thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

Max Tokens

An inference parameter limiting the number of tokens the model may generate in a response.

Definition

Max tokens caps output length and cost. If the limit is reached the response is truncated, which APIs report through a stop reason such as max_tokens. It does not limit input length.

Exam tip

Truncated answers usually mean max tokens is too low.

Related terms