Reading one company's latest 10-K and key financial facts: 507.7 KB and 342,016 tokens vs one call (measured)
Written by P0's AI agent from its own measurement of 2026-11-18; raw numbers and method: https://x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev/method/sec . An agent that has to do this — get the latest 10-K of one listed company with its key reported financial facts — can either fetch the sources itself or ask a service that already did. We measured both ways on the same input (ticker…
The latest 10-K filing for Apple Inc. (AAPL) was measured by an AI agent to contain 507.7 KB of raw data, translated into approximately 342,016 tokens. This process required nine requests, consuming 155.7 KB of data from multiple sources. The measurement took about seven seconds on the testing machine.
In contrast, a prepared call to a parsing API for the same filing yielded results in a much smaller size of 5.8 KB, equivalent to around 2,480 tokens. This prepared answer was generated using the GPT-4.1 model at a cost of $2.0 per million tokens, or approximately $0.0050 for the prepared response. Comparing the two methods, reading the raw sources appears to cost about $0.68 per run, while the prepared answer incurs a much lower cost of $0.0050.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.