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, Saas, 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 16 more developer resources.

🌐 Visit website 📡 Source on GitHub
43.2/100 thin ▬ flat Agent 61/100 agent native Full breakdown ↓
scored 2026-07-28 · rubric v0.5
AccessSelf serve
5 APIs 1 MCP Servers
CompanySaasContent ModerationTrust And SafetyArtificial IntelligenceMachine LearningComputer VisionVideoVirtual Agents

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-28 · rubric v0.5
Composite quality — 43.2/100 · thin
Contract Quality 16.0 / 25
Developer Ergonomics 11.7 / 20
Commercial Clarity 3.7 / 20
Operational Transparency 1.7 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 61/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 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 4 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. 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. Want it done for you? Prioritized profiling — $2,500 →

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.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

unitary-ai-mcp.yml

MCP SERVER

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
 MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conformance
Conformance
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conventions
Conventions
 Webhooks
Webhooks
 DataModel
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

Source (apis.yml)

apis.yml Raw ↑ 
aid: unitary-ai
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  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: '0.20'
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 19
  pass: local-v1
created: '2026-07-17'
modified: '2026-07-21'
tags:
- 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
  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
  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: 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: MCPServer
  url: mcp/unitary-ai-mcp.yml
- 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