by OpenAI

OpenAI Moderation API review, pricing and verdict

OpenAI's free moderation endpoint: the omni-moderation-latest model flags text and images across 13 harm categories, with no per-call charge.

Best for
Startup developer
Not for
Head of trust and safety at a video platform

Should you use OpenAI Moderation API?

Use the OpenAI Moderation API as a free first filter for text and images in any app, especially one already built on OpenAI. Do not rely on it alone for video, voice or platform-specific rules such as spam: it has none of those. Approved platforms also get a free CSAM image classifier.

Text and image moderation with no per-call charge.

Being free and already inside every OpenAI account makes it the default first layer, while its fixed categories and missing audio and video push serious platforms to add a paid vendor.

Also for

  • Chatbot developer
  • Developers adding a first moderation layer to a new app
Show 3 more
  • Teams building chatbots on OpenAI models
  • Small community and forum operators
  • Trust and safety teams needing a free CSAM image check

Main trade-off

Fixed categories with no audio, video or custom policies.

OpenAI Moderation API pricing

Free to use with an OpenAI API key, with no per-request charge. Images can be up to 20MB. The separate OpenAI CSAM Image Classifier is also free, for approved organisations only.

What OpenAI Moderation API does

The OpenAI Moderation API is a free classification endpoint from OpenAI. Its omni-moderation-latest model scores text and images for harassment, hate, illicit content, self-harm, sexual content and violence, returning a flag and a confidence score for each of 13 categories. It does not accept audio or video.

  • omni-moderation-latest

    One model that classifies both text and images and returns a flag, per-category results and per-category confidence scores.

  • Thirteen harm categories

    Harassment, hate, illicit content, self-harm, sexual content, sexual content involving minors and violence, each with sub-categories such as threats or instructions.

  • Input-type reporting

    Each score says whether it came from the text, the image or both, so mixed posts can be routed correctly.

  • Inline moderation

    The Responses and Chat Completions APIs can return moderation results for the prompt and the reply in the same call that generates the reply.

Show all 6 features
  • CSAM Image Classifier

    A separate model, omni-moderation-csam-latest, scores single images for potential CSAM and AI-generated CSAM for approved organisations.

  • SDKs in every major language

    Official examples for JavaScript, Python, Go, Java, C#, Ruby and plain curl call the same moderations endpoint.

Works with

  • OpenAI Responses API
  • OpenAI Chat Completions API

Capabilities

  • Content moderation
  • Text classification
  • Image classification
  • Csam detection

Strengths and limits

Strengths

  • It costs nothing per call, so a startup can screen every post and image from day one.
  • It covers text and images in one model, so a post with a caption is scored together rather than in two systems.
  • The CSAM Image Classifier gives approved platforms a free specialist check, where Deploy sells its Thorn-based CSAM detection through sales.

Limits

  • It has no audio, video or live-stream input, so voice and video platforms need a second vendor.
  • Categories are fixed: there is no way to add a platform-specific rule such as spam, scams or off-platform contact details.
  • OpenAI's docs warn that category scores can be recalibrated over time, so custom thresholds can drift without notice in your code.

How Hokai rates it

  • Ease of use9.0 / 10
  • Features6.5 / 10
  • Value for money9.5 / 10
  • Support5.5 / 10

OpenAI Moderation API alternatives

ToolPrice fromFree planRuns onRating
OpenAI Moderation API This pageFreeYesWeb3.8
SightenginePick the OpenAI Moderation API if text and images are all you need and the budget is zero; pick Sightengine if you need video, live streams, audio or custom lists.$29/moYesWeb3.9
Deploy Content SafetyPick the OpenAI Moderation API for a free first layer; pick Deploy Content Safety if you need audio, OCR, video and enterprise volume under contract.QuoteNoWeb3.6
ActiveFenceAlice's trust and safety service for user-generated content, pairing AI detection across 20+ abuse areas with threat intelligence and analyst teams.QuoteNoWeb3.9

OpenAI Moderation API facts

Works offline
No
Minimum skill level
Intermediate
Price band
Free

Data and privacy

Proprietary

Questions about OpenAI Moderation API

How much does the OpenAI Moderation API cost?

Nothing. OpenAI's moderation guide states that the endpoint is free to use, so there is no per-request bill. You need an OpenAI API key to call it.

Is the OpenAI Moderation API free for non-OpenAI content?

The docs present it as a general classifier for text and image inputs, not only for checking OpenAI model output, and they show it classifying standalone user content. Check OpenAI's usage policies for your own use case.

What categories does omni-moderation-latest detect?

Harassment, harassment with threats, hate, hate with threats, illicit, violent illicit, self-harm, self-harm intent, self-harm instructions, sexual, sexual involving minors, violence and graphic violence. Harassment and hate are scored on text only.

Can I send suspected CSAM to the OpenAI Moderation API?

No. The general model must not receive child sexual abuse material, known or suspected. Approved organisations can apply for the separate OpenAI CSAM Image Classifier, which returns signals for potential CSAM and potential AI-generated CSAM and does not report to authorities by itself.

Does the OpenAI Moderation API work on audio or video?

No. The current model takes text and images only. For video you would extract frames yourself, and for voice you would transcribe first, or use a vendor with native audio and video moderation.

About OpenAI Moderation API

The OpenAI Moderation API is the content classification endpoint that OpenAI offers to every developer with an API key. Its current model, omni-moderation-latest, reads text and images and returns a flagged verdict plus a score for each harm category. OpenAI does not charge for the endpoint, so it costs nothing to put in front of a paid vendor as a first layer.

Read the full background

A call returns three things: a top-level flagged value, a true or false per category, and a confidence score per category with the input types each score applied to. The categories cover harassment and threats, hate and hateful threats, illicit and violent-illicit content, self-harm, its intent and instructions, sexual content, sexual content involving minors, violence and graphic violence. Some are text-only: harassment and hate, for example, are not scored on images. Developers can also ask for moderation scores inline, in the same request that generates a model reply, through the Responses and Chat Completions APIs.

Child safety is handled apart. OpenAI's docs say never to send known or suspected CSAM to the general model; approved organisations can apply for the OpenAI CSAM Image Classifier, a separate model that is also free and scores an image for potential CSAM and potential AI-generated CSAM. Moderation platforms such as Checkstep have begun offering that classifier inside their own queues.

It is a classifier, not a moderation system. It has no audio or video input, no custom categories, no review queue and no appeals, and OpenAI warns that scores can be recalibrated over time, so thresholds built on them need re-testing. Platforms that need video, live streams or audio should compare Sightengine or Deploy Content Safety, and teams that need the workflow around the scores should look at platforms in AI governance tools.

Sources and guides

More AI Tools on Hokai

  • Azure AI Content SafetyMicrosoft's moderation API scores text and images for hate, sexual content, violence and self-harm on severity levels, trained on 8 languages.
  • CheckstepAI content moderation platform with review queues, appeals and EU DSA reporting built in, moderating text, images, video and audio in 100+ languages.
  • Safer by ThornChild-safety detection from the nonprofit Thorn: hash matching against 153.9M+ verified CSAM hashes plus AI classifiers for new images, video and text.
  • ToxModModulate's real-time voice chat moderation for games and social apps, with plans from a free Starter tier to 200,000 voice hours a month.
  • ReadilyAI compliance platform for healthcare payers that cites audit evidence and drafts policy redlines; one customer cut consulting spend $734K a year.
  • BotCityBotCity has raised $15.3M so IT teams can see and govern the Python code that AI copilots and staff quietly run on company endpoints.