I am running openAi api and this information for tokens
output_tokens=230
input_tokens=601
total_tokens=831
So, Why are 0.2$ deducted from this?
Although I see in the documentation that every million tokens is worth two or three dollars
- Which model did you use?
- Did you include tools such as web search and file search? They are charged separately.
- You can detail your billing exporting a csv of your usage.
3 Likes
- I am using the “GPT-4” model.
- I’m only using “function calling”, no web search or file search tools.
- I checked the usage details for today.
- Input tokens: 1,807
- Output tokens: 653
- Total cost: $0.11
- This is for 3 separate requests.
I’m still new to the API and would love to hear any suggestions for managing usage and keeping costs low.
GPT 4 is $30 per million tokens input $40 output, that’s why you are finding it expensive.
Try using gpt-4.1, it’s cheaper.
1 Like