ESTIMATED_TOKEN_COUNT
Estimates the number of tokens which would represent the input data when passed to a Claude 3 LLM. The token count is an estimate based on an older Claude tokenizer and will not be an exact match for the tokens used. The formula will error if the input contains more than 1 million characters.
Categories: Text, Objects, Arrays, Numbers
Syntax
ESTIMATED_TOKEN_COUNT(input)
Examples
Example 1
Formula
ESTIMATED_TOKEN_COUNT('Hi! Welcome to Tines')
Output
6
Example 2
Input
1
{
2
"fetch_items": {
3
"data": [
4
{
5
"finding": "A",
6
"severity": "High"
7
},
8
{
9
"finding": "B",
10
"severity": "Medium"
11
},
12
{
13
"finding": "C",
14
"severity": "Low"
15
}
16
]
17
}
18
}
Formula
ESTIMATED_TOKEN_COUNT(fetch_items.data)
Output
28
Sample actions
Select an action to inspect
You can also click "Copy action" and paste them in your Tines story to see how they work.