Root Endpoint Deprecated Removal: April 2026
POST /
The input text to classify.
If
true, return a list of the most indicative AI sentences.Classification score from 0.0 (human) to 1.0 (AI).
The classified text.
A string representing the classification.
List of the most indicative AI sentences. Only present when
return_ai_sentences is true.Batch Endpoint Deprecated Removal: April 2026
POST /
An array of input texts to classify.
The classification results as a list. Each item contains
text, ai_likelihood, and prediction.Sliding Window Endpoint Deprecated Removal: April 2026
POST /
The input text to segment into windows and classify.
If
true, return a list of the most indicative AI sentences.The classified text.
Classification score from 0.0 (human) to 1.0 (AI).
Maximum AI likelihood score among all windows.
Average AI likelihood score among all windows.
A string representing the classification.
Short classification string (
"AI", "Human", "Mixed").Fraction of windows classified as AI.
List of windows and their individual classifications.
Dashboard Endpoint Deprecated Removal: April 2026
POST /
The input text to classify.
Classification score from 0.0 (human) to 1.0 (AI).
A string representing the classification.
Short classification string (
"AI", "Human", "Mixed").A link to the dashboard page containing the full classification result.
Fraction of windows classified as AI.
Maximum AI likelihood score among all windows.
Average AI likelihood score among all windows.
List of windows and their individual classifications.
Extended Endpoint Deprecated Removal: April 2026
POST /
The input text to classify with extended analysis.
Enable dashboard integration.
Control visibility in dashboard.
The input text that was analyzed.
Weighted average AI likelihood score across all windows.
Maximum AI likelihood score among all windows.
Long-form prediction string representing the classification.
Short-form prediction string (
"AI", "Human", "Mixed").Classification headline summarizing the result.
List of text segments analyzed individually. Each window contains
text, ai_likelihood, label, confidence, start_index, end_index, and word_count.AI likelihood scores for each window (list of values from 0.0 to 1.0).
Indices indicating the position of each window in the original text (list of
[start_char_index, end_char_index]).Fraction of text classified as human-written (0.0–1.0).
Fraction of text classified as AI-written (0.0–1.0).
Fraction of text classified as mixed content (0.0–1.0).
Additional metadata about the analysis.
Analysis version identifier (
"adaptive_boundaries").Dashboard link. Only present when
dashboard is true. is_public controls visibility.