Back to openai-moderation
OpenAI /

AI
text-moderation

Closed SourceSpecializedtextUpdated July 14, 2026

text-moderation: OpenAI's Latest Moderation Model

Model Overview

text-moderation (also referred to as text-moderation-latest) is OpenAI's most recent content moderation API model, automatically updated to the latest version over time. It classifies text content into harmful categories including violence, self-harm, sexual content, harassment, and hate speech, returning per-category probability scores and an overall flagged verdict. Unlike the -stable variant, this endpoint receives automatic improvements as OpenAI updates their moderation capabilities.


✨ Key Features

Specification Table
FeatureDescription
Auto-UpdatedAlways reflects the latest improvements to OpenAI's moderation capabilities
Multi-CategoryClassifies across violence, self-harm, sexual, harassment, hate, and more
Per-Category ScoresReturns probability scores for each harm category individually
Free APIThe moderation endpoint is free to use via the OpenAI API
Continuous ImprovementBenefits from ongoing OpenAI safety research without API changes

🔗 Resources

Specification Table

📜 License & Access

Proprietary (Free) — Free to use via OpenAI API for moderation purposes.

You might also want to compare

Verified Sources

Model Specs

closed-source

Parameters

Unknown

Context Window

Unknown

License

Proprietary

Deployment

api-only

Resources & Links

Lineage

Model Family

Part of the openai-moderation family

Curator Notes

Bulk imported from OpenAI developer docs.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model