend: 10; Flow: —; Positioning: 20. Scored components: Price vs 125-day average: 17; 52-week range position: 2; Up-day volume share (20d): 12; Short interest: 13; Implied-volatility rank: 27. Omitted components: Put/call volume (5-day avg): history accruing; Open-interest put/call tilt: history accruing.

§ 02 · Why it exists

Finterm gathers and structures the data before analysis.

It returns ticker data, filing diffs, ownership flows, market context, and filtered research. Sourced research findings retain links, timestamps, and caveats.

One command

Give your agent a question and let the CLI pull the relevant financial context.

Agent-readable output

Results come back as structured data your agent can read, cite, and reuse.

Research sources included

Sourced findings retain links, timestamps, and caveats for inspection.

§ 03 · Example workflow

Compare three cloud-company filings in one workflow.

A real run: the prompt, your agent’s sourced answer, and the exact finterm calls underneath.

finterm sec_filing_diff · GOOGL · AMZN · MSFT
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?

Mapped the three cloud brands to their SEC filers (Alphabet/GOOGL, Amazon/AMZN, Microsoft/MSFT) and diffed consecutive 10-Qs section by section.

Ran SEC filing diff · Alphabet (GOOGL)
Bash
$ finterm tool sec_filing_diff GOOGL --base 2025:Q3 --compare 2026:Q1
MD&A, Risk Factors changed · QA-checked
Ran SEC filing diff · Amazon (AMZN)
Bash
$ finterm tool sec_filing_diff AMZN --base 2025:Q3 --compare 2026:Q1
MD&A, Risk Factors changed · QA-checked
Ran SEC filing diff · Microsoft (MSFT)
Bash
$ finterm tool sec_filing_diff MSFT --base 2026:Q2 --compare 2026:Q3
MD&A, Risk Factors changed · QA-checked

Selected excerpts from the comparison show four forms of AI-related capital intensity:

  1. An AI-capex step-change. Alphabet more than doubled quarterly capital expenditures year over year and tied the increase to technical infrastructure.
    “During the three months ended March 31, 2025 and 2026, we spent $17.2 billion and $35.7 billion on capital expenditures, respectively.” Alphabet 10-Q · FY2026 Q1 · MD&A
  2. AI written into the risk factors. Alphabet expanded its risk language to address AI infrastructure and return on capital.
    “…building AI-optimized infrastructure, including our custom TPUs… Our investments ultimately may not be commercially viable or may not result in an adequate return of capital.” Alphabet 10-Q · FY2026 Q1 · Risk Factors
  3. A multi-billion-dollar model-company stake. Amazon disclosed a $15.0 billion investment and a conditional commitment for more.
    “In Q1 2026, we invested $15.0 billion in OpenAI’s Series C Preferred Stock and entered into an equity commitment letter agreement to purchase an additional $35.0 billion…” Amazon 10-Q · FY2026 Q1 · Financial Statements
  4. Data-center and power commitments. Alphabet disclosed uncommenced leases and credit backstops for third-party infrastructure.
    “…up to $33.3 billion of future backstops to support the build-out of data center and energy supply infrastructure, alongside uncommenced data-center leases of $75.6 billion.” Alphabet 10-Q · FY2026 Q1 · Commitments

These Alphabet and Amazon excerpts show how AI investment appears in capital spending, risk language, equity commitments, leases, and credit support. Each quote identifies and links to its filing and section; the commands above show the three-filer comparison workflow.

Real Finterm output · figures quoted from public filings Not investment advice
§ 04 · Prompts to try

Start with a research question.

Use a plain-language prompt. Finterm supplies the structured data and sources for your agent to analyze.

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.

§ 05 · Everything in the bundle

Compare the bundle with separate data categories.

The table compares Finterm’s coverage with category prices from a July 2026 review of public price lists.

In the bundle Comparable cost
The company packet. Earnings, guidance, price reaction, ratios, options, short pressure, technicals—one call. $60–150/mo
SEC filing diffs. Section-aware, line-by-line diff of any two filings, churn stats, QA-checked. No close packaged equivalent identified
SEC search and sections. Find any filer’s filings; pull clean narrative sections as text. $49/mo
Ownership flows, netted. Form 4 trades rolled into a 90-day open-market net; 13F holders, ticker-mapped. $49–149/mo
Options intelligence. Implied versus realized with rank, today’s flow, positioning, expected moves—one call. $99–199/mo
Sentiment as a number. A 0–100 composite of trend, flow, and positioning, each scored against the ticker’s own year. $59–99/mo
Ticker Deep Research. Web links filtered into a research packet: noise removed, reprints merged, sources tiered, provenance retained. No close packaged equivalent identified
Prices and statements. Latest available prices, reported financial statements, standard technicals. $20–99/mo
The dataroom. Runs cached to a local, re-queryable room for later reuse. No close packaged equivalent identified

Purchased separately: $300–450/month (APIs alone)

Finterm Pro: $200/month (fetched data cached, yours to keep)

Ranges reflect a July 2026 review of public price lists. Plans and feature coverage vary.

Set up Finterm for your agent.

$150/month
$200/month
3-day free trial

3-day free trial, card required.

Preview price for the first 1,000 users: $150 per month, $50 below the $200 standard price, during the preview period.

Once you have an account, give finterm to your coding agent:

In your terminal
npm install -g @finterm-ai/cli
Or paste 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.

Not investment advice.