obsidian sigil
hi, i have an assistant in my playground but want to get a better idea of the cost breakdown so i can create an overall cost estimate. i know the following:
gpt-4-1106-preview
Input: $0.01 /1k tokens
Output: $0.03 /1k tokens
Retrieval: $0.20 /GB /assistant /day
is there an additional cost for the assistant instructions? are there any other additional costs that i am missing?
still krakenBOT
Hi @obsidian sigil. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Based on the information provided in the extracts, here's a breakdown of the costs associated with using the Assistant API:
Model Usage (GPT-4-1106-preview): The cost for using the gpt-4-1106-preview model is $0.01 per 1k input tokens and $0.03 per 1k output tokens. This is the cost for the AI to process your instructions and generate responses. source (https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost)
Retrieval: The cost for retrieval is $0.20 per GB per assistant per day. This is the cost for storing and retrieving data used by your assistant. source (https://help.openai.com/en/articles/8550641-assistants-api)
Code Interpreter: If your assistant uses the Code Interpreter tool, it is charged at $0.03 per session. Each session is active by default for one hour. source (https://platform.openai.com/docs/assistants/tools)
Rate Limits: Depending on your usage tier, there may be limitations on the number of tokens per minute (TPM) you can use. Higher tiers allow for more TPM but require a certain amount to be paid. source (https://community.openai.com/t/475758)