AI detection that explains its reasoning. Determine if content is human-written, AI-generated, or a collaboration.
Human or AI or Both is a free, serverless AI detection tool that analyzes text to determine whether it was written by a human, generated by AI, or created through human-AI collaboration. Unlike simple binary classifiers, this tool provides detailed explanations of its reasoning and highlights specific passages that exhibit AI or human characteristics.
AI detection cannot be exact. This tool provides probability estimates and pattern analysis, not definitive proof. No AI detector can achieve 100% accuracy because:
Use this tool as one input among many when evaluating content authenticity. The analysis is most useful for understanding why content exhibits certain patterns, not for definitive authorship claims.
Each analysis returns a Detection Score (0-100, where 0 = definitely human and 100 = definitely AI), a classification (Human, AI, or Collaboration), confidence level, detailed reasoning across multiple detection dimensions, highlighted passages with explanations, and suggestions for attestation via attest.ink.
There are two ways to analyze content:
The tool examines text across multiple dimensions including vocabulary patterns, sentence structure, coherence, factual claims, stylistic markers, and more. It returns a probabilistic assessment with detailed explanations.
The analysis evaluates:
The Analysis tab shows the overall score, classification, and detailed reasoning. The Highlights tab shows the original content with color-coded passages indicating AI-like (orange) or human-like (green) characteristics. The JSON tab provides the raw analysis data for programmatic use.
Puter GPT-OSS is the default and is completely free with no API key required. It uses Puter's user-pays model.
OpenRouter is recommended for users who want access to hundreds of models through a single API key. CORS-friendly.
Anthropic, OpenAI, Google Gemini, and Ollama are also supported.
For content you want to formally attest as human-created or AI-assisted, use attest.ink. It provides cryptographic attestations that can be independently verified.
The tool supports URL parameters for automation and sharing:
?content=your text here — Prefill the content input with text?url=https://example.com/article — Fetch content from a URL on page load&enter — Add this to auto-analyze after loading contentExamples:
?content=Hello world&enter — Analyze "Hello world" immediately?url=https://example.com/blog-post&enter — Fetch and analyze a blog postAll processing happens through the selected API provider. No data is stored on any server.
python3 -m http.server 8000 then open http://localhost:8000
Powered by Puter.com — free, no API key needed.
Runs locally on your machine — no API key, no data leaves your computer.
Ollama lets you run AI models locally on your own machine. No API key needed, no data leaves your computer, and it's completely free.
Browser requirement: When using Ollama from GitHub Pages (or any HTTPS URL), Google Chrome is required. Safari and other WebKit browsers block HTTPS pages from connecting to local HTTP servers.
curl -fsSL https://ollama.com/install.sh | sh
ollama pull gpt-oss:20b
pkill ollama OLLAMA_ORIGINS=* ollama serve
To make this permanent, add to your ~/.zshrc:
export OLLAMA_ORIGINS=*
Download the installer from ollama.com/download and run it.
ollama pull gpt-oss:20b
Stop-Process -Name ollama -Force $env:OLLAMA_ORIGINS="*"; ollama serve
To make permanent:
[System.Environment]::SetEnvironmentVariable("OLLAMA_ORIGINS", "*", "User")
curl -fsSL https://ollama.com/install.sh | sh
ollama pull gpt-oss:20b
sudo systemctl edit ollama
Add under [Service]:
[Service] Environment="OLLAMA_ORIGINS=*"
sudo systemctl restart ollama
http://localhost:11434Paste a blog post or article URL to automatically extract its main content.
Share this content as a prefilled analysis link.
The gpt-oss-120b model (117B parameters) produces the most thorough analysis but can take 30-60 seconds. If speed is more important, switch to the smaller model:
The 20b model is roughly 2-3x faster with slightly lower quality. Both are free through Puter.
You can run GPT-OSS locally for free using Ollama. No API key, no usage limits, no data leaves your computer.
Browser requirement: When using Ollama from GitHub Pages (or any HTTPS URL), Google Chrome is required.
1. Install Ollama:
curl -fsSL https://ollama.com/install.sh | sh
2. Pull GPT-OSS and start with browser access:
ollama pull gpt-oss:20b pkill ollama OLLAMA_ORIGINS=* ollama serve
1. Download from ollama.com/download and install.
2. In PowerShell:
ollama pull gpt-oss:20b Stop-Process -Name ollama -Force $env:OLLAMA_ORIGINS="*"; ollama serve
1. Install and configure:
curl -fsSL https://ollama.com/install.sh | sh ollama pull gpt-oss:20b sudo systemctl edit ollama # Add: Environment="OLLAMA_ORIGINS=*" sudo systemctl restart ollama
3. Click below to switch to Ollama:
Use attest.ink to create a cryptographic attestation of your content's authorship. Attestations provide verifiable proof that can be independently validated, unlike detection tools which only provide probability estimates.
Create attestation on attest.ink