Add: cost calc explanation

README.md

@@ -56,6 +56,10 @@ We computed the validation set accuracy based on a sample of 1,000 points from o
   <img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/plots/accuracy-vs-cost--nosible-dataset.png"/>
 <p>
 
+Cost per 1M tokens for the LLMs was calculated as a weighted average of input and output token costs using a 10:1 ratio (10× input cost + 1× output cost, divided by 11), based on pricing from OpenRouter. This reflects the ratio between our prompt used to label our dataset.
+
+For the NOSIBLE model, we conservatively used the cost of Qwen-8B on OpenRouter with a 100:1 ratio since the model produces a single output token when used as described in this guide. Despite this, our model is still the cheapest option.
+
 #### Financial PhraseBank Dataset
 
 We computed the Financial PhraseBank accuracies on the entire dataset. The 86% for FinBERT was their reported number in their paper.