Replies: 1 comment
-
Hello sagsunda! The cost of running the LMOS Demo depends on: Which model you use: GPT-4 is more expensive GPT-3.5 is cheaper How many tokens you send and receive: Tokens are chunks of text (words or parts of words) you send in your prompt plus the tokens generated in the response More tokens = higher cost How many API calls the demo makes per session: Each API call costs based on tokens used More calls = more cost In short: Example: If a demo uses 3 calls, each with about 1,000 tokens, GPT-4 might cost around $0.13 total, GPT-3.5 just a few cents. That’s why costs vary depending on model and usage! |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
What is the estimated price of running LMOS Demo in terms of invoking OpenAI API Calls ?
Beta Was this translation helpful? Give feedback.
All reactions