Unitary AI

Unitary is a London-based, Creandum-backed AI company that provides multimodal content classification and moderation as an API, analyzing video, image, audio, and text in context to detect harmful or policy-violating content at a scale of tens of millions of videos per day. The Unitary API at api.unitary.ai offers policy classification, granular Items and Characteristics signals, Detoxify text-toxicity scoring, and a Virtual Moderator endpoint that blends AI agents with human review, with results delivered by signed webhooks or polling. The company also maintains the popular open-source Detoxify Python library, and has expanded into AI Virtual Agents that automate manual workflows across insurance, financial services, healthcare, and marketplaces.

Unitary AI publishes 5 APIs on the APIs.io network, including API Authentication API, Detoxify API, Items & Characteristics API, and 2 more. Tagged areas include Company, Software-as-a-Service, Content Moderation, Trust and Safety, and Artificial Intelligence.

The Unitary AI catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Unitary AI’s developer surface includes documentation, getting-started guide, API reference, authentication, engineering blog, support, and 17 more developer resources.

🌐 Visit website 📡 Source on GitHub

34.7/100 thin ▬ flat Agent 26/100 agent aware Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

1 APIs

Company Software-as-a-Service Content Moderation Trust and Safety Artificial Intelligence Machine-Learning Computer-Vision Video Virtual Agents

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 34.7/100 · thin

Contract Quality 13.8 / 23

Developer Ergonomics 3.7 / 18

Access Clarity 3.3 / 18

Operational Transparency 1.2 / 12

Contract Governance 0.5 / 11

Discoverability 6.8 / 9

Create-or-Update Ergonomics 2.8 / 10

Agent readiness — 26/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/unitary-ai: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 5

Individual APIs this provider publishes, each with its own machine-readable definition.

Unitary AI API Authentication API

The API Authentication API from Unitary AI — 1 operation(s) for api authentication.

Unitary AI Detoxify API

The Detoxify API from Unitary AI — 2 operation(s) for detoxify.

Unitary AI Items & Characteristics API

The Items & Characteristics API from Unitary AI — 4 operation(s) for items & characteristics.

Unitary AI moderation API

The moderation API from Unitary AI — 1 operation(s) for moderation.

Unitary AI Policy Classification API

The Policy Classification API from Unitary AI — 6 operation(s) for policy classification.

Open Collections 6

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Unitary content classification API Authentication API

OPEN COLLECTION

Unitary content classification API Authentication Detoxify API

OPEN COLLECTION

Unitary content classification API Authentication Items & Characteristics API

OPEN COLLECTION

Unitary content classification API Authentication moderation API

OPEN COLLECTION

Unitary content classification API Authentication Policy Classification API

OPEN COLLECTION

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Unitary Ai Webhooks

ASYNCAPI

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Unitary Ai Authentication

http · 1 scheme

SECURITY

Unitary Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Unitary Ai Trust Center

trust center published

SECURITY

Resources

Get Started 1

Portal, sign-up, and the first successful call

GettingStarted

GettingStarted

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

WellKnown

WellKnown

X-MCPServerCandidate

X-MCPServerCandidate

LLMsTxt

LLMsTxt

AgentSkill

AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conformance

ErrorCatalog

Lifecycle

Conventions

Webhooks

DataModel

Build 2

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

TrustCenter

TrustCenter

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 1

Pricing, plans, and the legal terms of use

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: unitary-ai
deliveryModel:
  model: unknown
  open_source: false
  commercial: false
  callable_host: true
  label: Delivery model not determined — needs a product licence on record
  confidence: low
  source:
  - openapi
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/unitary-ai.png
name: Unitary AI
description: Unitary is a London-based, Creandum-backed AI company that provides multimodal content classification and moderation
  as an API, analyzing video, image, audio, and text in context to detect harmful or policy-violating content at a scale of
  tens of millions of videos per day. The Unitary API at api.unitary.ai offers policy classification, granular Items and Characteristics
  signals, Detoxify text-toxicity scoring, and a Virtual Moderator endpoint that blends AI agents with human review, with
  results delivered by signed webhooks or polling. The company also maintains the popular open-source Detoxify Python library,
  and has expanded into AI Virtual Agents that automate manual workflows across insurance, financial services, healthcare,
  and marketplaces.
url: https://raw.githubusercontent.com/api-evangelist/unitary-ai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- creandum
x-tier: profile
x-tier-reason: enriched-from-portfolio-lead
specificationVersion: '0.23'
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 19
  pass: local-v1
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Software-as-a-Service
- Content Moderation
- Trust and Safety
- Artificial Intelligence
- Machine-Learning
- Computer-Vision
- Video
- Virtual Agents
tags_raw:
- Company
- Saas
- Content Moderation
- Trust And Safety
- Artificial Intelligence
- Machine Learning
- Computer Vision
- Video
- Virtual Agents
apis:
- aid: unitary-ai:unitary-ai-api-authentication-api
  name: Unitary AI API Authentication API
  description: The API Authentication API from Unitary AI — 1 operation(s) for api authentication.
  humanURL: https://docs.unitary.ai/
  baseURL: https://api.unitary.ai/v1
  tags:
  - API / Authentication
  tags_raw:
  - API Authentication
  properties:
  - type: OpenAPI
    url: openapi/unitary-ai-api-authentication-api-openapi.yml
  - type: Documentation
    url: https://docs.unitary.ai/
- aid: unitary-ai:unitary-ai-detoxify-api
  name: Unitary AI Detoxify API
  description: The Detoxify API from Unitary AI — 2 operation(s) for detoxify.
  humanURL: https://docs.unitary.ai/
  baseURL: https://api.unitary.ai/v1
  tags:
  - Detoxify
  properties:
  - type: OpenAPI
    url: openapi/unitary-ai-detoxify-api-openapi.yml
  - type: Documentation
    url: https://docs.unitary.ai/
- aid: unitary-ai:unitary-ai-items-characteristics-api
  name: Unitary AI Items & Characteristics API
  description: The Items & Characteristics API from Unitary AI — 4 operation(s) for items & characteristics.
  humanURL: https://docs.unitary.ai/
  baseURL: https://api.unitary.ai/v1
  tags:
  - Items & Characteristics
  properties:
  - type: OpenAPI
    url: openapi/unitary-ai-items-characteristics-api-openapi.yml
  - type: Documentation
    url: https://docs.unitary.ai/
- aid: unitary-ai:unitary-ai-moderation-api
  name: Unitary AI moderation API
  description: The moderation API from Unitary AI — 1 operation(s) for moderation.
  humanURL: https://docs.unitary.ai/
  baseURL: https://api.unitary.ai/v1
  tags:
  - Moderation
  tags_raw:
  - moderation
  properties:
  - type: OpenAPI
    url: openapi/unitary-ai-moderation-api-openapi.yml
  - type: Documentation
    url: https://docs.unitary.ai/
- aid: unitary-ai:unitary-ai-policy-classification-api
  name: Unitary AI Policy Classification API
  description: The Policy Classification API from Unitary AI — 6 operation(s) for policy classification.
  humanURL: https://docs.unitary.ai/
  baseURL: https://api.unitary.ai/v1
  tags:
  - Policy Classification
  properties:
  - type: OpenAPI
    url: openapi/unitary-ai-policy-classification-api-openapi.yml
  - type: Documentation
    url: https://docs.unitary.ai/
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Overlay
  url: overlays/unitary-ai-content-classification-overlay.yaml
- type: Website
  url: https://www.unitary.ai/
- type: Documentation
  url: https://docs.unitary.ai/
- type: GettingStarted
  url: https://docs.unitary.ai/get-started/readme
- type: APIReference
  url: https://docs.unitary.ai/api-references/policy-classification
- type: Authentication
  url: authentication/unitary-ai-authentication.yml
- type: Blog
  url: https://www.unitary.ai/blog
- type: Support
  url: https://www.unitary.ai/contact-us
- type: GitHubOrganization
  url: https://github.com/unitaryai
- type: PrivacyPolicy
  url: https://www.unitary.ai/privacy-policy
- type: TrustCenter
  url: security/unitary-ai-trust-center.yml
- type: DomainSecurity
  url: security/unitary-ai-domain-security.yml
- type: Packages
  url: packages/unitary-ai-packages.yml
- type: WellKnown
  url: well-known/unitary-ai-well-known.yml
- type: X-MCPServerCandidate
  url: mcp/unitary-ai-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: LLMsTxt
  url: llms/unitary-ai-docs-llms.txt
- type: Conformance
  url: conformance/unitary-ai-conformance.yml
- type: ErrorCatalog
  url: errors/unitary-ai-problem-types.yml
- type: Lifecycle
  url: lifecycle/unitary-ai-lifecycle.yml
- type: Conventions
  url: conventions/unitary-ai-conventions.yml
- type: Webhooks
  url: asyncapi/unitary-ai-webhooks.yml
- type: DataModel
  url: data-model/unitary-ai-data-model.yml
- type: AgentSkill
  url: skills/_index.yml

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/unitary-ai"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/unitary-ai/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/unitary-ai/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.