The request "NSFWmodel" names no specific product, so the best matches are dedicated NSFW detection models. Replicate hosts NSFW image and video detection models that can be run through its cloud API 1, and Hugging Face offers image classification models suited to content moderation 3. Azure AI Content Safety 2 and OpenAI's moderation endpoint 6 also classify harmful content in text and images.
A question back: Do you need an NSFW classifier for images, video, or text, and would you prefer a hosted API or a model you run yourself?
- 1
Replicatereplicate.comverified and signed
Hosts NSFW detection models, including NSFW image and video frame classifiers, runnable via its cloud API 1.
+14 community tools built for it
for agents: littletry/video-nsfw-filter · lucataco/nsfw_video_detection · falcons-ai/nsfw_image_detection
- 2
Hugging Facehuggingface.coverified and signed
Provides image classification models with pre-trained options usable for content moderation 3.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: image_classification · text_classification · image-classification
- 3
Azure AI Content Safetymicrosoft.comverified and signed
Analyzes text and images for harmful content through Azure AI Content Safety SDKs for TypeScript, Python and Java 2.
official:MCP server · Playwright MCP ServerSDK · markitdownlibrary · windows-sysCLI · playwright-mcppackage · Azure DevOps (ADO)+151 community tools built for it
for agents: azure-ai-contentsafety-ts · azure-ai-contentsafety-py · azure-ai-contentsafety-java
- 4
OpenAI Moderation APIopenai.comverified and signed
Classifies text against OpenAI's content policy for hate, violence and similar harm, via the createModeration endpoint 6.
official:MCP server · mcp-extensionsAPI · OpenAI APISDK · openailibrary · OpenAICLI · openai-whisper+177 community tools built for it
for agents: createModeration · classify_text · createClassification
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2Microsoft – AI, Cloud, Productivity, Computing, Gaming & Appsmicrosoft.com · read 2026-10-29
- 3Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 6Openaiopenai.com ·
For agents: the 10 actions behind this answer
littletry/video-nsfw-filter · littletry/video-nsfw-filter verified and signed
Detect NSFW content in sampled video frames with adjustable sensitivity, per-frame scores, and optional screenshots.
azure-ai-contentsafety-ts · azure-ai-contentsafety-ts verified and signed
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
image_classification · Hugging Face (Activepieces) verified and signed
Image Classification — Classify images with pre-trained models or custom categories - perfect for content moderation, automated tagging, and smart asset management
train_node_classification_model · neo4j-gds found in code, not yet checked
Train a node classification model on a projected graph and store it in the GDS model catalog under modelName.
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
createModeration · OpenAI API verified and signed
Classifies if text violates OpenAI's Content Policy
nemotron-policy-generator · nemotron-policy-generator verified and signed
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories
workers-ai-search-model · Cloudflare API verified and signed
Model Search
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
XLNet · sentence-transformers verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.