Skip to main content

​
Installation

pip install pangram-sdk

​
PangramText

The main client class for interacting with the Pangram Labs API.

​
Constructor

from pangram import Pangram

client = Pangram(api_key="your-api-key")
​
api_key
string
Your API key for Pangram Labs. If not provided, the PANGRAM_API_KEY environment variable will be used.
Raises ValueError if the API key is not provided and not set in the environment.

​
predict()

Classify text as AI-generated, AI-assisted, or human-written using the V3 API. Returns analysis with windowed, segment-level results. 
result = client.predict(text, public_dashboard_link=False)
Parameters
​
text
string
required
The text to be classified.
​
public_dashboard_link
boolean
default:"false"
Whether to include a public dashboard link in the response.
Returns A dictionary with the following fields:
​
text
string
The input text.
​
version
string
The API version identifier (e.g., "3.0").
​
headline
string
Classification headline summarizing the result.
​
prediction
string
Long-form prediction string describing the classification.
​
prediction_short
string
Short-form prediction string ("AI", "AI-Assisted", "Human", "Mixed").
​
fraction_ai
float
Fraction of text classified as AI-written (0.0–1.0).
​
fraction_ai_assisted
float
Fraction of text classified as AI-assisted (0.0–1.0).
​
fraction_human
float
Fraction of text classified as human-written (0.0–1.0).
​
num_ai_segments
integer
Number of text segments classified as AI.
​
num_ai_assisted_segments
integer
Number of text segments classified as AI-assisted.
​
num_human_segments
integer
Number of text segments classified as human.
​
dashboard_link
string
Dashboard link. Only present when public_dashboard_link is True.
​
windows
list
List of text windows and their classifications. Each window contains:
Raises ValueError if the API returns an error.

​
predict_short()

Classify text using the short endpoint. Cuts off text at 512 tokens. 
result = client.predict_short(text)
Parameters
​
text
string
required
The text to be classified.
Returns A dictionary with the following fields:
​
text
string
The input text.
​
ai_likelihood
float
Classification score from 0.0 (human) to 1.0 (AI).
​
prediction
string
A string representing the classification.

​
check_plagiarism()

Check text for potential plagiarism against a database of online content. 
result = client.check_plagiarism(text)
Parameters
​
text
string
required
The text to check for plagiarism.
Returns A dictionary with the following fields:
​
text
string
The input text.
​
plagiarism_detected
boolean
Whether plagiarism was detected.
​
plagiarized_content
list
List of detected plagiarized content with source URLs.
​
total_sentences
integer
Total number of sentences checked.
​
plagiarized_sentences
list
List of sentences detected as plagiarized.
​
percent_plagiarized
float
Percentage of text detected as plagiarized.
Raises ValueError if the API returns an error.

​
Deprecated Methods

The following methods are deprecated and will be removed by April 1st, 2026. Use predict() instead.

​
predict_extended() Deprecated

Extended analysis with adaptive boundaries. Use predict() instead. 
result = client.predict_extended(text)

​
batch_predict() Deprecated

Classify a batch of texts. Iterates through the batch and calls predict() for each text. 
results = client.batch_predict(["text one", "text two"])

​
predict_sliding_window() Deprecated

Classify a long document using a sliding window. Use predict() instead. 
result = client.predict_sliding_window(text)