Jentic OSThe workplace. An in-house AI platform for every employeeJentic OneSafe access. Agents reach your systems without holding keysJentic AIRThe foundation. Gets your existing platforms ready for AI
Pricing

GET STARTED

API DirectoryBrowse 10,000+ APIs ready for AI agent integrationDocumentationGuides and API reference

TOOLS

API ScoringCheck your AI readiness using our scorecardArazzo UIVisualize Arazzo workflows as interactive documentationArazzo EditorBuild and edit multi-step API workflows visually

COMMUNITY

GitHubOpen source projects and examplesOpen StandardsBuilt on open specs. Never locked in.
All ResourcesEverything in one placeBlogLatest articles and insightsTech Talk NewsletterAPIs, AI agents, architecture and strategyWebinarsLive sessions and on-demand recordingsReports & WhitepapersOriginal research on enterprise AI
About UsOur mission and teamCareersJoin our teamContactGet in touch
Try it now
Jentic OSJentic OneJentic AIR
Pricing
API DirectoryDocumentationAPI ScoringArazzo UIArazzo EditorGitHubOpen Standards
All ResourcesBlogTech Talk NewsletterWebinarsReports & Whitepapers
About UsCareersContact
Try it now
JenticJentic
Products
  • Jentic OS
  • Jentic One
  • Jentic AIR
For Developers
  • API Directory
  • Documentation
  • GitHub
Company
  • About Jentic
  • Careers
  • Contact Us
  • Trust Centre
ISO/IEC 27001:2022 certification badge issued by Prescient SecurityISO/IEC 27001:2022 certification badge issued by Prescient Security

Information Security Management System

Certified to ISO/IEC 27001:2022 by Prescient Security

AICPA SOC for Service Organizations logoAICPA SOC for Service Organizations logo

SOC 2® Type 1 report

Audited by Prescient Assurance

Terms & Conditions•Privacy Policy•
© 2026 Jentic Technology Ltd. All rights reserved.
2 Grattan Court East, Dublin, D02 VX86, Ireland
Switch to light modeSwitch to dark mode
APIs / AI/ML / Google / Perspective Comment Analyzer API
Perspective Comment Analyzer API logo

Google Perspective Comment Analyzer API

Browse all Google APIs
40
AI ReadinessFoundational (D-)40/100
See full scorecard
Official vendor OpenAPI document · agent-readyAI/MLMl Inferenceoauth22 EndpointsREST

For Agents

Score user-generated text for toxicity, insult, threat, and related attributes, and submit human-labeled feedback to improve the model. Lets agents triage harmful content in moderation pipelines.

Use for: I need to score a comment for toxicity, Check whether a message looks like an insult or threat, Analyze a forum post for severe toxicity, Submit a moderator's score back to Perspective for training

Not supported: Does not block, delete, or rewrite content, identify users, or detect spam beyond its trained attributes - use for scoring text on toxicity-related attributes only.

The Perspective Comment Analyzer API scores user-generated text on attributes such as toxicity, severe toxicity, insult, profanity, and threat. Built by Jigsaw and Google's Counter Abuse Technology team, it powers comment moderation for newsrooms, forums, and chat apps. Callers submit a comment and receive per-attribute probability scores and span-level annotations, plus a suggestscore endpoint to send labels back into the model's training pipeline.

Jentic One on GithubView OpenAPI Document

Install Jentic One Beta

Connect the Perspective Comment Analyzer API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Perspective Comment Analyzer API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

1

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fcommentanalyzer" | sh
2

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fcommentanalyzer" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Perspective Comment Analyzer API.

Score a comment on TOXICITY, SEVERE_TOXICITY, INSULT, THREAT, and PROFANITY attributes

Request span-level annotations for parts of a comment that triggered each score

Submit moderator-corrected scores back to the model via comments:suggestscore

Score text in multiple supported languages with a single request

Filter or route content based on per-attribute probability thresholds

Use Cases

Patterns agents use Perspective Comment Analyzer API for, with concrete tasks.

★ Pre-Publish Comment Moderation

Score every new comment with the analyze endpoint before it is shown to the public. Comments with toxicity probability above a threshold are routed to a human moderator queue, while clearly safe comments are published immediately. This lets community sites keep submission latency low without exposing readers to abuse.

Call comments:analyze with the comment text and the TOXICITY attribute, and route any comment with summaryScore.value > 0.7 to manual review

Real-Time Chat Filtering

Score chat messages as they are sent so the platform can soft-block or flag harmful content before it reaches recipients. Perspective returns per-attribute probabilities for TOXICITY, INSULT, THREAT, and PROFANITY in a single call, letting product teams build a tiered response (warn, hide, escalate) without retraining their own models.

Score every inbound chat message for INSULT and THREAT and hide messages where either summaryScore exceeds 0.85

Active Learning Feedback Loop

When human moderators override an automated decision, send their corrected score back to Perspective via comments:suggestscore. This signal is used by Jigsaw to improve future model versions on the attributes that matter most to your community, which keeps moderation quality high as language norms shift over time.

When a moderator marks an automated TOXICITY=0.9 decision as incorrect, call comments:suggestscore with the moderator's score of 0.1

Agent-Mediated Trust And Safety

An AI agent built into a community platform can call Perspective via Jentic to triage every report or new post, escalating only borderline cases to humans. Because Jentic returns the analyze schema, the agent can ask for the exact attributes it cares about and act on the structured probabilities directly.

Use Jentic to call comments:analyze for each reported post requesting attributes TOXICITY, SEVERE_TOXICITY, INSULT, THREAT, and surface any post where any attribute exceeds 0.8

Key Endpoints

2 endpoints — the perspective comment analyzer api scores user-generated text on attributes such as toxicity, severe toxicity, insult, profanity, and threat.

METHOD

PATH

DESCRIPTION

POST

/v1alpha1/comments:analyze

Score a comment on the requested attributes

POST

/v1alpha1/comments:suggestscore

Submit a corrected score for a previously analyzed comment

POST

/v1alpha1/comments:analyze

Score a comment on the requested attributes

POST

/v1alpha1/comments:suggestscore

Submit a corrected score for a previously analyzed comment

Jentic AI Readiness Score

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

P

Perspective Comment Analyzer API

- Foundational (D-)
40/100
73
Foundational Compliance
56
Developer Experience & Jentic Compatibility
17
AI-Readiness & Agent Experience
94
Agent Usability
63
Security
56
AI Discoverability
Powered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
73

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4
91%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

0%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

56

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: CSignals: 4
0%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

25%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

17

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4
70%

Description Coverage

Coverage of descriptions across API elements.

0%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

0%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

0%

Summary Coverage

Coverage of summaries across operations/tags/info.

94

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1
94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

63

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1
62%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

56

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: CSignals: 1
56%

Descriptive Richness

Clarity and depth of descriptions across API elements.

View full reportHow the score is calculatedMore about the dimensions

Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

Score your own APIScoring CLI agent skill
npx @jentic/api-scorecard-cli score <openapi-url>

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the Perspective Comment Analyzer API by hand means setting up Google OAuth 2.0, minting short-lived tokens, and posting each comment to commentanalyzer.googleapis.com yourself. Through Jentic you install once, import the Perspective Comment Analyzer API from the API Directory, store the OAuth credential once, and your agent calls it.

Permission scoping

Perspective takes the text to score in the request body rather than a resource id in the URL path, so limit the agent to the operations it needs, such as scoring a comment on toxicity attributes. You choose the operations it may call, so the score-suggestion operation is not included unless you add it.

Credential isolation

Your Perspective OAuth credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'score a comment for toxicity', and Jentic returns the matching Perspective operation with its input schema and supported attributes so the agent calls the right endpoint without browsing the reference docs.

Related APIs

Alternatives and complements available in the Jentic catalogue.

Complementary

Cloud Search API

→

Indexes the moderated content corpus that Perspective scores upstream

Use Cloud Search to expose moderated content for retrieval; use Perspective to filter what gets indexed

Complementary

Compute Engine API

→

Runs the moderation worker fleet that calls Perspective

Provision Compute Engine workers when you need to score very high volumes of content with parallel calls

Complementary

Cloud Tasks API

→

Throttles outbound calls to Perspective so you stay under its QPS quota

Use Cloud Tasks to rate-limit your scoring calls to Perspective during traffic spikes

FAQs

Specific to using Perspective Comment Analyzer API through Jentic.

What authentication does the Perspective Comment Analyzer API use?

It uses Google OAuth 2.0 with the cloud-platform scope, and Perspective additionally accepts API keys at the request level. Through Jentic the credential is stored encrypted in your Jentic One instance and the agent only sees scoped tokens at execution time.

Which attributes can the API score a comment on?

Common attributes include TOXICITY, SEVERE_TOXICITY, INSULT, IDENTITY_ATTACK, THREAT, and PROFANITY, with additional experimental attributes available for English text. The full list is supplied per-request via requestedAttributes in the comments:analyze body.

What are the rate limits for the Perspective API?

Perspective enforces a default per-project quota of one query per second, with higher limits available on request through the Perspective developer site. Batch your moderation calls and cache scores for repeated text to stay under the QPS ceiling.

How do I score a comment through Jentic?

Search Jentic for 'score comment for toxicity', load the comments:analyze schema, and execute the call against /v1alpha1/comments:analyze with the comment text and a requestedAttributes map. Jentic returns the schema so the agent fills only the attributes it cares about.

Is the Perspective API free?

Yes. Perspective is provided free of charge by Jigsaw within the published quotas. Higher-volume access requires a request through the Perspective developer portal.

Can I submit moderator decisions back to improve the model?

Yes. Call /v1alpha1/comments:suggestscore with the original comment, the requested attributes, and the corrected score from your moderator. Jigsaw uses these signals to retrain and improve future model versions.

Can I limit what my agent is allowed to do with the Perspective Comment Analyzer API?

Yes. Because you self-host Jentic One, your own rules decide which Perspective operations and credentials the agent may use. You can allow it to score comments on attributes like toxicity, insult, and threat via comments:analyze while withholding comments:suggestscore, so the agent cannot submit corrected scores back to the model unless you add that operation. Since Perspective takes the text to score in the request body rather than a resource id in the path, you scope access at the operation level and the stored OAuth credential is injected only at execution time.

GET STARTED

Start building with Perspective Comment Analyzer API

Explore with Jentic One
View OpenAPI Document