Skip to main content
POST
Detect KOSA-aligned harm signals in text

Authorizations

Authorization
string
header
required

API key as Bearer token

Body

application/json
text
string
required

The content to analyze

Maximum string length: 10000
context
object
options
object
support_threshold
enum<string>

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.

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

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.

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.

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.

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)

attestation
object | null

Present only when the request set attestation: true. Null when none could be produced; see attestation_reason.

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