Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or “fisha” accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.
Top-level alias for options.support_threshold. Minimum severity to show crisis support resources (default: high). Critical always shows.
Available options:
low,
medium,
high,
critical
continuation_token
string
Opaque signed token from a previous /unsafe call. Carries derived analysis state — no message content is stored server-side.
reset_conversation
boolean
Discard any continuation_token and start a fresh conversation.
new_conversation
boolean
Cross into a new conversation WITHOUT discarding the sustained_hopelessness pattern carried in continuation_token — unlike reset_conversation, which discards everything. Requires continuation_token to also be set. Use this when a new conversation starts on your side (e.g. a new chat session days later) but you still want Tuteliq to notice if the same pattern keeps recurring across those sessions.
message_id
string
Optional customer-side message id for evidence pointers.
Maximum string length: 128
external_id
string
Your unique identifier (e.g. message ID, content ID) for correlating Tuteliq results with your own system. Echoed back in the response and included in webhook payloads so you can match alerts to the original content.
Maximum string length: 255
customer_id
string
Your end-customer identifier for multi-tenant / B2B2C scenarios. If you serve multiple customers (schools, apps, brands) from a single API key, set this to route webhook alerts to the correct customer. Echoed back in the response and included in webhook payloads as "customerId".
Maximum string length: 255
metadata
object
Arbitrary key-value pairs for additional context (e.g. { "channel": "discord", "region": "eu" }). Stored with the detection result, echoed in the response, and included in webhook payloads. Maximum 20 properties.
incident_moderation_enabled
boolean
Per-call override of your account incident logging setting. When set, it takes precedence over the account-level flag for THIS request: true forces the incident to be persisted, false suppresses persistence. Omit to use your account default (which itself defaults to enabled). Lets you control incident logging per request, e.g. suppress logging for test traffic.
attestation
boolean
Ask for a detection attestation: a signed, non-identifying statement of what this call detected, for a platform that may report it. Off unless set to true. Returned as attestation; when none can be produced it is null and attestation_reason says why. It proves what was detected, not that the detection is correct. Sandbox keys are never signed.
Response
200 - application/json
Default Response
urgency_kept
boolean
An urgent action that a declared setting would have lowered to review was kept, because the case is acute. Absent otherwise.
urgency_kept_reason
string
Human-readable explanation. Present only when urgency_kept is true.
conversation_type_in_effect
enum<string>
The declared setting in effect for this request, from context.conversation_type or, when the request sent none, from your account's default_conversation_type. Present whenever a setting was in effect, whether or not it changed the result; absent when none was. Unlike conversation_type_applied, which is present only when the setting changed routing.
Available options:
fraud_report,
abuse_report,
support_disclosure,
helpline,
clinical,
investigative,
legal,
advisory,
training,
journalism,
research,
moderation_review,
healthcare,
law_enforcement,
education,
family,
workplace,
dating,
adult_community,
direct_message,
group_chat,
public_post,
customer_service,
gaming_chat
conversation_type_source
enum<string>
Where conversation_type_in_effect came from: request (sent with this request), participants (the relationship declared in context.recipients) or account_default (your account's default_conversation_type). Present only with conversation_type_in_effect.
Available options:
request,
participants,
account_default
participants_applied
object
What the declared context.sender and context.recipients supplied to this request: the setting their relationship names, and a declared child's age group and age. Present only when something was applied.
Show child attributes
conversation_type_applied
string
Present only when a caller-declared context.conversation_type actually changed routing. Confirms the setting was taken into account, rather than leaving the platform to assume it was.
unsafe
boolean
Unsafe-content signal observed at ANY severity (including low / monitor cases). For production branching prefer recommended_action (flag_for_review / block / immediate_intervention), which is a stable enum, over the bare presence of a signal. SCOPED TO THIS ENDPOINT: false means no KOSA-category signal was found HERE, not that the content is safe. It is also false where the sender is describing a harm rather than being subject to it. Peer harassment and image-based abuse of a named person are scored by /safety/bullying, so do not read false as a clearance without also calling that endpoint or /api/v1/analyse/multi.
categories
string[]
severity
enum<string>
Available options:
low,
medium,
high,
critical
confidence
number
risk_score
number
rationale
string
recommended_action
enum<string>
Routing key, weakest to strongest: none, monitor, flag_for_review, block, immediate_intervention. Safe to switch on.
Available options:
none,
monitor,
flag_for_review,
block,
immediate_intervention
action_detail
string
Optional human-readable expansion of recommended_action for a moderator UI. Free text: do not branch on it.
context_factors
string[]
Named influences on the severity assessment, restricted to values that are safe to publish. Currently only stated_test_frame, set when the speaker themselves called this a test, demo or rehearsal. DESCRIPTIVE: the statement is still scored as if genuine, because presenting a disclosure as a test is also how a real one gets minimised, so this marks the frame for a reviewer rather than discounting it. Absent when nothing applies. ADVISORY: for a moderator UI and triage queues. Do not branch production logic on it; use recommended_action, which is a stable enum.
language
string
Language code used for analysis (auto-detected or provided)
language_status
enum<string>
Language support maturity: "stable" (en) or "beta" (all others)
Available options:
stable,
beta
credits_used
number
Number of credits consumed by this request
continuation_token
string
Signed token carrying derived analysis state for the next call. Server stores nothing.
continuation_expires_at
string
ISO 8601 expiry timestamp of the continuation_token.
state_source
enum<string>
How prior state was sourced.
Available options:
token,
fresh,
reset
trajectory_risk
number
Conversation-level risk 0-1, distinct from risk_score which scores only this message. Anchored on the highest severity seen so far and decaying slowly across benign turns. Absent on the first turn. Derived from the signed token: no message content is stored to produce it.
trajectory
enum<string>
Direction of travel across the conversation so far.
Available options:
rising,
stable,
declining,
none
severity_series
number[]
Per-turn severity, oldest first — the evidence behind trajectory_risk.
sustained_hopelessness_conversations
number
Count of distinct conversations, within the last 30 days, that named the hopelessness_sustained marker at least once. Only present when new_conversation has been used to cross at least one conversation boundary. recommended_action is floored to at least flag_for_review once this reaches 3.
escalation_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
escalation_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
third_party_concern
boolean
True when this detection rests on a child reporting, disclosing or reacting to a real risk involving somebody, rather than on anyone in the conversation enacting one -- a peer saying another child has self-harm marks, that a sibling is using again, that a suicide challenge is going round. Route these to a welfare/safeguarding queue rather than an intervention queue: the speaker is the person who spoke up, and the risk may belong to somebody who is not in the conversation. Set only when the verdict rests on that report: if the analysis independently called the content unsafe, this is absent and recommended_action carries the answer. This path itself raises neither severity nor action, but it is NOT a cap on the response -- always route on recommended_action, which can be anything up to immediate_intervention. Absent unless it applied.
third_party_concern_reason
string
Human-readable explanation. Present only when third_party_concern is true.
declared_age_overridden
boolean
True when the caller declared an adult age group but the speaker states a minor age in the message or in the earlier turns sent with it. The declared age was not used. Nothing is escalated by this on its own; the analysis runs as if no age had been sent. Worth investigating at your end: an age check that disagrees with what the user says is what a bypassed age verification looks like. A stated ADULT age never has this effect. Absent unless it applied.
declared_age_overridden_reason
string
Human-readable explanation. Present only when declared_age_overridden is true.
minor_disclosure
object
Present when the request declared an adult and the speaker says they are under 18, by stating an age or in other words. The declared adult age or setting was then not used, and declared_age_overridden says so. Never set by a stated adult age. Absent otherwise.
Show child attributes
minor_on_adult_platform_raised
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
minor_on_adult_platform_raised_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
protective_speech_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
protective_speech_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
number_coincidence_cleared
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
number_coincidence_cleared_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
figurative_low_mood_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
figurative_low_mood_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
ordinary_hyperbole_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
ordinary_hyperbole_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
banter_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
banter_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
no_child_shown_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
no_child_shown_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
conversation_distress_surfaced
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
conversation_distress_surfaced_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
logistics_only_capped
boolean
Adjustment the API applied to this result, reported for transparency. Descriptive only: route on recommended_action. Absent when it did not apply.
logistics_only_capped_reason
string
Human-readable explanation of the adjustment above. Present only when it applied.
profanity
object | null
Present only when options.flag_profanity (or the account-level default_flag_profanity setting) is true. Deterministic word-list result — additive, never affects unsafe/severity/risk_score/recommended_action.
Show child attributes
risk_terms
object | null
Present only when options.flag_risk_terms (or the account-level default_flag_risk_terms setting) is true. Deterministic drug/violence word-list result — additive, never affects unsafe/severity/risk_score/recommended_action. Purely lexical: can fire on benign uses of an included term.
Show child attributes
external_id
string
Echo of the external_id you provided in the request
customer_id
string
Echo of the customer_id you provided in the request
metadata
object
Echo of the metadata you provided in the request
support
object
Country-specific crisis helplines and response guidance (only included for high/critical severity)
Show child attributes
attestation
object | null
Present only when the request set attestation: true. Null when none could be produced; see attestation_reason.
Show child attributes
attestation_reason
enum<string>
Present only when an attestation was asked for and attestation is null: nothing_detected, endpoint_unsupported, not_attributable (the detector reads the speaker as the person it is happening to, a reporter or speaking of themselves: speaker_role experiencing, reporting_other or self_directed, or speaker_stance describing_third_party; always on social-engineering, app-fraud, gambling-harm, unsafe and distress-signals, which do not say who is speaking), signing_unavailable (signing or storage failed; the detection is unaffected) or sandbox.
Available options:
endpoint_unsupported,
nothing_detected,
not_attributable,
signing_unavailable,
sandbox
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Tuteliq","description":"Documentation for the Tuteliq API — AI-powered child safety detection and synthetic content analysis for text, voice, images, and video.","colors":{"primary":"#2DD4BF","light":"#5EEAD4","dark":"#14B8A6"},"logo":{"light":"https://mintcdn.com/tuteliqab/hdzalAxyQzAjfPhG/logo/light.svg?fit=max\u0026auto=format\u0026n=hdzalAxyQzAjfPhG\u0026q=85\u0026s=9eb846d75c78b0b0fda0a2ec08593138","dark":"https://mintcdn.com/tuteliqab/hdzalAxyQzAjfPhG/logo/dark.svg?fit=max\u0026auto=format\u0026n=hdzalAxyQzAjfPhG\u0026q=85\u0026s=15ca54dfeb7a464d2ccceea26d9238a2"},"favicon":"https://mintcdn.com/tuteliqab/ojO0FyWWHktOfRcE/favicon.svg?fit=max\u0026auto=format\u0026n=ojO0FyWWHktOfRcE\u0026q=85\u0026s=80290a1af52b2f0a15a8bf27d53160b0","api":{"playground":{"display":"interactive"},"examples":{"languages":["bash","javascript","python","kotlin","swift","csharp","dart"]}},"navbar":{"links":[{"href":"mailto:support@tuteliq.ai","label":"Support"}],"primary":{"type":"button","label":"Get API Key","href":"https://tuteliq.ai/dashboard"}},"footer":{"socials":{"x":"https://x.com/tuteliq","github":"https://github.com/Tuteliq","linkedin":"https://linkedin.com/company/tuteliq"}},"search":{"prompt":"Search Tuteliq docs..."},"seo":{},"icons":{"library":"fontawesome"},"styling":{"eyebrows":"breadcrumbs","codeblocks":"dark","latex":true},"contextual":{"options":["copy","view","chatgpt","claude","cursor","vscode"],"display":"header"},"metadata":{"timestamp":false},"navigation":{"global":{"anchors":[{"anchor":"API Status","icon":"signal","href":"https://tuteliq.ai/status"},{"anchor":"Dashboard","icon":"gauge","href":"https://tuteliq.ai/dashboard"}]},"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"tuteliqab","hasAudioNarration":false,"actualSubdomain":"tuteliqab","customDomains":["docs.tuteliq.ai"],"gitSource":{"type":"github","owner":"tuteliq","repo":"docs","deployBranch":"main","contentDirectory":"","isPrivate":false,"mountPath":"","label":""},"entitlements":{},"buildId":"6af81797dc14d847bbc354ec","clientVersion":"0.0.4143","searchFilterCounts":[{"language":"default","tag":"API Reference","count":141},{"language":"default","tag":"Guides","count":62},{"language":"default","tag":"Verification","count":18},{"language":"default","tag":"Compliance","count":15},{"language":"default","tag":"Advanced","count":15},{"language":"default","tag":"Account","count":14},{"language":"default","tag":"Getting Started","count":12},{"language":"default","tag":"Other","count":12},{"language":"default","tag":"Safety","count":12},{"language":"default","tag":"Admin","count":10}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[],"page":{"pagePath":"api-reference/safety/detect-kosa-aligned-harm-signals-in-text","slug":"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text","pageMetadata":{"title":"Detect KOSA-aligned harm signals in text","description":"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. **Pair it with `/safety/bullying`, or call `/api/v1/analyse/multi`.** Peer-to-peer harassment, exposure or \"fisha\" accounts, and image-based abuse of a named person are scored by `/safety/bullying`; grooming trajectories by `/safety/grooming`; extremist recruitment by `/safety/radicalisation`. This endpoint also reports `unsafe: false` where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/unsafe","href":"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text","autogeneratedByOpenApi":true},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx, jsxs: _jsxs} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n code: \"code\",\n p: \"p\",\n strong: \"strong\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsxs(_components.p, {\n children: [\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. \", _jsxs(_components.strong, {\n children: [\"Pair it with \", _jsx(_components.code, {\n children: \"/safety/bullying\"\n }), \", or call \", _jsx(_components.code, {\n children: \"/api/v1/analyse/multi\"\n }), \".\"]\n }), \" Peer-to-peer harassment, exposure or “fisha” accounts, and image-based abuse of a named person are scored by \", _jsx(_components.code, {\n children: \"/safety/bullying\"\n }), \"; grooming trajectories by \", _jsx(_components.code, {\n children: \"/safety/grooming\"\n }), \"; extremist recruitment by \", _jsx(_components.code, {\n children: \"/safety/radicalisation\"\n }), \". This endpoint also reports \", _jsx(_components.code, {\n children: \"unsafe: false\"\n }), \" where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\"]\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){return _jsx(_Fragment,{})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent}","frontmatter":{},"scope":{"codeStyling":"dark","config":{},"pageMetadata":{"title":"Detect KOSA-aligned harm signals in text","description":"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. **Pair it with `/safety/bullying`, or call `/api/v1/analyse/multi`.** Peer-to-peer harassment, exposure or \"fisha\" accounts, and image-based abuse of a named person are scored by `/safety/bullying`; grooming trajectories by `/safety/grooming`; extremist recruitment by `/safety/radicalisation`. This endpoint also reports `unsafe: false` where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/unsafe","href":"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text","autogeneratedByOpenApi":true}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[],"codeExamples":{}},"jsLinks":[],"openApiReferenceData":{"operation":{"summary":"Detect KOSA-aligned harm signals in text","tags":["Safety"],"description":"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. **Pair it with `/safety/bullying`, or call `/api/v1/analyse/multi`.** Peer-to-peer harassment, exposure or \"fisha\" accounts, and image-based abuse of a named person are scored by `/safety/bullying`; grooming trajectories by `/safety/grooming`; extremist recruitment by `/safety/radicalisation`. This endpoint also reports `unsafe: false` where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.","requestBody":"b988a91b-7ffd-4348-95d7-07e881d302d7","responses":{"200":"4aff3417-deef-49a5-8fd7-86bfed12c455"},"method":"post","type":"path","servers":["963ca56e-2bda-4677-a27f-d2700b52c03e","33199c6a-1a12-4967-ba40-a340db6e8222"],"security":["4e0cf0c4-6818-4ae1-920f-edcd6a9bd7f9","29a5b78a-2d1e-4978-9a2c-fe1fcfe7e329"],"path":"/api/v1/safety/unsafe","baseUrlOptions":["https://api.tuteliq.ai","http://localhost:3000"],"title":"Detect KOSA-aligned harm signals in text","codeSamples":[],"requestExampleLanguages":["bash","javascript","python","kotlin","swift","csharp","dart"],"requiredOnlyExamples":false,"requestExampleType":"generated","responseExampleType":"generated"},"dependencies":{"parameters":{},"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","required":["text"],"properties":{"text":{"type":"string","maxLength":10000,"description":"The content to analyze","isRequired":true,"uniqueKey":"text","typeLabel":"string"},"context":{"type":"object","properties":{"sender":{"type":"object","properties":{"role":{"type":"string","enum":["child","teen","adult","guardian","educator","staff","unknown"],"description":"Who this participant is, as your platform knows it.","uniqueKey":"context.sender.role","typeLabel":"enum\u003cstring>"},"age_group":{"type":"string","description":"This participant's age group, for example \"8-10\". For a child or teen it gives the child's age the detectors use.","uniqueKey":"context.sender.age_group","typeLabel":"string"}},"description":"The sender, as your platform knows them. Declared, like an age: never inferred from the text.","uniqueKey":"context.sender","typeLabel":"object"},"recipients":{"type":"array","maxItems":20,"items":{"type":"object","properties":{"role":{"type":"string","enum":["child","teen","adult","guardian","educator","staff","unknown"],"description":"Who this participant is, as your platform knows it.","uniqueKey":"context.recipients.items.[INDEX].role","typeLabel":"enum\u003cstring>"},"age_group":{"type":"string","description":"This participant's age group, for example \"8-10\". For a child or teen it gives the child's age the detectors use.","uniqueKey":"context.recipients.items.[INDEX].age_group","typeLabel":"string"},"relationship_to_sender":{"type":"string","enum":["guardian_of_sender","child_of_sender","sibling","peer","educator_of_sender","student_of_sender","staff","none","unknown"],"description":"How this recipient is related to the sender. `guardian_of_sender` or `child_of_sender` applies the `family` setting; `educator_of_sender` or `student_of_sender` applies `education`.","uniqueKey":"context.recipients.items.[INDEX].relationship_to_sender","typeLabel":"enum\u003cstring>"}},"uniqueKey":"context.recipients.items.[INDEX]","typeLabel":"object"},"description":"The recipients and how each is related to the sender. A declared relationship supplies the setting, and a declared child or teen supplies the child's age, where the request did not send them; `participants_applied` in the response says what was applied. It never excuses harm: a declared guardian or educator doing harm is flagged like anyone else.","uniqueKey":"context.recipients","typeLabel":"object[]"},"age_group":{"type":"string","description":"Age group (e.g., \"14-17\")","uniqueKey":"context.age_group","typeLabel":"string"},"ageGroup":{"type":"string","description":"Age group (camelCase alias, e.g., \"under 18\")","uniqueKey":"context.ageGroup","typeLabel":"string"},"language":{"type":"string","description":"Language code (e.g., \"en\"). 33 supported languages: en is stable, the other 32 are beta (ar, bg, ca, cs, da, de, el, es, et, fi, fr, ga, hr, hu, it, ja, ko, lt, lv, mt, nl, no, pl, pt, ro, ru, sk, sl, sv, tr, uk, zh). The code is the documented form; the English name of a supported language is also accepted (\"English\" as \"en\"). A region or script suffix is read as its base language (\"en-US\" as \"en\"), and \"nb\" or \"nn\" as \"no\". A value that is not supported is refused with a 400 that lists the supported codes. Omit the field, or send \"auto\", and the language is detected from the text.","uniqueKey":"context.language","typeLabel":"string"},"platform":{"type":"string","description":"Platform name (e.g., \"Discord\", \"Telegram\")","uniqueKey":"context.platform","typeLabel":"string"},"prior_messages":{"type":"array","maxItems":100,"items":{"type":"object","required":["role","text"],"properties":{"role":{"type":"string","description":"Role of the sender (e.g., \"user\", \"contact\", \"adult\", \"child\")","isRequired":true,"uniqueKey":"context.prior_messages.items.[INDEX].role","typeLabel":"string"},"text":{"type":"string","maxLength":10000,"description":"Message text","isRequired":true,"uniqueKey":"context.prior_messages.items.[INDEX].text","typeLabel":"string"},"timestamp":{"type":"string","description":"ISO 8601 timestamp of the message (optional)","uniqueKey":"context.prior_messages.items.[INDEX].timestamp","typeLabel":"string"}},"uniqueKey":"context.prior_messages.items.[INDEX]","typeLabel":"object"},"description":"Prior turns of this conversation, oldest first, submitted by you for this request only -- Tuteliq stores no message content, so nothing here is retained after the call completes. Use this when you already have the whole conversation in hand; use continuation_token instead when you are calling once per new message as it arrives.","uniqueKey":"context.prior_messages","typeLabel":"object[]"},"conversation_type":{"type":"string","enum":["fraud_report","abuse_report","support_disclosure","helpline","clinical","investigative","legal","advisory","training","journalism","research","moderation_review","healthcare","law_enforcement","education","family","workplace","dating","adult_community","direct_message","group_chat","public_post","customer_service","gaming_chat"],"description":"Optional, no default: omit it and behaviour is unchanged. The setting this conversation was captured in, declared by your platform from its own configuration, never from end-user input. A declared setting names the responsible party in the conversation: a counsellor or helpline worker (`helpline`, `clinical`), a clinician (`healthcare`), an officer or investigator (`law_enforcement`, `investigative`), an adviser taking a report (`fraud_report`, `abuse_report`, `support_disclosure`, `advisory`), a moderator (`moderation_review`), a lawyer, trainer, journalist or researcher (`legal`, `training`, `journalism`, `research`), a teacher, tutor or safeguarding lead (`education`), a parent or guardian (`family`). In any of these settings, a conversation in which a person is at risk, that responsible party is already handling it, and nothing is happening as the text is written, is kept visible at `monitor` without an alert, and `protective_speech_capped` says so. Harm being done in the conversation, by anyone including the responsible party, a person at risk with nobody acting, and anything acute alert as they would with no setting. On social engineering, app fraud, romance scam, mule recruitment, gambling harm and bullying, harm happening now to the writer, or to a specific other person the writer tells of, never ends below `flag_for_review` because of a setting, even with the responsible party handling it; `ongoing_harm_floor_applied` says when that held a result the setting would have lowered. Where the harm is discussed and not enacted (`fraud_report`, `abuse_report`, `support_disclosure`, `helpline`, `clinical`, `investigative`, `legal`, `advisory`, `training`, `journalism`, `research`, `moderation_review`) an urgent action is also capped to `flag_for_review`, and the response echoes `conversation_type_applied`. `direct_message`, `group_chat`, `public_post`, `customer_service` and `gaming_chat` change nothing. In `education` and `family` this applies only when the speaker is not the person at risk: a young person speaking for themselves to a teacher or a parent alerts as with no setting. Whenever a setting is in effect, from this field or from the account's `default_conversation_type`, the response names it in `conversation_type_in_effect` and says where it came from in `conversation_type_source`.","uniqueKey":"context.conversation_type","typeLabel":"enum\u003cstring>"},"minor_disclosure_check":{"type":"boolean","description":"Optional, off unless true. For a platform that suspects users may get past its age verification. When true and the request declares an adult (an adult `age_group`, `child_age` of 18 or more, or `conversation_type` `dating`, `adult_community` or `workplace`), one extra narrow reading asks whether the speaker says they are under 18 in other words than a stated age (a school year, parental controls, a milestone), beside the analysis. On a yes the analysis runs without the declared age and adult audience, `declared_age_overridden` and `minor_disclosure` say so, and on `dating` or `adult_community` a result that asked for nothing is raised to `flag_for_review` (`minor_on_adult_platform_raised`). With it on, a plainly stated minor age (\"im 15\") is reported in `minor_disclosure` and raised on `dating` or `adult_community` the same way, with no extra call. Omitted or false: no extra call and behaviour is unchanged. A plainly stated minor age (\"im 15\") drops the declared adult age whatever this is set to, as it always has.","uniqueKey":"context.minor_disclosure_check","typeLabel":"boolean"}},"uniqueKey":"context","typeLabel":"object"},"options":{"type":"object","properties":{"support_threshold":{"type":"string","enum":["low","medium","high","critical"],"description":"Minimum severity to show crisis support resources (default: high). Critical always shows.","uniqueKey":"options.support_threshold","typeLabel":"enum\u003cstring>"},"verdict_only":{"type":"boolean","default":false,"description":"Fast mode: skip generating `action_detail`, the moderator-guidance expansion of `recommended_action`. Lower latency and a smaller response; `rationale` (used for incident summaries) and the verdict itself (severity, categories, recommended_action, risk_score) are unchanged.","uniqueKey":"options.verdict_only","typeLabel":"boolean"},"flag_profanity":{"type":"boolean","description":"Additive, deterministic word-list flag for plain profanity/vulgarity. Adds `profanity` to the response; never affects `unsafe`, `severity`, `risk_score`, or `recommended_action`. Free — no extra credits. Not a harm classifier: does not cover slurs or hate speech, which the detector itself already handles with full context.","uniqueKey":"options.flag_profanity","typeLabel":"boolean"},"flag_risk_terms":{"type":"boolean","description":"Additive, deterministic word-list flag for bare drug and violence terms (e.g. \"cocaine\", \"kill\"). Adds `risk_terms` to the response; never affects `unsafe`, `severity`, `risk_score`, or `recommended_action`. Free — no extra credits. Purely lexical: WILL fire on benign uses of an included term (\"kill the lights\") since it cannot read context the way the detector itself does — combine with the detector’s own verdict for a stricter policy, don’t use in isolation as a block decision.","uniqueKey":"options.flag_risk_terms","typeLabel":"boolean"}},"uniqueKey":"options","typeLabel":"object"},"support_threshold":{"type":"string","enum":["low","medium","high","critical"],"description":"Top-level alias for options.support_threshold. Minimum severity to show crisis support resources (default: high). Critical always shows.","uniqueKey":"support_threshold","typeLabel":"enum\u003cstring>"},"continuation_token":{"type":"string","description":"Opaque signed token from a previous /unsafe call. Carries derived analysis state — no message content is stored server-side.","uniqueKey":"continuation_token","typeLabel":"string"},"reset_conversation":{"type":"boolean","description":"Discard any continuation_token and start a fresh conversation.","uniqueKey":"reset_conversation","typeLabel":"boolean"},"new_conversation":{"type":"boolean","description":"Cross into a new conversation WITHOUT discarding the sustained_hopelessness pattern carried in continuation_token — unlike reset_conversation, which discards everything. Requires continuation_token to also be set. Use this when a new conversation starts on your side (e.g. a new chat session days later) but you still want Tuteliq to notice if the same pattern keeps recurring across those sessions.","uniqueKey":"new_conversation","typeLabel":"boolean"},"message_id":{"type":"string","maxLength":128,"description":"Optional customer-side message id for evidence pointers.","uniqueKey":"message_id","typeLabel":"string"},"external_id":{"type":"string","maxLength":255,"description":"Your unique identifier (e.g. message ID, content ID) for correlating Tuteliq results with your own system. Echoed back in the response and included in webhook payloads so you can match alerts to the original content.","uniqueKey":"external_id","typeLabel":"string"},"customer_id":{"type":"string","maxLength":255,"description":"Your end-customer identifier for multi-tenant / B2B2C scenarios. If you serve multiple customers (schools, apps, brands) from a single API key, set this to route webhook alerts to the correct customer. Echoed back in the response and included in webhook payloads as \"customerId\".","uniqueKey":"customer_id","typeLabel":"string"},"metadata":{"type":"object","additionalProperties":true,"maxProperties":20,"description":"Arbitrary key-value pairs for additional context (e.g. { \"channel\": \"discord\", \"region\": \"eu\" }). Stored with the detection result, echoed in the response, and included in webhook payloads. Maximum 20 properties.","uniqueKey":"metadata","typeLabel":"object"},"incident_moderation_enabled":{"type":"boolean","description":"Per-call override of your account incident logging setting. When set, it takes precedence over the account-level flag for THIS request: true forces the incident to be persisted, false suppresses persistence. Omit to use your account default (which itself defaults to enabled). Lets you control incident logging per request, e.g. suppress logging for test traffic.","uniqueKey":"incident_moderation_enabled","typeLabel":"boolean"},"attestation":{"type":"boolean","description":"Ask for a detection attestation: a signed, non-identifying statement of what this call detected, for a platform that may report it. Off unless set to true. Returned as `attestation`; when none can be produced it is null and `attestation_reason` says why. It proves what was detected, not that the detection is correct. Sandbox keys are never signed.","uniqueKey":"attestation","typeLabel":"boolean"}},"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"text":"\u003cstring>","context":{"sender":{"age_group":"\u003cstring>"},"recipients":[{"age_group":"\u003cstring>"}],"age_group":"\u003cstring>","ageGroup":"\u003cstring>","language":"\u003cstring>","platform":"\u003cstring>","prior_messages":[{"role":"\u003cstring>","text":"\u003cstring>","timestamp":"\u003cstring>"}],"minor_disclosure_check":true},"options":{"verdict_only":false,"flag_profanity":true,"flag_risk_terms":true},"continuation_token":"\u003cstring>","reset_conversation":true,"new_conversation":true,"message_id":"\u003cstring>","external_id":"\u003cstring>","customer_id":"\u003cstring>","metadata":{},"incident_moderation_enabled":true,"attestation":true}}},"exampleType":"generated"}},"exampleType":"generated"},"responses":{"4aff3417-deef-49a5-8fd7-86bfed12c455":{"description":"Default Response","content":{"application/json":{"schema":{"type":"object","properties":{"urgency_kept":{"type":"boolean","description":"An urgent action that a declared setting would have lowered to review was kept, because the case is acute. Absent otherwise.","uniqueKey":"urgency_kept","typeLabel":"boolean"},"urgency_kept_reason":{"type":"string","description":"Human-readable explanation. Present only when urgency_kept is true.","uniqueKey":"urgency_kept_reason","typeLabel":"string"},"conversation_type_in_effect":{"type":"string","enum":["fraud_report","abuse_report","support_disclosure","helpline","clinical","investigative","legal","advisory","training","journalism","research","moderation_review","healthcare","law_enforcement","education","family","workplace","dating","adult_community","direct_message","group_chat","public_post","customer_service","gaming_chat"],"description":"The declared setting in effect for this request, from `context.conversation_type` or, when the request sent none, from your account's `default_conversation_type`. Present whenever a setting was in effect, whether or not it changed the result; absent when none was. Unlike `conversation_type_applied`, which is present only when the setting changed routing.","uniqueKey":"conversation_type_in_effect","typeLabel":"enum\u003cstring>"},"conversation_type_source":{"type":"string","enum":["request","participants","account_default"],"description":"Where `conversation_type_in_effect` came from: `request` (sent with this request), `participants` (the relationship declared in `context.recipients`) or `account_default` (your account's `default_conversation_type`). Present only with `conversation_type_in_effect`.","uniqueKey":"conversation_type_source","typeLabel":"enum\u003cstring>"},"participants_applied":{"type":"object","description":"What the declared `context.sender` and `context.recipients` supplied to this request: the setting their relationship names, and a declared child's age group and age. Present only when something was applied.","properties":{"conversation_type":{"type":"string","enum":["family","education"],"uniqueKey":"participants_applied.conversation_type","typeLabel":"enum\u003cstring>"},"age_group":{"type":"string","uniqueKey":"participants_applied.age_group","typeLabel":"string"},"child_age":{"type":"number","uniqueKey":"participants_applied.child_age","typeLabel":"number"}},"uniqueKey":"participants_applied","typeLabel":"object"},"conversation_type_applied":{"type":"string","description":"Present only when a caller-declared `context.conversation_type` actually changed routing. Confirms the setting was taken into account, rather than leaving the platform to assume it was.","uniqueKey":"conversation_type_applied","typeLabel":"string"},"unsafe":{"type":"boolean","description":"Unsafe-content signal observed at ANY severity (including low / monitor cases). For production branching prefer `recommended_action` (`flag_for_review` / `block` / `immediate_intervention`), which is a stable enum, over the bare presence of a signal. SCOPED TO THIS ENDPOINT: `false` means no KOSA-category signal was found HERE, not that the content is safe. It is also `false` where the sender is describing a harm rather than being subject to it. Peer harassment and image-based abuse of a named person are scored by `/safety/bullying`, so do not read `false` as a clearance without also calling that endpoint or `/api/v1/analyse/multi`.","uniqueKey":"unsafe","typeLabel":"boolean"},"categories":{"type":"array","items":{"type":"string","uniqueKey":"categories.items.[INDEX]","typeLabel":"string"},"uniqueKey":"categories","typeLabel":"string[]"},"severity":{"type":"string","enum":["low","medium","high","critical"],"uniqueKey":"severity","typeLabel":"enum\u003cstring>"},"confidence":{"type":"number","uniqueKey":"confidence","typeLabel":"number"},"risk_score":{"type":"number","uniqueKey":"risk_score","typeLabel":"number"},"rationale":{"type":"string","uniqueKey":"rationale","typeLabel":"string"},"recommended_action":{"type":"string","enum":["none","monitor","flag_for_review","block","immediate_intervention"],"description":"Routing key, weakest to strongest: `none`, `monitor`, `flag_for_review`, `block`, `immediate_intervention`. Safe to switch on.","uniqueKey":"recommended_action","typeLabel":"enum\u003cstring>"},"action_detail":{"type":"string","description":"Optional human-readable expansion of `recommended_action` for a moderator UI. Free text: do not branch on it.","uniqueKey":"action_detail","typeLabel":"string"},"context_factors":{"type":"array","items":{"type":"string","uniqueKey":"context_factors.items.[INDEX]","typeLabel":"string"},"description":"Named influences on the severity assessment, restricted to values that are safe to publish. Currently only `stated_test_frame`, set when the speaker themselves called this a test, demo or rehearsal. DESCRIPTIVE: the statement is still scored as if genuine, because presenting a disclosure as a test is also how a real one gets minimised, so this marks the frame for a reviewer rather than discounting it. Absent when nothing applies. ADVISORY: for a moderator UI and triage queues. Do not branch production logic on it; use `recommended_action`, which is a stable enum.","uniqueKey":"context_factors","typeLabel":"string[]"},"language":{"type":"string","description":"Language code used for analysis (auto-detected or provided)","uniqueKey":"language","typeLabel":"string"},"language_status":{"type":"string","enum":["stable","beta"],"description":"Language support maturity: \"stable\" (en) or \"beta\" (all others)","uniqueKey":"language_status","typeLabel":"enum\u003cstring>"},"credits_used":{"type":"number","description":"Number of credits consumed by this request","uniqueKey":"credits_used","typeLabel":"number"},"continuation_token":{"type":"string","description":"Signed token carrying derived analysis state for the next call. Server stores nothing.","uniqueKey":"continuation_token","typeLabel":"string"},"continuation_expires_at":{"type":"string","description":"ISO 8601 expiry timestamp of the continuation_token.","uniqueKey":"continuation_expires_at","typeLabel":"string"},"state_source":{"type":"string","enum":["token","fresh","reset"],"description":"How prior state was sourced.","uniqueKey":"state_source","typeLabel":"enum\u003cstring>"},"trajectory_risk":{"type":"number","description":"Conversation-level risk 0-1, distinct from `risk_score` which scores only this message. Anchored on the highest severity seen so far and decaying slowly across benign turns. Absent on the first turn. Derived from the signed token: no message content is stored to produce it.","uniqueKey":"trajectory_risk","typeLabel":"number"},"trajectory":{"type":"string","enum":["rising","stable","declining","none"],"description":"Direction of travel across the conversation so far.","uniqueKey":"trajectory","typeLabel":"enum\u003cstring>"},"severity_series":{"type":"array","items":{"type":"number","uniqueKey":"severity_series.items.[INDEX]","typeLabel":"number"},"description":"Per-turn severity, oldest first — the evidence behind `trajectory_risk`.","uniqueKey":"severity_series","typeLabel":"number[]"},"sustained_hopelessness_conversations":{"type":"number","description":"Count of distinct conversations, within the last 30 days, that named the hopelessness_sustained marker at least once. Only present when new_conversation has been used to cross at least one conversation boundary. recommended_action is floored to at least flag_for_review once this reaches 3.","uniqueKey":"sustained_hopelessness_conversations","typeLabel":"number"},"escalation_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"escalation_capped","typeLabel":"boolean"},"escalation_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"escalation_capped_reason","typeLabel":"string"},"third_party_concern":{"type":"boolean","description":"True when this detection rests on a child reporting, disclosing or reacting to a real risk involving somebody, rather than on anyone in the conversation enacting one -- a peer saying another child has self-harm marks, that a sibling is using again, that a suicide challenge is going round. Route these to a welfare/safeguarding queue rather than an intervention queue: the speaker is the person who spoke up, and the risk may belong to somebody who is not in the conversation. Set only when the verdict rests on that report: if the analysis independently called the content unsafe, this is absent and recommended_action carries the answer. This path itself raises neither severity nor action, but it is NOT a cap on the response -- always route on recommended_action, which can be anything up to immediate_intervention. Absent unless it applied.","uniqueKey":"third_party_concern","typeLabel":"boolean"},"third_party_concern_reason":{"type":"string","description":"Human-readable explanation. Present only when third_party_concern is true.","uniqueKey":"third_party_concern_reason","typeLabel":"string"},"declared_age_overridden":{"type":"boolean","description":"True when the caller declared an adult age group but the speaker states a minor age in the message or in the earlier turns sent with it. The declared age was not used. Nothing is escalated by this on its own; the analysis runs as if no age had been sent. Worth investigating at your end: an age check that disagrees with what the user says is what a bypassed age verification looks like. A stated ADULT age never has this effect. Absent unless it applied.","uniqueKey":"declared_age_overridden","typeLabel":"boolean"},"declared_age_overridden_reason":{"type":"string","description":"Human-readable explanation. Present only when declared_age_overridden is true.","uniqueKey":"declared_age_overridden_reason","typeLabel":"string"},"minor_disclosure":{"type":"object","description":"Present when the request declared an adult and the speaker says they are under 18, by stating an age or in other words. The declared adult age or setting was then not used, and `declared_age_overridden` says so. Never set by a stated adult age. Absent otherwise.","properties":{"detected":{"type":"boolean","description":"Always true when the object is present.","isRequired":true,"uniqueKey":"minor_disclosure.detected","typeLabel":"boolean"},"evidence_type":{"type":"string","enum":["stated_age","school_year","parental_control","age_milestone","life_stage","other"],"description":"What showed it: `stated_age`, `school_year`, `parental_control`, `age_milestone`, `life_stage` or `other`.","isRequired":true,"uniqueKey":"minor_disclosure.evidence_type","typeLabel":"enum\u003cstring>"},"message_index":{"type":"integer","description":"0-based index into the turns read (earlier turns first, the message last; for grooming, `messages`).","isRequired":true,"uniqueKey":"minor_disclosure.message_index","typeLabel":"integer"},"suggested_age_group":{"type":"string","description":"The value to send back as `context.age_group` on this user's later requests. Tuteliq stores nothing: your platform carries the signal forward. Always a minor band, never an adult value: `under 18` by default, or `under 13`, `13-15` or `16-17` when the speaker stated an age. Sent back, it is read as a minor age group, so a minor's protections apply, and with `conversation_type` `dating`, `adult_community` or `workplace` the declared child beats the setting: the adult audience is not used.","isRequired":true,"uniqueKey":"minor_disclosure.suggested_age_group","typeLabel":"string"},"reason":{"type":"string","description":"Human-readable explanation. Never quotes the message.","isRequired":true,"uniqueKey":"minor_disclosure.reason","typeLabel":"string"}},"required":["detected","evidence_type","message_index","suggested_age_group","reason"],"uniqueKey":"minor_disclosure","typeLabel":"object"},"minor_on_adult_platform_raised":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"minor_on_adult_platform_raised","typeLabel":"boolean"},"minor_on_adult_platform_raised_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"minor_on_adult_platform_raised_reason","typeLabel":"string"},"protective_speech_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"protective_speech_capped","typeLabel":"boolean"},"protective_speech_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"protective_speech_capped_reason","typeLabel":"string"},"number_coincidence_cleared":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"number_coincidence_cleared","typeLabel":"boolean"},"number_coincidence_cleared_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"number_coincidence_cleared_reason","typeLabel":"string"},"figurative_low_mood_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"figurative_low_mood_capped","typeLabel":"boolean"},"figurative_low_mood_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"figurative_low_mood_capped_reason","typeLabel":"string"},"ordinary_hyperbole_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"ordinary_hyperbole_capped","typeLabel":"boolean"},"ordinary_hyperbole_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"ordinary_hyperbole_capped_reason","typeLabel":"string"},"banter_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"banter_capped","typeLabel":"boolean"},"banter_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"banter_capped_reason","typeLabel":"string"},"no_child_shown_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"no_child_shown_capped","typeLabel":"boolean"},"no_child_shown_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"no_child_shown_capped_reason","typeLabel":"string"},"conversation_distress_surfaced":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"conversation_distress_surfaced","typeLabel":"boolean"},"conversation_distress_surfaced_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"conversation_distress_surfaced_reason","typeLabel":"string"},"logistics_only_capped":{"type":"boolean","description":"Adjustment the API applied to this result, reported for transparency. Descriptive only: route on `recommended_action`. Absent when it did not apply.","uniqueKey":"logistics_only_capped","typeLabel":"boolean"},"logistics_only_capped_reason":{"type":"string","description":"Human-readable explanation of the adjustment above. Present only when it applied.","uniqueKey":"logistics_only_capped_reason","typeLabel":"string"},"profanity":{"oneOf":[{"type":"object","description":"Present only when options.flag_profanity (or the account-level default_flag_profanity setting) is true. Deterministic word-list result — additive, never affects unsafe/severity/risk_score/recommended_action.","properties":{"detected":{"type":"boolean","uniqueKey":"profanity.oneOf.0.detected","typeLabel":"boolean"},"matches":{"type":"array","items":{"type":"string","uniqueKey":"profanity.oneOf.0.matches.items.[INDEX]","typeLabel":"string"},"uniqueKey":"profanity.oneOf.0.matches","typeLabel":"string[]"}},"uniqueKey":"profanity.oneOf.0","typeLabel":"object"},{"type":"null","description":"Present only when options.flag_profanity (or the account-level default_flag_profanity setting) is true. Deterministic word-list result — additive, never affects unsafe/severity/risk_score/recommended_action.","properties":{"detected":{"type":"boolean"},"matches":{"type":"array","items":{"type":"string"}}},"uniqueKey":"profanity.oneOf.1","typeLabel":"null"}],"uniqueKey":"profanity","typeLabel":"object | null"},"risk_terms":{"oneOf":[{"type":"object","description":"Present only when options.flag_risk_terms (or the account-level default_flag_risk_terms setting) is true. Deterministic drug/violence word-list result — additive, never affects unsafe/severity/risk_score/recommended_action. Purely lexical: can fire on benign uses of an included term.","properties":{"detected":{"type":"boolean","uniqueKey":"risk_terms.oneOf.0.detected","typeLabel":"boolean"},"matches":{"type":"array","items":{"type":"object","properties":{"term":{"type":"string","uniqueKey":"risk_terms.oneOf.0.matches.items.[INDEX].term","typeLabel":"string"},"category":{"type":"string","enum":["drug","violence"],"uniqueKey":"risk_terms.oneOf.0.matches.items.[INDEX].category","typeLabel":"enum\u003cstring>"}},"uniqueKey":"risk_terms.oneOf.0.matches.items.[INDEX]","typeLabel":"object"},"uniqueKey":"risk_terms.oneOf.0.matches","typeLabel":"object[]"}},"uniqueKey":"risk_terms.oneOf.0","typeLabel":"object"},{"type":"null","description":"Present only when options.flag_risk_terms (or the account-level default_flag_risk_terms setting) is true. Deterministic drug/violence word-list result — additive, never affects unsafe/severity/risk_score/recommended_action. Purely lexical: can fire on benign uses of an included term.","properties":{"detected":{"type":"boolean"},"matches":{"type":"array","items":{"type":"object","properties":{"term":{"type":"string"},"category":{"type":"string","enum":["drug","violence"]}}}}},"uniqueKey":"risk_terms.oneOf.1","typeLabel":"null"}],"uniqueKey":"risk_terms","typeLabel":"object | null"},"external_id":{"type":"string","description":"Echo of the external_id you provided in the request","uniqueKey":"external_id","typeLabel":"string"},"customer_id":{"type":"string","description":"Echo of the customer_id you provided in the request","uniqueKey":"customer_id","typeLabel":"string"},"metadata":{"type":"object","additionalProperties":true,"description":"Echo of the metadata you provided in the request","uniqueKey":"metadata","typeLabel":"object"},"support":{"type":"object","description":"Country-specific crisis helplines and response guidance (only included for high/critical severity)","properties":{"country":{"type":"string","uniqueKey":"support.country","typeLabel":"string"},"country_name":{"type":"string","uniqueKey":"support.country_name","typeLabel":"string"},"emergency_number":{"type":"string","uniqueKey":"support.emergency_number","typeLabel":"string"},"helplines":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","uniqueKey":"support.helplines.items.[INDEX].name","typeLabel":"string"},"number":{"type":"string","uniqueKey":"support.helplines.items.[INDEX].number","typeLabel":"string"},"description":{"type":"string","uniqueKey":"support.helplines.items.[INDEX].description","typeLabel":"string"},"category":{"type":"string","uniqueKey":"support.helplines.items.[INDEX].category","typeLabel":"string"},"available":{"type":"string","uniqueKey":"support.helplines.items.[INDEX].available","typeLabel":"string"}},"uniqueKey":"support.helplines.items.[INDEX]","typeLabel":"object"},"uniqueKey":"support.helplines","typeLabel":"object[]"},"response_guide":{"type":"object","properties":{"category":{"type":"string","uniqueKey":"support.response_guide.category","typeLabel":"string"},"immediateActions":{"type":"array","items":{"type":"string","uniqueKey":"support.response_guide.immediateActions.items.[INDEX]","typeLabel":"string"},"uniqueKey":"support.response_guide.immediateActions","typeLabel":"string[]"},"resources":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","uniqueKey":"support.response_guide.resources.items.[INDEX].name","typeLabel":"string"},"description":{"type":"string","uniqueKey":"support.response_guide.resources.items.[INDEX].description","typeLabel":"string"},"url":{"type":"string","uniqueKey":"support.response_guide.resources.items.[INDEX].url","typeLabel":"string"}},"uniqueKey":"support.response_guide.resources.items.[INDEX]","typeLabel":"object"},"uniqueKey":"support.response_guide.resources","typeLabel":"object[]"}},"uniqueKey":"support.response_guide","typeLabel":"object"}},"uniqueKey":"support","typeLabel":"object"},"attestation":{"oneOf":[{"type":"object","additionalProperties":false,"description":"Present only when the request set `attestation: true`. Null when none could be produced; see `attestation_reason`.","properties":{"v":{"type":"string","enum":["tlq-att-1"],"uniqueKey":"attestation.oneOf.0.v","typeLabel":"enum\u003cstring>"},"harm_descriptor":{"type":"string","description":"What was detected, non-identifying by construction.","uniqueKey":"attestation.oneOf.0.harm_descriptor","typeLabel":"string"},"external_ref":{"type":"string","description":"Your external_id, echoed verbatim. Not covered by the signature, and never stored by Tuteliq.","uniqueKey":"attestation.oneOf.0.external_ref","typeLabel":"string"},"detector":{"type":"object","additionalProperties":false,"properties":{"model_id":{"type":"string","uniqueKey":"attestation.oneOf.0.detector.model_id","typeLabel":"string"},"model_version":{"type":"string","uniqueKey":"attestation.oneOf.0.detector.model_version","typeLabel":"string"},"prompt_template_version":{"type":"string","uniqueKey":"attestation.oneOf.0.detector.prompt_template_version","typeLabel":"string"},"endpoint":{"type":"string","uniqueKey":"attestation.oneOf.0.detector.endpoint","typeLabel":"string"}},"uniqueKey":"attestation.oneOf.0.detector","typeLabel":"object"},"operating_point":{"type":"object","additionalProperties":{"type":"number","uniqueKey":"attestation.oneOf.0.operating_point.additionalProperties","typeLabel":"number"},"uniqueKey":"attestation.oneOf.0.operating_point","typeLabel":"object"},"detected_at":{"type":"string","description":"RFC 3339, to the second.","uniqueKey":"attestation.oneOf.0.detected_at","typeLabel":"string"},"disclosure_url":{"type":"string","description":"Where this detector's published performance, including known weaknesses, is.","uniqueKey":"attestation.oneOf.0.disclosure_url","typeLabel":"string"},"limits":{"type":"array","items":{"type":"string","uniqueKey":"attestation.oneOf.0.limits.items.[INDEX]","typeLabel":"string"},"description":"What the attestation does not prove, carried inside it.","uniqueKey":"attestation.oneOf.0.limits","typeLabel":"string[]"},"signature":{"type":"object","additionalProperties":false,"properties":{"algorithm":{"type":"string","uniqueKey":"attestation.oneOf.0.signature.algorithm","typeLabel":"string"},"key_id":{"type":"string","uniqueKey":"attestation.oneOf.0.signature.key_id","typeLabel":"string"},"signature":{"type":"string","uniqueKey":"attestation.oneOf.0.signature.signature","typeLabel":"string"},"signed_at":{"type":"string","uniqueKey":"attestation.oneOf.0.signature.signed_at","typeLabel":"string"}},"uniqueKey":"attestation.oneOf.0.signature","typeLabel":"object"}},"uniqueKey":"attestation.oneOf.0","typeLabel":"object"},{"type":"null","additionalProperties":false,"description":"Present only when the request set `attestation: true`. Null when none could be produced; see `attestation_reason`.","properties":{"v":{"type":"string","enum":["tlq-att-1"]},"harm_descriptor":{"type":"string","description":"What was detected, non-identifying by construction."},"external_ref":{"type":"string","description":"Your external_id, echoed verbatim. Not covered by the signature, and never stored by Tuteliq."},"detector":{"type":"object","additionalProperties":false,"properties":{"model_id":{"type":"string"},"model_version":{"type":"string"},"prompt_template_version":{"type":"string"},"endpoint":{"type":"string"}}},"operating_point":{"type":"object","additionalProperties":{"type":"number"}},"detected_at":{"type":"string","description":"RFC 3339, to the second."},"disclosure_url":{"type":"string","description":"Where this detector's published performance, including known weaknesses, is."},"limits":{"type":"array","items":{"type":"string"},"description":"What the attestation does not prove, carried inside it."},"signature":{"type":"object","additionalProperties":false,"properties":{"algorithm":{"type":"string"},"key_id":{"type":"string"},"signature":{"type":"string"},"signed_at":{"type":"string"}}}},"uniqueKey":"attestation.oneOf.1","typeLabel":"null"}],"uniqueKey":"attestation","typeLabel":"object | null"},"attestation_reason":{"type":"string","enum":["endpoint_unsupported","nothing_detected","not_attributable","signing_unavailable","sandbox"],"description":"Present only when an attestation was asked for and `attestation` is null: `nothing_detected`, `endpoint_unsupported`, `not_attributable` (the detector reads the speaker as the person it is happening to, a reporter or speaking of themselves: `speaker_role` experiencing, reporting_other or self_directed, or `speaker_stance` describing_third_party; always on social-engineering, app-fraud, gambling-harm, unsafe and distress-signals, which do not say who is speaking), `signing_unavailable` (signing or storage failed; the detection is unaffected) or `sandbox`.","uniqueKey":"attestation_reason","typeLabel":"enum\u003cstring>"}},"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"urgency_kept":true,"urgency_kept_reason":"\u003cstring>","conversation_type_in_effect":"fraud_report","conversation_type_source":"request","participants_applied":{"conversation_type":"family","age_group":"\u003cstring>","child_age":123},"conversation_type_applied":"\u003cstring>","unsafe":true,"categories":["\u003cstring>"],"severity":"low","confidence":123,"risk_score":123,"rationale":"\u003cstring>","recommended_action":"none","action_detail":"\u003cstring>","context_factors":["\u003cstring>"],"language":"\u003cstring>","language_status":"stable","credits_used":123,"continuation_token":"\u003cstring>","continuation_expires_at":"\u003cstring>","state_source":"token","trajectory_risk":123,"trajectory":"rising","severity_series":[123],"sustained_hopelessness_conversations":123,"escalation_capped":true,"escalation_capped_reason":"\u003cstring>","third_party_concern":true,"third_party_concern_reason":"\u003cstring>","declared_age_overridden":true,"declared_age_overridden_reason":"\u003cstring>","minor_disclosure":{"detected":true,"evidence_type":"stated_age","message_index":123,"suggested_age_group":"\u003cstring>","reason":"\u003cstring>"},"minor_on_adult_platform_raised":true,"minor_on_adult_platform_raised_reason":"\u003cstring>","protective_speech_capped":true,"protective_speech_capped_reason":"\u003cstring>","number_coincidence_cleared":true,"number_coincidence_cleared_reason":"\u003cstring>","figurative_low_mood_capped":true,"figurative_low_mood_capped_reason":"\u003cstring>","ordinary_hyperbole_capped":true,"ordinary_hyperbole_capped_reason":"\u003cstring>","banter_capped":true,"banter_capped_reason":"\u003cstring>","no_child_shown_capped":true,"no_child_shown_capped_reason":"\u003cstring>","conversation_distress_surfaced":true,"conversation_distress_surfaced_reason":"\u003cstring>","logistics_only_capped":true,"logistics_only_capped_reason":"\u003cstring>","profanity":{"detected":true,"matches":["\u003cstring>"]},"risk_terms":{"detected":true,"matches":[{"term":"\u003cstring>","category":"drug"}]},"external_id":"\u003cstring>","customer_id":"\u003cstring>","metadata":{},"support":{"country":"\u003cstring>","country_name":"\u003cstring>","emergency_number":"\u003cstring>","helplines":[{"name":"\u003cstring>","number":"\u003cstring>","description":"\u003cstring>","category":"\u003cstring>","available":"\u003cstring>"}],"response_guide":{"category":"\u003cstring>","immediateActions":["\u003cstring>"],"resources":[{"name":"\u003cstring>","description":"\u003cstring>","url":"\u003cstring>"}]}},"attestation":{"v":"tlq-att-1","harm_descriptor":"\u003cstring>","external_ref":"\u003cstring>","detector":{"model_id":"\u003cstring>","model_version":"\u003cstring>","prompt_template_version":"\u003cstring>","endpoint":"\u003cstring>"},"operating_point":{},"detected_at":"\u003cstring>","disclosure_url":"\u003cstring>","limits":["\u003cstring>"],"signature":{"algorithm":"\u003cstring>","key_id":"\u003cstring>","signature":"\u003cstring>","signed_at":"\u003cstring>"}},"attestation_reason":"endpoint_unsupported"}}},"exampleType":"generated"}},"exampleType":"generated"}},"security":{"4e0cf0c4-6818-4ae1-920f-edcd6a9bd7f9":{"bearerAuth":{"type":"http","scheme":"bearer","description":"API key as Bearer token","scopes":[],"schemeName":"bearerAuth"}},"29a5b78a-2d1e-4978-9a2c-fe1fcfe7e329":{"apiKeyHeader":{"type":"apiKey","in":"header","name":"x-api-key","description":"API key in header","scopes":[],"schemeName":"apiKeyHeader"}}},"servers":{"963ca56e-2bda-4677-a27f-d2700b52c03e":{"url":"https://api.tuteliq.ai","description":"Production server"},"33199c6a-1a12-4967-ba40-a340db6e8222":{"url":"http://localhost:3000","description":"Development server"}},"processedSecurityOptions":[{"schemes":[{"scheme":{"type":"http","scheme":"bearer","description":"API key as Bearer token","scopes":[],"schemeName":"bearerAuth"},"schema":{"title":"Bearer Auth","type":"string","isRequired":true,"description":"API key as Bearer token","format":"bearer","typeLabel":"string\u003cbearer>","deprecated":false},"schemeName":"bearerAuth","name":"Authorization"}],"title":"bearerAuth"},{"schemes":[{"scheme":{"type":"apiKey","in":"header","name":"x-api-key","description":"API key in header","scopes":[],"schemeName":"apiKeyHeader"},"schema":{"title":"x-api-key","type":"string","description":"API key in header","isRequired":true,"typeLabel":"string","deprecated":false},"schemeName":"apiKeyHeader","name":"x-api-key"}],"title":"apiKeyHeader"}]},"originalFileLocation":"openapi.json"},"subdomain":"tuteliqab","siteName":"Tuteliq","title":"Detect KOSA-aligned harm signals in text - Tuteliq","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-11-14T08:11:09.643Z","originalFileLocation":"api-reference/safety/detect-kosa-aligned-harm-signals-in-text.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or \u0026quot;fisha\u0026quot; accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\">\u003cmeta data-mint-head name=\"application-name\" content=\"Tuteliq\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Detect KOSA-aligned harm signals in text - Tuteliq\">\u003cmeta data-mint-head property=\"og:description\" content=\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or \u0026quot;fisha\u0026quot; accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Tuteliq\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://tuteliqab.mintlify.site/_mintlify/api/og/v2?division=Safety\u0026amp;title=Detect+KOSA-aligned+harm+signals+in+text\u0026amp;description=Comprehensive+safety+analysis+covering+all+KOSA+harm+categories%3A+self-harm+and+suicidal+ideation%2C+eating+disorders%2C+substance+use%2C+depression%2Fanxiety+indicators\u0026amp;theme=b1c2e2e516957331fbc00107\u0026amp;signature=a1c71cfd70a79127046757a0454e7cad91432d1eb7fd8698f1926601bdb5ab39\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Detect KOSA-aligned harm signals in text - Tuteliq\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or \u0026quot;fisha\u0026quot; accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://tuteliqab.mintlify.site/_mintlify/api/og/v2?division=Safety\u0026amp;title=Detect+KOSA-aligned+harm+signals+in+text\u0026amp;description=Comprehensive+safety+analysis+covering+all+KOSA+harm+categories%3A+self-harm+and+suicidal+ideation%2C+eating+disorders%2C+substance+use%2C+depression%2Fanxiety+indicators\u0026amp;theme=b1c2e2e516957331fbc00107\u0026amp;signature=a1c71cfd70a79127046757a0454e7cad91432d1eb7fd8698f1926601bdb5ab39\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/tuteliqab/a-CVBRHabZUe6nPE/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Tuteliq\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#2DD4BF\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.tuteliq.ai/#organization\",\"name\":\"Tuteliq\",\"url\":\"https://docs.tuteliq.ai\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/tuteliqab/hdzalAxyQzAjfPhG/logo/light.svg?fit=max\u0026auto=format\u0026n=hdzalAxyQzAjfPhG\u0026q=85\u0026s=9eb846d75c78b0b0fda0a2ec08593138\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.tuteliq.ai#website\",\"name\":\"Tuteliq\",\"url\":\"https://docs.tuteliq.ai\",\"publisher\":{\"@id\":\"https://docs.tuteliq.ai/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text#webpage\",\"url\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text\",\"name\":\"Detect KOSA-aligned harm signals in text\",\"description\":\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or \\\"fisha\\\" accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\",\"dateModified\":\"2026-11-14T08:11:09.643Z\",\"isPartOf\":{\"@id\":\"https://docs.tuteliq.ai#website\"},\"breadcrumb\":{\"@id\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Safety\",\"item\":\"https://docs.tuteliq.ai/api-reference/safety/detect-bullying-harassment-and-intimidation-in-text\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Detect KOSA-aligned harm signals in text\",\"item\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text\"}]},{\"@type\":[\"TechArticle\",\"APIReference\"],\"@id\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text#apireference\",\"headline\":\"Detect KOSA-aligned harm signals in text\",\"name\":\"Detect KOSA-aligned harm signals in text\",\"description\":\"Comprehensive safety analysis covering all KOSA harm categories: self-harm and suicidal ideation, eating disorders, substance use, depression/anxiety indicators, compulsive usage patterns, sexual content, violence, and hate speech. Returns categorized findings with age-calibrated severity scoring. This is the recommended STARTING endpoint for broad content moderation, not a complete safety layer on its own. Pair it with /safety/bullying, or call /api/v1/analyse/multi. Peer-to-peer harassment, exposure or \\\"fisha\\\" accounts, and image-based abuse of a named person are scored by /safety/bullying; grooming trajectories by /safety/grooming; extremist recruitment by /safety/radicalisation. This endpoint also reports unsafe: false where the sender is DESCRIBING a harm rather than being subject to it (survivor testimony, news, a lesson, a child relaying something seen elsewhere), which is deliberate and keeps protective speech out of your queue, but means a message another detector would flag can come back clear here. Measured on our published kids-online-slang set, every case in that shape was caught by a sibling detector. If you call only this endpoint you inherit that boundary.\",\"url\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text\",\"mainEntityOfPage\":{\"@id\":\"https://docs.tuteliq.ai/api-reference/safety/detect-kosa-aligned-harm-signals-in-text#webpage\"},\"dateModified\":\"2026-11-14T08:11:09.643Z\",\"publisher\":{\"@id\":\"https://docs.tuteliq.ai/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.tuteliq.ai#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Tuteliq\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Tuteliq\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text.md","siteName":"Tuteliq","nav":{"global":{"anchors":[{"anchor":"API Status","icon":"signal","href":"https://tuteliq.ai/status"},{"anchor":"Dashboard","icon":"gauge","href":"https://tuteliq.ai/dashboard"}]},"tabs":[{"tab":"Guides","pages":[{"title":"Guides","href":""}]},{"tab":"API Reference","groups":[{"group":"Overview","pages":[{"title":"API Reference","sidebarTitle":"Overview","icon":"code","href":"/api-reference/introduction"}]},{"group":"Safety","pages":[{"title":"Detect bullying, harassment, and intimidation in text","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/bullying","href":"/api-reference/safety/detect-bullying-harassment-and-intimidation-in-text"},{"title":"Analyze a PDF or image for safety and compliance concerns","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/document","href":"/api-reference/safety/analyze-a-pdf-or-image-for-safety-and-compliance-concerns"},{"title":"Detect grooming patterns in conversations","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/grooming","href":"/api-reference/safety/detect-grooming-patterns-in-conversations"},{"title":"Analyze image for visual and textual safety concerns","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/image","href":"/api-reference/safety/analyze-image-for-visual-and-textual-safety-concerns"},{"title":"Read a display name and return a signal","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/nickname","href":"/api-reference/safety/read-a-display-name-and-return-a-signal"},{"title":"Detect AI-generated or synthetic content","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/synthetic-content","href":"/api-reference/safety/detect-ai-generated-or-synthetic-content"},{"title":"Detect AI-generated or cloned voice audio","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/synthetic-content/audio","href":"/api-reference/safety/detect-ai-generated-or-cloned-voice-audio"},{"title":"Detect AI-generated or synthetic images","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/synthetic-content/image","href":"/api-reference/safety/detect-ai-generated-or-synthetic-images"},{"title":"Detect deepfake or AI-generated video","description":"Multi-signal forensic video analysis: per-frame semantic analysis, temporal face consistency, lip-sync correlation, audio spectral analysis, and transcription. Classifies as confirmed_synthetic, suspected_synthetic, unknown, or confirmed_authentic.","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/synthetic-content/video","href":"/api-reference/safety/detect-deepfake-or-ai-generated-video"},{"title":"Detect KOSA-aligned harm signals in text","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/unsafe","href":"/api-reference/safety/detect-kosa-aligned-harm-signals-in-text"},{"title":"Analyze video for visual safety concerns across extracted frames","description":"Upload a video file (mp4, webm, quicktime, avi — max 100MB, max 10 min). Extracts key frames at even intervals and runs vision analysis on each frame. Returns per-frame results, flagged timestamps, and an aggregated overall risk score. Ideal for moderating uploaded video content, screen recordings, and video messages.","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/video","href":"/api-reference/safety/analyze-video-for-visual-safety-concerns-across-extracted-frames"},{"title":"Analyze voice/audio for safety concerns with transcription","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/voice","href":"/api-reference/safety/analyze-voiceaudio-for-safety-concerns-with-transcription"}]},{"group":"Fraud","pages":[{"title":"Detect app fraud and financial scam patterns","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/fraud/app-fraud","href":"/api-reference/fraud/detect-app-fraud-and-financial-scam-patterns"},{"title":"Detect money mule recruitment attempts","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/fraud/mule-recruitment","href":"/api-reference/fraud/detect-money-mule-recruitment-attempts"},{"title":"Detect romance scam indicators in conversation","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/fraud/romance-scam","href":"/api-reference/fraud/detect-romance-scam-indicators-in-conversation"},{"title":"Detect social engineering tactics in text","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/fraud/social-engineering","href":"/api-reference/fraud/detect-social-engineering-tactics-in-text"}]},{"group":"Safety Extended","pages":[{"title":"Detect coercive control patterns","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/coercive-control","href":"/api-reference/safety-extended/detect-coercive-control-patterns"},{"title":"Detect linguistic distress-signal patterns (pre-vulnerability indicators)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/distress-signals","href":"/api-reference/safety-extended/detect-linguistic-distress-signal-patterns-pre-vulnerability-indicators"},{"title":"Detect gambling harm indicators","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/gambling-harm","href":"/api-reference/safety-extended/detect-gambling-harm-indicators"},{"title":"Detect radicalisation and extremism indicators","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/radicalisation","href":"/api-reference/safety-extended/detect-radicalisation-and-extremism-indicators"},{"title":"Detect tech-facilitated gender-based violence","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/tfgbv","href":"/api-reference/safety-extended/detect-tech-facilitated-gender-based-violence"},{"title":"Detect exploitation of vulnerable individuals","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/safety/vulnerability-exploitation","href":"/api-reference/safety-extended/detect-exploitation-of-vulnerable-individuals"}]},{"group":"Analyse","pages":[{"title":"Fan-out analysis across multiple detection endpoints","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/detection/multi","href":"/api-reference/analyse/fan-out-analysis-across-multiple-detection-endpoints"},{"title":"Fan-out analysis across multiple detection endpoints","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/detection/multi","href":"/api-reference/analyse/fan-out-analysis-across-multiple-detection-endpoints"}]},{"group":"Privacy","pages":[{"title":"Remove personal data from a text or a conversation","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/privacy/redact","href":"/api-reference/privacy/remove-personal-data-from-a-text-or-a-conversation"}]},{"group":"Analysis","pages":[{"title":"Analyze emotional patterns and mental health indicators in conversation","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/analysis/emotions","href":"/api-reference/analysis/analyze-emotional-patterns-and-mental-health-indicators-in-conversation"}]},{"group":"Guidance","pages":[{"title":"Generate age-appropriate action plan for a safety situation","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/guidance/action-plan","href":"/api-reference/guidance/generate-age-appropriate-action-plan-for-a-safety-situation"}]},{"group":"Reports","pages":[{"title":"Generate professional incident report from conversation data","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/reports/incident","href":"/api-reference/reports/generate-professional-incident-report-from-conversation-data"}]},{"group":"Batch","pages":[{"title":"Analyze up to 50 items in a single request","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/batch/analyze","href":"/api-reference/batch/analyze-up-to-50-items-in-a-single-request"}]},{"group":"Webhooks","pages":[{"title":"Delete a webhook","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/webhooks/{webhookId}","href":"/api-reference/webhooks/delete-a-webhook"},{"title":"List all webhooks","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/webhooks/","href":"/api-reference/webhooks/list-all-webhooks"},{"title":"Create a webhook","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/webhooks/","href":"/api-reference/webhooks/create-a-webhook"},{"title":"Test a webhook","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/webhooks/test","href":"/api-reference/webhooks/test-a-webhook"},{"title":"Regenerate webhook secret","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/webhooks/{webhookId}/regenerate-secret","href":"/api-reference/webhooks/regenerate-webhook-secret"},{"title":"Update a webhook","deprecated":null,"version":null,"openapi":"/openapi.json put /api/v1/webhooks/{webhookId}","href":"/api-reference/webhooks/update-a-webhook"}]},{"group":"Usage","pages":[{"title":"Get usage breakdown by tool and endpoint","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/usage/by-tool","href":"/api-reference/usage/get-usage-breakdown-by-tool-and-endpoint"},{"title":"Get usage history over time","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/usage/history","href":"/api-reference/usage/get-usage-history-over-time"},{"title":"Get monthly billing period usage and upgrade recommendations","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/usage/monthly","href":"/api-reference/usage/get-monthly-billing-period-usage-and-upgrade-recommendations"},{"title":"Get real-time rate limit and quota status","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/usage/quota","href":"/api-reference/usage/get-real-time-rate-limit-and-quota-status"},{"title":"Get daily usage summary with quota status","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/usage/summary","href":"/api-reference/usage/get-daily-usage-summary-with-quota-status"}]},{"group":"Policy","pages":[{"title":"Get current detection policy configuration","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/policy/","href":"/api-reference/policy/get-current-detection-policy-configuration"},{"title":"Update detection policy configuration","deprecated":null,"version":null,"openapi":"/openapi.json put /api/v1/policy/","href":"/api-reference/policy/update-detection-policy-configuration"}]},{"group":"Pricing","pages":[{"title":"Get pricing plans","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/pricing/","href":"/api-reference/pricing/get-pricing-plans"},{"title":"Get detailed pricing plans","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/pricing/details","href":"/api-reference/pricing/get-detailed-pricing-plans"}]},{"group":"Account","pages":[{"title":"Withdraw consent for a processing purpose","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/account/consent/{type}","href":"/api-reference/account/withdraw-consent-for-a-processing-purpose"},{"title":"Exercise Right to Erasure (GDPR Article 17)","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/account/data","href":"/api-reference/account/exercise-right-to-erasure-gdpr-article-17"},{"title":"Revoke the customer-registered public key","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/account/encryption-key","href":"/api-reference/account/revoke-the-customer-registered-public-key"},{"title":"Revoke an MCP session token","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/account/mcp-tokens/{tokenId}","href":"/api-reference/account/revoke-an-mcp-session-token"},{"title":"Get API key count quota for current tier","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/api-keys/quota","href":"/api-reference/account/get-api-key-count-quota-for-current-tier"},{"title":"View your account audit trail","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/audit-logs","href":"/api-reference/account/view-your-account-audit-trail"},{"title":"Get current consent status","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/consent","href":"/api-reference/account/get-current-consent-status"},{"title":"Get the customer-registered public key for end-to-end incident encryption","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/encryption-key","href":"/api-reference/account/get-the-customer-registered-public-key-for-end-to-end-incident-encryption"},{"title":"Export all account data (GDPR Article 20)","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/export","href":"/api-reference/account/export-all-account-data-gdpr-article-20"},{"title":"List MCP session tokens","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/account/mcp-tokens","href":"/api-reference/account/list-mcp-session-tokens"},{"title":"Rectify account data (GDPR Article 16)","deprecated":null,"version":null,"openapi":"/openapi.json patch /api/v1/account/data","href":"/api-reference/account/rectify-account-data-gdpr-article-16"},{"title":"Rename an MCP session token","deprecated":null,"version":null,"openapi":"/openapi.json patch /api/v1/account/mcp-tokens/{tokenId}","href":"/api-reference/account/rename-an-mcp-session-token"},{"title":"Record user consent","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/account/consent","href":"/api-reference/account/record-user-consent"},{"title":"Register (or rotate) the public key Tuteliq uses to encrypt your incident records","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/account/encryption-key","href":"/api-reference/account/register-or-rotate-the-public-key-tuteliq-uses-to-encrypt-your-incident-records"}]},{"group":"Compliance","pages":[{"title":"Get Data Processing Agreement summary","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/compliance/dpa","href":"/api-reference/compliance/get-data-processing-agreement-summary"},{"title":"Get data retention schedule","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/compliance/retention","href":"/api-reference/compliance/get-data-retention-schedule"},{"title":"List current sub-processors","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/compliance/sub-processors","href":"/api-reference/compliance/list-current-sub-processors"}]},{"group":"Admin","pages":[{"title":"Delete known-synthetic perceptual hashes","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/admin/retention/phash","href":"/api-reference/admin/delete-known-synthetic-perceptual-hashes"},{"title":"List all recorded breach incidents","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/admin/breach/","href":"/api-reference/admin/list-all-recorded-breach-incidents"},{"title":"Get breach incident details","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/admin/breach/{id}","href":"/api-reference/admin/get-breach-incident-details"},{"title":"Cloud IDS threat statistics","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/admin/ids/stats","href":"/api-reference/admin/cloud-ids-threat-statistics"},{"title":"List Cloud IDS threats","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/admin/ids/threats","href":"/api-reference/admin/list-cloud-ids-threats"},{"title":"Get Cloud IDS threat details","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/admin/ids/threats/{id}","href":"/api-reference/admin/get-cloud-ids-threat-details"},{"title":"Update breach status and notification progress","deprecated":null,"version":null,"openapi":"/openapi.json patch /api/v1/admin/breach/{id}","href":"/api-reference/admin/update-breach-status-and-notification-progress"},{"title":"Log a new data breach incident","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/admin/breach/","href":"/api-reference/admin/log-a-new-data-breach-incident"},{"title":"Cloud IDS Pub/Sub push endpoint","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/admin/ids/webhook","href":"/api-reference/admin/cloud-ids-pubsub-push-endpoint"},{"title":"Trigger manual data retention cleanup","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/admin/retention/cleanup","href":"/api-reference/admin/trigger-manual-data-retention-cleanup"}]},{"group":"Health","pages":[{"title":"Health check","deprecated":null,"version":null,"openapi":"/openapi.json get /health","href":"/api-reference/health/health-check"},{"title":"Dependency status (admin)","deprecated":null,"version":null,"openapi":"/openapi.json get /health/dependencies","href":"/api-reference/health/dependency-status-admin"},{"title":"Liveness probe","deprecated":null,"version":null,"openapi":"/openapi.json get /live","href":"/api-reference/health/liveness-probe"},{"title":"Readiness probe","deprecated":null,"version":null,"openapi":"/openapi.json get /ready","href":"/api-reference/health/readiness-probe"}]},{"group":"Status","pages":[{"title":"API landing page","deprecated":null,"version":null,"openapi":"/openapi.json get /","href":"/api-reference/status/api-landing-page"},{"title":"Get API status and component health","deprecated":null,"version":null,"openapi":"/openapi.json get /status","href":"/api-reference/status/get-api-status-and-component-health"},{"title":"Embeddable HTML status page","deprecated":null,"version":null,"openapi":"/openapi.json get /status/page","href":"/api-reference/status/embeddable-html-status-page"},{"title":"Simple ping for external monitors","deprecated":null,"version":null,"openapi":"/openapi.json get /status/ping","href":"/api-reference/status/simple-ping-for-external-monitors"},{"title":"List components available for granular pings","deprecated":null,"version":null,"openapi":"/openapi.json get /status/ping/components","href":"/api-reference/status/list-components-available-for-granular-pings"},{"title":"Per-component health ping","deprecated":null,"version":null,"openapi":"/openapi.json get /status/ping/{component}","href":"/api-reference/status/per-component-health-ping"}]},{"group":"Other","pages":[{"title":"Delete mcp","deprecated":null,"version":null,"openapi":"/openapi.json delete /mcp/","href":"/api-reference/delete-mcp"},{"title":"Get well knownoauth authorization server","deprecated":null,"version":null,"openapi":"/openapi.json get /.well-known/oauth-authorization-server","href":"/api-reference/get-well-knownoauth-authorization-server"},{"title":"Get well knownoauth protected resource","deprecated":null,"version":null,"openapi":"/openapi.json get /.well-known/oauth-protected-resource","href":"/api-reference/get-well-knownoauth-protected-resource"},{"title":"Get well knownoauth protected resourcemcp","deprecated":null,"version":null,"openapi":"/openapi.json get /.well-known/oauth-protected-resource/mcp","href":"/api-reference/get-well-knownoauth-protected-resourcemcp"},{"title":"Get mcp","deprecated":null,"version":null,"openapi":"/openapi.json get /mcp/","href":"/api-reference/get-mcp"},{"title":"Get mcpsse","deprecated":null,"version":null,"openapi":"/openapi.json get /mcp/sse","href":"/api-reference/get-mcpsse"},{"title":"Get oauthauthorize","deprecated":null,"version":null,"openapi":"/openapi.json get /oauth/authorize","href":"/api-reference/get-oauthauthorize"},{"title":"Post mcp","deprecated":null,"version":null,"openapi":"/openapi.json post /mcp/","href":"/api-reference/post-mcp"},{"title":"Post mcpmessages","deprecated":null,"version":null,"openapi":"/openapi.json post /mcp/messages","href":"/api-reference/post-mcpmessages"},{"title":"Post oauthauthorize","deprecated":null,"version":null,"openapi":"/openapi.json post /oauth/authorize","href":"/api-reference/post-oauthauthorize"},{"title":"Post oauthregister","deprecated":null,"version":null,"openapi":"/openapi.json post /oauth/register","href":"/api-reference/post-oauthregister"},{"title":"Post oauthtoken","deprecated":null,"version":null,"openapi":"/openapi.json post /oauth/token","href":"/api-reference/post-oauthtoken"}]},{"group":"Age Verification","pages":[{"title":"Get a signed liveness challenge nonce with randomized sequence","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/age/challenge","href":"/api-reference/age-verification/get-a-signed-liveness-challenge-nonce-with-randomized-sequence"},{"title":"Get age verification mode configuration","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/age/config","href":"/api-reference/age-verification/get-age-verification-mode-configuration"},{"title":"Retrieve a past age verification result","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/age/{verificationId}","href":"/api-reference/age-verification/retrieve-a-past-age-verification-result"},{"title":"Submit documents for age verification","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/age/submit","href":"/api-reference/age-verification/submit-documents-for-age-verification"},{"title":"Validate a document image (per-step validation)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/age/validate-document","href":"/api-reference/age-verification/validate-a-document-image-per-step-validation"},{"title":"Validate a selfie image (per-step validation)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/age/validate-selfie","href":"/api-reference/age-verification/validate-a-selfie-image-per-step-validation"}]},{"group":"Wallet","pages":[{"title":"Bootstrap a wallet device via App Attest","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/wallet/token","href":"/api-reference/wallet/bootstrap-a-wallet-device-via-app-attest"}]},{"group":"Prescreen","pages":[{"title":"Fetch the Tuteliq prescreen lexicon","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/prescreen/lexicon","href":"/api-reference/prescreen/fetch-the-tuteliq-prescreen-lexicon"}]},{"group":"Verification","pages":[{"title":"Cancel a verification session","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/verify/session/{id}","href":"/api-reference/verification/cancel-a-verification-session"},{"title":"Get a signed liveness challenge nonce","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/challenge","href":"/api-reference/verification/get-a-signed-liveness-challenge-nonce"},{"title":"Get verification session status","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/session/{id}","href":"/api-reference/verification/get-verification-session-status"},{"title":"Subscribe to session status updates via SSE","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/session/{id}/events","href":"/api-reference/verification/subscribe-to-session-status-updates-via-sse"},{"title":"Resolve verification mode and language for end-user","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/session/{id}/mode","href":"/api-reference/verification/resolve-verification-mode-and-language-for-end-user"},{"title":"Retrieve a past verification result","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/{verificationId}","href":"/api-reference/verification/retrieve-a-past-verification-result"},{"title":"Composite non-LLM image verification","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify-image-match","href":"/api-reference/verification/composite-non-llm-image-verification"},{"title":"Create a cross-device verification session","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/session","href":"/api-reference/verification/create-a-cross-device-verification-session"},{"title":"Report verification step progress from mobile","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/session/{id}/progress","href":"/api-reference/verification/report-verification-step-progress-from-mobile"},{"title":"Submit verification via session (mobile)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/session/{id}/submit","href":"/api-reference/verification/submit-verification-via-session-mobile"},{"title":"Validate and process a document image via session (mobile)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/session/{id}/validate-document","href":"/api-reference/verification/validate-and-process-a-document-image-via-session-mobile"},{"title":"Validate and assess a selfie via session (mobile)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/session/{id}/validate-selfie","href":"/api-reference/verification/validate-and-assess-a-selfie-via-session-mobile"},{"title":"Submit documents for age verification","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/submit","href":"/api-reference/verification/submit-documents-for-age-verification"}]},{"group":"Identity Verification","pages":[{"title":"Retrieve a past identity verification result","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/verify/identity/{verificationId}","href":"/api-reference/identity-verification/retrieve-a-past-identity-verification-result"},{"title":"Submit documents for identity verification","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/identity/submit","href":"/api-reference/identity-verification/submit-documents-for-identity-verification"},{"title":"Validate a document image (per-step validation)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/identity/validate-document","href":"/api-reference/identity-verification/validate-a-document-image-per-step-validation"},{"title":"Validate a selfie image (per-step validation)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/verify/identity/validate-selfie","href":"/api-reference/identity-verification/validate-a-selfie-image-per-step-validation"}]},{"group":"Risk Profile","pages":[{"title":"Get anonymised global risk trends","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/safety/risk-trends","href":"/api-reference/risk-profile/get-anonymised-global-risk-trends"}]},{"group":"Threat Intelligence","pages":[{"title":"Get emerging threats","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/intelligence/emerging","href":"/api-reference/threat-intelligence/get-emerging-threats"},{"title":"Get anonymised threat intelligence trends","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/intelligence/trends","href":"/api-reference/threat-intelligence/get-anonymised-threat-intelligence-trends"},{"title":"Get weekly threat intelligence digest","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/intelligence/weekly-digest","href":"/api-reference/threat-intelligence/get-weekly-threat-intelligence-digest"}]},{"group":"Policy Rules","pages":[{"title":"Delete a policy rule","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/policy/automation/{ruleId}","href":"/api-reference/policy-rules/delete-a-policy-rule"},{"title":"List all policy rules","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/policy/automation/","href":"/api-reference/policy-rules/list-all-policy-rules"},{"title":"Get a policy rule","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/policy/automation/{ruleId}","href":"/api-reference/policy-rules/get-a-policy-rule"},{"title":"Create a policy rule","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/policy/automation/","href":"/api-reference/policy-rules/create-a-policy-rule"},{"title":"Test-evaluate policy rules","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/policy/automation/evaluate","href":"/api-reference/policy-rules/test-evaluate-policy-rules"},{"title":"Update a policy rule","deprecated":null,"version":null,"openapi":"/openapi.json put /api/v1/policy/automation/{ruleId}","href":"/api-reference/policy-rules/update-a-policy-rule"}]},{"group":"Settings","pages":[{"title":"Reset detection settings to defaults","deprecated":null,"version":null,"openapi":"/openapi.json delete /api/v1/settings/detection","href":"/api-reference/settings/reset-detection-settings-to-defaults"},{"title":"Get detection settings","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/settings/detection","href":"/api-reference/settings/get-detection-settings"},{"title":"Update detection settings","deprecated":null,"version":null,"openapi":"/openapi.json put /api/v1/settings/detection","href":"/api-reference/settings/update-detection-settings"}]},{"group":"Audit","pages":[{"title":"Fetch an EU AI Act Art 12 audit receipt","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/audit/receipts/{request_id}","href":"/api-reference/audit/fetch-an-eu-ai-act-art-12-audit-receipt"}]},{"group":"Incidents","pages":[{"title":"List the caller's incidents (newest first, paginated)","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/incidents/","href":"/api-reference/incidents/list-the-callers-incidents-newest-first-paginated"},{"title":"KPI overview of incidents in a time window","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/incidents/overview","href":"/api-reference/incidents/kpi-overview-of-incidents-in-a-time-window"},{"title":"Time-series buckets of incident volume","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/incidents/trends","href":"/api-reference/incidents/time-series-buckets-of-incident-volume"},{"title":"Get the full detail for a single incident (read-only)","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/incidents/{incident_id}","href":"/api-reference/incidents/get-the-full-detail-for-a-single-incident-read-only"},{"title":"Submit the same moderator review across multiple incidents (Art 14, bulk)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/incidents/batch-review","href":"/api-reference/incidents/submit-the-same-moderator-review-across-multiple-incidents-art-14-bulk"},{"title":"Submit a moderator review of an incident (Art 14 human oversight)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/incidents/{incident_id}/review","href":"/api-reference/incidents/submit-a-moderator-review-of-an-incident-art-14-human-oversight"}]},{"group":"Agent","pages":[{"title":"List the org's device fleet with a compliance summary","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/agent/fleet","href":"/api-reference/agent/list-the-orgs-device-fleet-with-a-compliance-summary"},{"title":"Get a single device's latest attestation","deprecated":null,"version":null,"openapi":"/openapi.json get /api/v1/agent/fleet/{deviceId}","href":"/api-reference/agent/get-a-single-devices-latest-attestation"},{"title":"Report a device attestation (endpoint agent check-in)","deprecated":null,"version":null,"openapi":"/openapi.json post /api/v1/agent/check-in","href":"/api-reference/agent/report-a-device-attestation-endpoint-agent-check-in"}]}]}]},"basePath":"","title":"Detect KOSA-aligned harm signals in text - Tuteliq","buildId":"dpl_Fyv1NbzwP68g2bEH2Roy98uY1zmE","deploymentId":"dpl_Fyv1NbzwP68g2bEH2Roy98uY1zmE","dynamics":["c2aa737661","2b790eda92","b0f84f53ff","a9bb46feb3"],"chunks":["OpenApiReferenceProvider-DdEMm2kG.js","utils-BMo572L7.js","cloneDeep-izs3Hzxb.js","_Uint8Array-BVIqJ90l.js","isObjectLike-C8vmzPEN.js","isArray-Dcu1dQ5t.js","utils-C-4m9KAx.js","toString-BX-iyh8G.js","isSymbol-CSH9U2Gm.js","addUniqueKeysToSchema-DPLK2Oq9.js","snippetPresets-BKjfJMC9.js","style-to-object-BY3JEAdk.js","v4-DIgz8zy6.js","conditional-requirements-CFM0id0Q.js","ApiExamples-DTsgtCEj.js","isEqual-BfaiBbcl.js","usePlaygroundInputsStore-C8vmhyQM.js","shallow-r9w8LQGS.js","getApiPlaygroundDisplay-DjPI64HQ.js","CodeSnippet-C8Bvhl16.js","CodeSnippets-BtWUwcMy.js","Page-BIYvYBgk.js","getPastedJson-Dcm_3Pgl.js","icon-BXwrTpjc.js","MethodPill-CcjfVmmy.js","DuplicateIcon-BuKIbXAQ.js","createIcon-DaL9yXsO.js","DynamicMarkdown-Co5nikxh.js","SectionHeading-P4UNTsMZ.js","axios-vUo_bRtp.js","Markdown-CEfymfIH.js","clsx-Dq9TQuNi.js","lib-DuNMoZ05.js","lib-B8HbPgcC.js","html-void-elements-mCSPHezU.js","dist-D2J8knkn.js","katex-YMM-FMeD.js","marked.esm-CZWythHk.js","AssistantPageLink-BgZ2ThuU.js"]}