claude-cost-teardown
A cost teardown of a Claude agent, turn by turn. Tactics for debugging inference token costs, ranked by what each is measurably worth — including the ones that cost more than they save.
- 0
- HTML
- MIT
- 3 mo ago
A cost teardown of a Claude agent, turn by turn. Tactics for debugging inference token costs, ranked by what each is measurably worth — including the ones that cost more than they save.
What LLM inference actually costs. 874 verified price rows across 24 providers, 378 GPU rental rates, 395 cited throughput datapoints, and a self-hosting break-even model. Every number carries a source URL, a retrieval date, and passed a mechanical evidence gate. Dated immutable snapshots. CC BY 4.0.
NeoSmith Maestro — frontier-level coding accuracy from a bouquet of small models at ~1/30th the cost. Technical report + reproducible evidence (LiveCodeBench v6 92.2%, SWE-bench Pro 74.2/88.9).