📚 Glossary
Inference
In one line: Running a trained model to get an answer. Distinct from training, which is teaching the model in the first place.
Inference is the act of using a trained model — sending it your prompt and getting back an answer. Inference is what happens when you ask ChatGPT a question.
Distinct from training, which is the (much more expensive) process of teaching the model in the first place. Training a foundation model can cost $10M-$100M; one inference call costs a fraction of a cent.
Inference cost is what you pay per token via the API. AskAI.free's pricing is based on monthly inference allowances — Pro gives you ~1M tokens/month, Max gives 5M.
See it in action — ask any AI about inference on AskAI.free.
Try it free →