GPTZero API: Pricing, Playground & Docs

About GPTZero

Deep-learning detector that flags portions of text likely generated by AI versus human, classifying content as entirely human, AI, or mixed.

ai detectionclassification

GPTZero specs

Model ID: gptzero
Author: GPTZero
Category: Tools & Agents
Released: -
Input: TextDocument
Output: Text
Endpoints: POST/v1/detectPOST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/gptzero:generateContent
Alternate model IDs: gptzero/detect

GPTZero API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

Type

Spec

Rate

Text Scan

per 1,000 words

$0.39

Compare on the full pricing page

How to call the GPTZero API

GPTZero serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id gptzero. Get an API key from the EmpirioLabs dashboard.

cURL

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gptzero",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="gptzero",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)

Full GPTZero API reference

GPTZero API parameters

Request parameters supported by the GPTZero API on EmpirioLabs. Defaults apply when a field is omitted.

Parameter	Type	Default	Range / values	Description
input	string	-	-	Text to analyze
scan_type	enum	ai_detection	ai_detection	AI Detection: detect AI-generated text.
file_url	string	-	-	URL of a document to scan instead of pasting text. Supported: PDF, DOC, DOCX, RTF, ODT, TXT, MD (max 25 MB). Provide either input (text) or file_url, not both.
model_version	string	__latest__	-	The GPTZero model version to scan with. Leave as __latest__ to use the newest version. A version that is unknown or no longer available returns a 400 error that...
version	string	__latest__	-	The GPTZero model version to scan with. Leave as __latest__ to use the newest version. A version that is unknown or no longer available returns a 400 error that...
ai_threshold	number	0.7	0.1 to 0.99	Formatted reports only: the probability at which a sentence is labeled AI-generated. Lower = more sensitive. Range 0.10 to 0.99. It does not change the detection scores.
max_sentences	number	15	1 to 50	Formatted reports only: the maximum number of sentences shown in the per-sentence breakdown.
disable_formatting	boolean	false	-	Return the detection result as JSON instead of the formatted Markdown report.

Good to know

File limits

One document per request, sent as file_url
Max 25 MB
Each document truncated to 50,000 characters

Supported formats

PDF, DOC, DOCX, RTF, ODT, TXT, MD

GPTZero API: common questions

How much does the GPTZero API cost?

On EmpirioLabs, GPTZero is billed pay as you go: Text Scan $0.39 per 1,000 words. The live rate card on this page always matches what the API charges.

Is the GPTZero API OpenAI-compatible?

Yes. GPTZero serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to gptzero.

Can I try GPTZero in the browser before integrating?

Yes. The EmpirioLabs playground runs GPTZero in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a GPTZero API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.

GPTZero API