Do Assistants' instruction values consume tokens?

Do Assistants’ instruction values consume tokens?
The length of the message between users and assistants exchanged at once is about 300 length.
Probably about 100 tokens will be consumed.

However, once a message is sent, it costs more than $0.1.

My instructions value is about 9000 length string.

I didn’t find anywhere in the guide or API documentation that it was explained that instructions consume tokens.

Short answer, yes.

Anything you send to be processed by the model counts.


Instructions consume tokens, chat history consumes tokens, so does retrieval of data from your stored files, so does sending information from the code interpreter and tool calls. The GPT models are stateless, everything has to be sent to the model from scratch every time you make an API call.


As this topic has an accepted solution, closing topic.