Task: get the latest 10-K of one listed company with its key reported financial facts. Input: ticker AAPL, form 10-K, one filing. Measured 2026-11-18.
| Requests | Size | Time | Tokens if read into a model | |
|---|---|---|---|---|
| By hand: read the ticker list, the company's filing index and one XBRL concept file per fact | 9 requests | 507.7 KB | 7.1 s | about 340,000 tokens |
One call: one call to a parsing API for the same filing (/sec/filings) | 1 call | 5.8 KB | 4.3 s | about 2,500 tokens |
| Tokens | Cost | |
|---|---|---|
| By hand: the raw content read into a model | about 340,000 tokens | about $0.68 in model input tokens |
| One call: the price of the call | $0.003 | |
| One call: the answer's own tokens read into a model | about 2,500 tokens | about $0.005 |
| One call, together | about $0.008 |
Tokens are priced at $2.00 per 1 million input tokens (OpenAI gpt-4.1, standard tier, text input tokens). Source: https://developers.openai.com/api/docs/pricing, read 2026-11-11. The price of the call is the amount in the route's own payment offer when it was measured (2026-11-18). Only input tokens are counted, not the model's own output. Prices change; these figures hold for those dates, and another model costs more or less. A local parser spends no tokens but needs code and upkeep, and some by-hand sizes are larger than a model's context window, so the by-hand figure is the price of the tokens, not a workable procedure.
| Source | Address | HTTP | Size | Time | Tokens |
|---|---|---|---|---|---|
| www.sec.gov | www.sec.gov/include/ticker.txt | 200 | 155.7 KB (80.0 KB on the wire) | 1.6 s | 132,033 |
| data.sec.gov | data.sec.gov/submissions/CIK0000320193.json | 200 | 164.1 KB (28.4 KB on the wire) | 1.2 s | 91,009 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/Revenues.json | 200 | 2.3 KB (593 bytes on the wire) | 0.2 s | 1,251 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/Assets.json | 200 | 20.2 KB (2.5 KB on the wire) | 0.6 s | 13,117 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/dei/EntityCommonStockSharesOutstanding.js | 200 | 10.8 KB (2.3 KB on the wire) | 0.7 s | 6,712 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/StockholdersEquity.json | 200 | 35.5 KB (3.3 KB on the wire) | 0.7 s | 22,570 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/RevenueFromContractWithCustomerEx | 200 | 18.8 KB (2.0 KB on the wire) | 0.7 s | 11,892 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/NetIncomeLoss.json | 200 | 51.2 KB (3.9 KB on the wire) | 0.7 s | 32,995 |
| data.sec.gov | data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/EarningsPerShareDiluted.json | 200 | 49.2 KB (4.0 KB on the wire) | 0.8 s | 30,437 |
A local parser reads files without spending tokens but needs code and upkeep; a cached copy avoids the download but goes stale; accuracy, completeness and price of any answer are separate questions.
Repeat: Re-measured weekly by agents/savings_facts.py; the harness is ops/savings_measure.mjs. Raw numbers as JSON: ?format=json.
Published by P0, run by dev Mike. An open index of the machine-to-machine (agent) economy. Terms · Who runs P0 · All measurements