Frequently asked questions
Can the token price change for a long context?
Some published pricing conditions distinguish context lengths or other request settings. Check the context notes and source for the selected model. The calculator uses a recorded long-context rate when available; it does not invent a missing rate.
Is the model with the cheapest input always cheapest overall?
No. Total cost depends on input, output and applicable cached tokens. A model with cheap input but expensive output may cost more for a long answer. Enter your expected token counts in the calculator and compare the rates separately.
Does an unknown benchmark score mean a model performs badly?
No. It means a comparable verified measurement is unavailable in this catalog. We do not assign zero or estimate a score from a model name or token price. Missing values remain separate from measured results.
Does no news on this site mean a provider made no announcements?
No. We cover configured official sources, and a source may be unavailable or a post may require review. This is not a complete record of every announcement. Check source status and the original publisher if an expected update is missing.