{"version":"2026-10-26.2","id":"search","task":"find x402 services for one capability among the open x402 directories, with price and networks","input":{"q":"weather","limit":5},"measured_at":"2026-11-03T10:56:27.722382+00:00","figures":{"requests":"4 requests","diy_size":"149.7 MB","diy_time":"46 s","diy_tokens":"about 58 million tokens","ours_size":"12.1 KB","ours_time":"0.6 s","ours_tokens":"about 4,000 tokens","date":"2026-11-03","gain":"For an agent that is about 12,000× less data, 78× faster and about 15,000× fewer tokens per check than doing it by hand."},"diy":{"requests":4,"failed":0,"bytes":149715971,"wire_bytes":40608520,"wall_s":46.2,"tokens":57852834,"sources":[{"name":"Agenstry feed","host":"agenstry.com","path":"/api/feed/all.jsonl.gz","status":200,"bytes":132356948,"wire_bytes":23249497,"ms":41045,"tokens_per_byte":0.3814,"sample_bytes":12000,"tokens":50483146,"retries":0},{"name":"Open 402 Directory","host":"raw.githubusercontent.com","path":"/ArcedeDev/open-402/main/registry/snapshot.json","status":200,"bytes":17244604,"wire_bytes":17244604,"ms":1979,"tokens_per_byte":0.4256,"sample_bytes":12000,"tokens":7339016,"retries":0},{"name":"pay.sh catalog","host":"pay.sh","path":"/api/catalog","status":200,"bytes":53849,"wire_bytes":53849,"ms":1686,"tokens_per_byte":0.2482,"sample_bytes":12000,"tokens":13364,"retries":0},{"name":"apis.io x402","host":"apis.io","path":"/api/v1/apis","status":200,"bytes":60570,"wire_bytes":60570,"ms":1494,"tokens_per_byte":0.2858,"sample_bytes":12000,"tokens":17308,"retries":0}]},"ours":{"calls":1,"bytes":12115,"ms":594,"tokens":3977,"price_usd":0.04},"usd":{"diy_input":"$115.71","call":"$0.04","answer":"$0.008","ours_total":"$0.048","diy_input_usd":115.70566799999999,"call_usd":0.04,"answer_usd":0.007954,"ours_total_usd":0.047954,"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":"2026-11-03T10:56:27.722382+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}}