Skip to content
SPECIFICTION
Get listed

Detoxify vs PicPurify

Detoxify

github.com

PicPurify

picpurify.com

Side by side

FigureDetoxifyPicPurify
Price fromFree$19/mo
Free planYesYes
Free trial—Yes
Open source——
Web—Yes
LinuxYes—
API—Yes
Self-hostedYes—
Plans published16
Spec score · Content Moderation Tools Software7.6 (#12)7.8 (#9)
Spec score · AI Content Moderation Software7.6 (#17)7.7 (#16)
PurposeDetoxify provides trained models and code to classify toxic comments from three Jigsaw challenges.PicPurify is a real-time image moderation API that detects and filters inappropriate user-generated images.

Plans

Detoxify

  • Open-source libraryFree

Detoxify pricing →

PicPurify

  • FREEFree
  • STARTER$19 a month
  • PRO$49 a month
  • ULTRA$99 a month
  • MEGA$249 a month
  • SUPRA$499 a month

PicPurify pricing →

In their own words

Detoxify

Detoxify is a free, self-hosted library that provides trained models and code to classify toxic comments. Its original, unbiased, and multilingual models are based on BERT, RoBERTa, and XLM-RoBERTa, respectively. Depending on the model, outputs include categories such as threats, obscenity, insults, identity attacks, and explicit sexual content. The multilingual model is intended for English, French, Spanish, Italian, Portuguese, Turkish, and Russian. The project describes research, fine-tuning on carefully constructed representative datasets, and helping moderators flag harmful content faster as intended uses. It can be installed with pip and called from Python to predict labels for one string or a list. Inference uses CPU by default and accepts a PyTorch device such as CUDA. The project warns that profanity-associated words may be labeled toxic regardless of tone or intent, potentially biasing results against vulnerable minority groups. Inference uses Transformers and PyTorch Lightning; training also requires the Kaggle API to download data. API access can be requested by email. The library is distributed under Apache-2.0.

Visit github.com

PicPurify

PicPurify is a real-time image moderation API for detecting and filtering inappropriate user-generated images. Its listed checks include porn, suggestive nudity, gore, money, weapons, drugs, hate symbols, obscene gestures, and QR codes. The API can also detect faces and return age-majority and gender classifications. It accepts JPG/JPEG, WEBP, PNG, BMP, TIFF, RAW, PDF, ICO, and GIF files, up to 4096×4096 pixels or 16 MB. The image API limit is five requests per second, which the maker says can be increased on request for legitimate reasons. Each task on an image uses one unit, so running multiple checks on the same image uses multiple units. Video moderation analyzes frames individually; its default interval is one frame per second, and charges depend on video size and frame interval. PicPurify says it can create a tailor-made model for specific detection needs. Integration examples are available for cURL, Python, Node.js, and PHP. The free plan includes 2,000 units with no time limit. Paid plans start at $19 per month.

Visit picpurify.com