by Microsoft

Azure AI Content Safety review, pricing and verdict

Microsoft's moderation API scores text and images for hate, sexual content, violence and self-harm on severity levels, trained on 8 languages.

Best for
Azure developer
Not for
Video platform trust and safety lead

Should you use Azure AI Content Safety?

Pick Azure AI Content Safety if your app runs on Azure and you moderate text and images in major European or Asian languages with graded severity. Skip it as your only tool for video, audio or child-safety detection, which its docs exclude. Its free tier stops when the monthly limit is reached.

Severity levels per harm category instead of a single flag.

Azure customers get it on their existing bill and region, and Microsoft Foundry offers the same service as guardrails for the models it hosts (Microsoft Learn, read 22 Nov 2026), while its lack of video, audio and CSAM detection sends media-heavy platforms elsewhere.

Also for

  • Chat app developer
  • Developers at social and gaming apps hosted on Azure
Show 3 more
  • Teams building chat apps on Microsoft Foundry
  • Marketplace moderation engineers working in European and Asian languages
  • Platform teams needing severity-based text and image filters

Main trade-off

Text and images only, and no child exploitation detection.

Azure AI Content Safety pricing

PlanMonthly priceWhat it includes
Free (F0)Free5,000 text records a month, 5,000 images a month, Usage stops at the limit, no overage, 5 requests a second
Commitment, image 250K$169/mo250,000 images a month, Overage $0.675 per 1,000 images
Commitment, text 1M$338/mo1 million text records a month, Overage $0.338 per 1,000 text records
Standard (S0)Custom$0.375 per 1,000 text records (East US), $0.75 per 1,000 images (East US), 1,000 requests per 10 seconds for text and image analysis

Free tier (F0): 5,000 text records and 5,000 images a month, with usage stopped at the limit. Standard (S0) pay as you go in East US: $0.375 per 1,000 text records and $0.75 per 1,000 images. A text record is up to 1,000 characters, so a 7,500-character input counts as 8. Commitment tiers: 1 million text records for $338 a month, 250,000 images for $169 a month.

Before you commit

  • Long text is billed per 1,000 characters, so a 7,500-character post costs eight text records, not one.

What Azure AI Content Safety does

Azure AI Content Safety is Microsoft's content moderation API. It rates user text and pictures in four harm categories, giving each a severity level instead of a single flag, and adds blocklists, Prompt Shields and custom categories. Microsoft says its models were trained and tested on eight languages.

  • Analyze text

    Scores text for hate, sexual content, violence and self-harm and returns a severity level per category, so you can set different cut-offs for each.

  • Analyze image

    Scores images in the same four categories with severity levels, using the same thresholds and blocklists as text.

  • Blocklists

    Custom lists of banned words and phrases run alongside the models for terms the categories do not cover.

  • Prompt Shields and protected material

    Checks user prompts for attacks on a language model and checks generated text for known lyrics, articles and recipes.

Show all 6 features
  • Custom categories (preview)

    Define and train your own content category, such as a platform-specific scam pattern, and scan text for matches.

  • Content Safety Studio

    A browser tool to test sensitivity levels on sample or uploaded text and images, watch block rates and export working code.

Works with

  • Microsoft Foundry guardrails
  • Azure OpenAI
  • Content Safety Studio

Capabilities

  • Content moderation
  • Text classification
  • Image classification
  • Prompt injection detection

Strengths and limits

Strengths

  • Severity levels per category let a platform allow mild violence in a game chat while blocking graphic violence, without writing its own scoring.
  • The free tier covers a small app or a full pilot, and usage simply stops at the limit instead of billing overage.
  • Teams already on Azure use their existing account, region choice and customer-managed keys rather than a new vendor.

Limits

  • Microsoft's docs state it cannot be used to detect child exploitation images, so a separate CSAM tool is required.
  • There is no video, audio or live-stream moderation API.
  • Rapid custom categories and groundedness detection are previews due to retire on 30 April 2027, so building on them carries a migration risk.

How Hokai rates it

  • Ease of use8.0 / 10
  • Features7.5 / 10
  • Value for money8.5 / 10
  • Support7.0 / 10

Azure AI Content Safety alternatives

ToolPrice fromFree planRuns onRating
Azure AI Content Safety This page$169/moYesWeb3.9
OpenAI Moderation APIPick Azure AI Content Safety if you want severity levels, blocklists and custom categories on Azure; pick the OpenAI Moderation API if a free flag per category is enough.FreeYesWeb3.8
SightenginePick Azure AI Content Safety for severity-graded text and images inside Azure; pick Sightengine if you also need video, live streams or audio.$29/moYesWeb3.9
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

Azure AI Content Safety facts

Works offline
No
Minimum skill level
Intermediate
Price band
Budget

Data and privacy

Proprietary

Questions about Azure AI Content Safety

How much does Azure AI Content Safety cost?

Pay-as-you-go pricing in East US is $0.375 for every thousand text records and $0.75 for every thousand images. Committed monthly bundles bring that down, at $338 for a million text records or $169 for 250,000 images. Each text record covers up to a thousand characters.

Is Azure AI Content Safety free?

Yes, the F0 tier is free each month up to its fixed allowance of text records and images. When you reach it, calls stop rather than running up overage, so it suits testing and small apps.

What are the severity levels in Azure AI Content Safety?

Every category the service checks comes back with a graded level rather than a yes or no. You choose the level at which to block in each one, for example blocking only severe violence in a game chat while letting mild cartoon violence through.

Which languages does Azure AI Content Safety support?

Microsoft says the models were trained and tested on Chinese, English, French, German, Spanish, Italian, Japanese and Portuguese. Other languages can work with varying quality, and protected material and groundedness detection are English only.

Can Azure AI Content Safety detect CSAM?

No. Microsoft's overview states the service cannot be used to detect illegal child exploitation images. Platforms need a dedicated child-safety tool for that.

About Azure AI Content Safety

Azure AI Content Safety is the moderation service in Microsoft's Azure cloud. It is sold as a standalone API and Studio, and the same service sits behind the guardrails Microsoft Foundry applies to the models it hosts. A team that already runs on Azure creates a Content Safety resource in a supported region and calls it with its existing account and billing.

Read the full background

The core is two calls. Analyze text and Analyze image each score content in four harm categories, hate, sexual, violence and self-harm, and return a severity level for each rather than a yes or no, so a platform can allow mild content and block severe content in the same category. Blocklists add your own banned terms. Around that sit features aimed at AI apps: Prompt Shields for injection attacks on a language model, protected material detection for lyrics and articles in generated text, a task adherence check for agents, and custom categories you define and train, currently in preview. The Studio lets a team test sensitivity levels on sample or uploaded content and export the code.

Its docs list eight trained languages, Chinese and Japanese among them alongside the main Western European ones, and warn that quality varies elsewhere; protected material, groundedness and standard custom categories are English only. That suits social, gaming and marketplace teams on Azure who moderate user text and images in those languages, and teams building chat apps who want one vendor for both user content and model guardrails.

Its limits are clear in its own docs. Child exploitation imagery is explicitly out of scope, so a platform needs a specialist such as Safer by Thorn, or the free CSAM image classifier that approved organisations can get alongside the OpenAI Moderation API. It has no video, audio or live-stream API, where Sightengine or Deploy Content Safety go further. Two preview features, rapid custom categories and groundedness detection, are scheduled to retire on 30 April 2027. Hokai lists the category in AI governance tools.

Sources and guides

More AI Tools on Hokai

  • CheckstepAI content moderation platform with review queues, appeals and EU DSA reporting built in, moderating text, images, video and audio in 100+ languages.
  • Deploy Content SafetyContent moderation APIs from Deploy, the company formerly called Hive, scoring images, video, text and audio from a portfolio of 20+ in-house models.
  • 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.