R AI detector quickstart
Send at least 150 characters for a more reliable signal. The response score ranges from 0 (more likely human-written) to 1 (more likely AI-generated); use it as evidence, not proof.
No language-specific SDK is required. The example uses a standard or commonly used HTTP client to call Sapling's JSON API.
R
/api/v1/aidetect
This example uses the httr2 package.
library(httr2)
api_key <- Sys.getenv("SAPLING_API_KEY")
if (!nzchar(api_key)) {
stop("Set SAPLING_API_KEY first.")
}
response <- request("https://api.sapling.ai/api/v1/aidetect") |>
req_headers(Authorization = paste("Bearer", api_key)) |>
req_body_json(list(
text = paste(
"I am an artificial intelligence system designed to help people solve complex problems.",
"My capabilities include natural language processing, machine learning, and predictive analytics."
),
sent_scores = TRUE
)) |>
req_perform()
resp_body_json(response, simplifyVector = TRUE)
Example response
application/json
{
"score": 0.9989,
"sentence_scores": [
{
"score": 0.9764,
"sentence": "I am an artificial intelligence system designed to help people solve complex problems."
},
{
"score": 0.9812,
"sentence": "My capabilities include natural language processing, machine learning, and predictive analytics."
}
],
"text": "I am an artificial intelligence system designed to help people solve complex problems. My capabilities include natural language processing, machine learning, and predictive analytics."
}
The overall score and sentence scores use different methods and may not match exactly. Choose thresholds based on the false-positive and false-negative costs of your use case.
About R
R is a programming language and environment for statistical computing, data analysis, and visualization. It is widely used by data scientists, researchers, and teams working with quantitative data.