{"version":"2026-10-26.2","id":"sec","task":"get the latest 10-K of one listed company with its key reported financial facts","input":{"ticker":"AAPL","form":"10-K","limit":1},"measured_at":"2026-10-28T19:13:00.200662+00:00","figures":{"requests":"9 requests","diy_size":"505.3 KB","diy_time":"4.7 s","diy_tokens":"about 340,000 tokens","ours_size":"5.4 KB","ours_time":"2.1 s","ours_tokens":"about 2,300 tokens","date":"2026-10-28","gain":"For an agent that is about 93× less data, 2.2× faster and about 150× fewer tokens per check than doing it by hand."},"diy":{"requests":9,"failed":0,"bytes":505273,"wire_bytes":126516,"wall_s":4.7,"tokens":340202,"sources":[{"name":"www.sec.gov","host":"www.sec.gov","path":"/include/ticker.txt","status":200,"bytes":155669,"wire_bytes":79996,"ms":975,"tokens_per_byte":0.8482,"sample_bytes":12000,"tokens":132033},{"name":"data.sec.gov","host":"data.sec.gov","path":"/submissions/CIK0000320193.json","status":200,"bytes":163917,"wire_bytes":28159,"ms":569,"tokens_per_byte":0.5528,"sample_bytes":12000,"tokens":90619},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/Revenues.json","status":200,"bytes":2252,"wire_bytes":593,"ms":253,"tokens_per_byte":0.5555,"sample_bytes":2252,"tokens":1251},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/NetIncomeLoss.json","status":200,"bytes":50767,"wire_bytes":3891,"ms":426,"tokens_per_byte":0.6446,"sample_bytes":12000,"tokens":32724},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/StockholdersEquity.json","status":200,"bytes":34970,"wire_bytes":3211,"ms":448,"tokens_per_byte":0.6365,"sample_bytes":12000,"tokens":22258},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/dei/EntityCommonStockSharesOutstanding.js","status":200,"bytes":10629,"wire_bytes":2255,"ms":490,"tokens_per_byte":0.6227,"sample_bytes":10629,"tokens":6619},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/RevenueFromContractWithCustomerEx","status":200,"bytes":18356,"wire_bytes":1967,"ms":507,"tokens_per_byte":0.6316,"sample_bytes":12000,"tokens":11593},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/EarningsPerShareDiluted.json","status":200,"bytes":48741,"wire_bytes":3972,"ms":507,"tokens_per_byte":0.6188,"sample_bytes":12000,"tokens":30163},{"name":"data.sec.gov","host":"data.sec.gov","path":"/api/xbrl/companyconcept/CIK0000320193/us-gaap/Assets.json","status":200,"bytes":19972,"wire_bytes":2472,"ms":529,"tokens_per_byte":0.648,"sample_bytes":12000,"tokens":12942}]},"ours":{"calls":1,"bytes":5414,"ms":2110,"tokens":2299,"price_usd":0.003},"usd":{"diy_input":"$0.68","call":"$0.003","answer":"$0.0046","ours_total":"$0.0076","diy_input_usd":0.680404,"call_usd":0.003,"answer_usd":0.004598,"ours_total_usd":0.007598,"saves_money":true},"token_price":{"provider":"OpenAI","model":"gpt-4.1","input_usd_per_mtok":2,"url":"https://developers.openai.com/api/docs/pricing","read_at":"2026-10-28T19:13:00.200662+00:00","scope":"standard tier, text input tokens","price_text":"$2.00 per 1 million input tokens"},"method":{"diy":"Requests an agent must make itself to get the same answer: for sanctions the five official list files fetched one after another with a plain GET without compression (the EU server drops TLS when gzip is requested); for the other tasks the outgoing data requests of our own worker for that call (payment-side requests excluded), run in a sandbox copy of the worker with the payment stubbed and the live network.","ours":"One call to the route with the input shown; size is the response body in bytes, time is the sandbox wall clock.","bytes":"Decoded response bytes; 1 MB = 1,000,000 bytes and 1 KB = 1,000 bytes. Wire bytes (compressed) are listed per source.","time":"Wall clock of this machine; requests one after another; a different machine or network gives different seconds.","tokens":"Tokens of the raw content if it is read into a model: Ollama qwen3.5:9b (prompt_eval_count of the loaded chat model). Three chunks of 4000 bytes per file (start, middle, end) give tokens per byte, applied to the full size of that file; our response is counted whole.","not_shown":"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."},"tokenizer":{"name":"Ollama qwen3.5:9b (prompt_eval_count of the loaded chat model)","real":true,"sample_bytes":4000}}