The 100K Cliff

Archived study

Models a discontinuity in token costs at a supplied 100K-input-token pricing boundary. The archived script and editable pricing configuration explore discounts, workload assumptions, and tokenizer inflation.

Interpretation and limits

The analysis is arithmetic on the session’s supplied pricing assumptions, not a live API billing experiment. Threshold semantics and serialized-request token counts matter; the model name and prices in the archive should not be treated as verified current service specifications.

Package and provenance

The original .science export and matching poster are preserved byte-for-byte from Hugging Face snapshot b0218fea4fc3fc9aa37ac616aba20e619e242c1e. The package contains the archived conversation, session metadata, and resources listed in its internal manifest. This introduction summarizes the archived record; the research, external sources, and model evaluations were not rerun for this reorganization.

Case files

• Session export
• Case poster