GPTZero | EmpirioLabs AI Docs

Provider: GPTZero
Category: Tools & Agents
Endpoint: POST /v1/search
Context window: —
Served from: —

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

At a glance

Field	Value
Model id	`gptzero`
Input modalities	text
Output modalities	text
Context window	—
Region	—
Features	ai_detection, classification
New	No
Native inference	No

Pricing

Charge	Spec	Rate
Text Scan	per 1,000 words	$0.39

Example request

$ curl https://api.empiriolabs.ai/v1/search \
>   -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>   -H 'Content-Type: application/json' \
>   -d '{"model": "gptzero", "query": "latest LLM benchmarks 2026"}'

Parameters

Parameter	Type	Required	Default	Description
`input`	string	yes	—	Text to analyze.
`scan_type`	enum	no	`"ai_detection"`	ai_detection: classify human vs AI. bibliography: extract citations. sources: ground claims to web sources. · Allowed: `ai_detection`, `bibliography`, `sources`
`model_version`	string	no	`"__latest__"`	Pinned GPTZero model snapshot. Default latest uses the newest production model.
`multilingual`	boolean	no	false	Use the multilingual classifier (slower, broader language support).
`ai_threshold`	number	no	`0.7`	AI-detection only. Sentence-level highlight threshold. · Range: 0.1 – 0.99
`max_sentences`	number	no	`15`	AI-detection only. Cap on highlighted sentences. · Range: 1 – 50
`claim_extractor`	enum	no	`"claimbuster"`	sources only. claimbuster: extractive. llm_claim_extractor: LLM-based. · Allowed: `claimbuster`, `llm_claim_extractor`
`source_sentence`	string	no	—	sources scan only. Specific sentence to ground.
`max_sources`	number	no	`3`	sources scan only. Max grounding sources. · Range: 1 – 10
`disable_formatting`	boolean	no	false	Return raw upstream response.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/gptzero.