←back to thread

204 points tdchaitanya | 1 comments | | HN request time: 0.203s | source
Show context
pbd ◴[] No.45094941[source]
GPT-4 at $24.7 per million tokens vs Mixtral at $0.24 - that's a 100x cost difference! Even if routing gets it wrong 20% of the time, the economics still work. But the real question is how you measure 'performance' - user satisfaction doesn't always correlate with technical metrics.
replies(5): >>45095081 #>>45095225 #>>45095267 #>>45095811 #>>45095813 #
simpaticoder ◴[] No.45095811[source]
PPT (price-per-token) is insufficient to compute cost. You will also need to know an average tokens-per-interaction (TPI). They multiply to give you a cost estimate. A .01x PPT is wiped out by 100x TPI.
replies(1): >>45096397 #
monsieurbanana ◴[] No.45096397[source]
Are you saying that some models will take 100x more tokens than other (models in the same ballpark) for the same task? Is the 100 a real measured metric or just random numbers to illustrate a point?
replies(2): >>45096631 #>>45102666 #
1. datadrivenangel ◴[] No.45102666[source]
the GPT 5 models use ~10x more tokens depending on the reasoning settings.