> ## Documentation Index > Fetch the complete documentation index at: https://docs.moderationapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Submit content > Submit text, image, video, audio, or object content for moderation analysis. Submit content for moderation and receive analysis results immediately. Supports text, image, object, video, and audio content types. For detailed usage examples and content metadata options, see [Submitting content](/content-moderation/submit-content). ## OpenAPI ````yaml POST /moderate openapi: 3.1.0 info: title: Moderation API description: API for automated content moderation version: 1.1.0 servers: - url: https://api.moderationapi.com/v1 security: [] tags: - name: Actions - name: Queues - name: Webhooks - name: Wordlist - name: UserReports - name: Voice description: Real-time voice moderation over WebSocket. externalDocs: url: https://docs.moderationapi.com paths: /moderate: post: operationId: newModerate-moderate parameters: [] requestBody: required: true content: application/json: schema: type: object properties: content: oneOf: - type: object properties: type: type: string const: text text: type: string maxLength: 100000 description: The content text required: - type - text description: Text title: Text - type: object properties: type: type: string const: image url: description: >- A public URL of the image content. Either url or data must be provided. type: string format: uri data: description: >- Base64-encoded image data. Either url or data must be provided. Note: base64 images are not stored and will not appear in the review queue. type: string maxLength: 5500000 required: - type description: Image title: Image - type: object properties: type: type: string const: video url: type: string format: uri description: A public URL of the video content required: - type - url description: Video title: Video - type: object properties: type: type: string const: audio url: type: string format: uri description: The URL of the audio content required: - type - url description: Audio title: Audio - type: object properties: type: type: string const: object data: type: object propertyNames: type: string description: The key of the content node additionalProperties: oneOf: - type: object properties: type: type: string const: text text: type: string maxLength: 100000 description: The content text required: - type - text description: Text title: Text - type: object properties: type: type: string const: image url: description: >- A public URL of the image content. Either url or data must be provided. type: string format: uri data: description: >- Base64-encoded image data. Either url or data must be provided. Note: base64 images are not stored and will not appear in the review queue. type: string maxLength: 5500000 required: - type description: Image title: Image - type: object properties: type: type: string const: video url: type: string format: uri description: A public URL of the video content required: - type - url description: Video title: Video - type: object properties: type: type: string const: audio url: type: string format: uri description: The URL of the audio content required: - type - url description: Audio title: Audio title: Content leaf type: object description: Values in the object. Can be mixed content types. required: - type - data description: Object title: Object description: The content sent for moderation type: object timestamp: description: >- Unix timestamp (in milliseconds) of when the content was created. Use if content is not submitted in real-time. type: number channel: description: >- Provide a channel ID or key. Will use the project's default channel if not provided. type: string contentId: description: The unique ID of the content in your database. type: string maxLength: 100 metaType: description: The meta type of content being moderated type: string enum: - profile - message - post - comment - event - product - review - voice - other authorId: description: The author of the content. type: string conversationId: description: For example the ID of a chat room or a post type: string metadata: description: Any metadata you want to store with the content type: object propertyNames: type: string additionalProperties: {} clientAction: description: >- A recommendation from your own client-side flagging (e.g. a banned-IP list or a third-party tool). Feeds the rules engine and can escalate or override the recommended action. Does not change whether our analysis flagged the content. type: object properties: action: type: string enum: - review - allow - reject description: >- Your recommendation for the content: allow, review, or reject. behavior: description: >- How your recommendation combines with ours. Defaults to 'escalate', which only applies it when stricter than ours; 'override' replaces ours outright. type: string enum: - override - escalate source: description: Where your recommendation came from, e.g. "banned-ip". type: string maxLength: 100 reason: description: A human-readable explanation for your recommendation. type: string maxLength: 500 required: - action doNotStore: description: >- Do not store the content. The content won't enter the review queue type: boolean policies: description: >- (Enterprise) override the channel policies for this moderation request only. type: array items: oneOf: - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: toxicity required: - flag - id title: Toxicity - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: personal_information required: - flag - id title: Personal Information - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: toxicity_severe required: - flag - id title: Toxicity Severe - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: hate required: - flag - id title: Hate - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit required: - flag - id title: Illicit - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit_drugs required: - flag - id title: Illicit Drugs - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit_alcohol required: - flag - id title: Illicit Alcohol - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit_firearms required: - flag - id title: Illicit Firearms - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit_tobacco required: - flag - id title: Illicit Tobacco - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: illicit_gambling required: - flag - id title: Illicit Gambling - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: cannabis required: - flag - id title: Cannabis - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: adult required: - flag - id title: Adult - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: crypto required: - flag - id title: Crypto - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: sexual required: - flag - id title: Sexual - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: flirtation required: - flag - id title: Flirtation - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: profanity required: - flag - id title: Profanity - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: violence required: - flag - id title: Violence - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: self_harm required: - flag - id title: Self Harm - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: spam required: - flag - id title: Spam - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: low_quality minWords: description: >- Flag content with fewer than this many words as low-effort. Defaults to 3. Set to disable by omitting. type: integer minimum: 1 maximum: 9007199254740991 required: - flag - id title: Low-quality content - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: face_detection comparator: description: >- Flag images that contain "at least" or "fewer than" the configured number of faces. Defaults to at_least. type: string enum: - at_least - fewer_than count: description: >- Number of faces the comparator applies to. Defaults to 1, so the default rule flags any image containing a face. type: integer minimum: 0 maximum: 9007199254740991 required: - flag - id title: Face detection - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: self_promotion required: - flag - id title: Self Promotion - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: political required: - flag - id title: Political - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: religion required: - flag - id title: Religion - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: code_abuse required: - flag - id title: Code Abuse - type: object properties: id: type: string const: pii entities: type: object propertyNames: type: string enum: - email - phone - url - address - name - username - ip_address - credit_card - sensitive_other additionalProperties: type: object properties: enable: type: boolean flag: type: boolean shouldMask: type: boolean mask: type: string additionalProperties: {} required: - email - phone - url - address - name - username - ip_address - credit_card - sensitive_other required: - id - entities title: PII Masking - type: object properties: id: type: string const: url entities: type: object propertyNames: type: string enum: - email - phone - url - address - name - username - ip_address - credit_card - sensitive_other additionalProperties: type: object properties: enable: type: boolean flag: type: boolean shouldMask: type: boolean mask: type: string additionalProperties: {} required: - email - phone - url - address - name - username - ip_address - credit_card - sensitive_other required: - id - entities title: URL Masking - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: url_risk allowlistWordlistIds: description: >- IDs of wordlists whose entries are treated as allowed URL domains. Matches short-circuit the risk model and are never flagged. type: array items: type: string blocklistWordlistIds: description: >- IDs of wordlists whose entries are treated as blocked URL domains. Matches short-circuit the risk model and are always flagged. Blocklists take precedence over allowlists. type: array items: type: string flagLinkShorteners: description: >- When true, any URL detected as a free link shortener (bit.ly, t.co, tinyurl, etc.) is always flagged regardless of risk score. Allowlist matches still win. type: boolean required: - flag - id title: URL Risk - type: object properties: flag: type: boolean threshold: type: number minimum: 0 maximum: 1 id: type: string const: guideline instructions: type: string guidelineKey: type: string required: - flag - id - instructions - guidelineKey title: Guideline type: object required: - content responses: '200': description: Successful response content: application/json: schema: type: object properties: content: type: object properties: id: type: string description: >- The unique identifier for the content. Either the contentId provided by you or an autogenerated ID. masked: type: boolean description: Whether any values have been masked. modified: anyOf: - anyOf: - type: string title: Modified string content - type: object propertyNames: type: string additionalProperties: {} title: Modified object content - type: object propertyNames: type: string additionalProperties: oneOf: - type: object properties: type: type: string const: text text: type: string maxLength: 100000 description: The content text required: - type - text additionalProperties: false description: Text title: Text - type: object properties: type: type: string const: image url: description: >- A public URL of the image content. Either url or data must be provided. type: string format: uri data: description: >- Base64-encoded image data. Either url or data must be provided. Note: base64 images are not stored and will not appear in the review queue. type: string maxLength: 5500000 required: - type additionalProperties: false description: Image title: Image - type: object properties: type: type: string const: video url: type: string format: uri description: A public URL of the video content required: - type - url additionalProperties: false description: Video title: Video - type: object properties: type: type: string const: audio url: type: string format: uri description: The URL of the audio content required: - type - url additionalProperties: false description: Audio title: Audio title: Content leaf type: object title: Modified nested object content - type: 'null' description: The modified content, if any. transcript: description: >- The transcribed text from audio content. Only present when audio moderation is used and transcript inclusion is enabled on the channel. anyOf: - type: string - type: 'null' required: - id - masked - modified additionalProperties: false description: Potentially modified content. author: anyOf: - type: object properties: id: type: string description: Author ID in Moderation API external_id: description: The author's ID from your system anyOf: - type: string - type: 'null' block: anyOf: - type: object properties: until: description: >- The timestamp until which they are blocked if the author is suspended. anyOf: - type: number - type: 'null' reason: description: >- The moderators reason why the author was blocked or suspended. anyOf: - type: string - type: 'null' additionalProperties: false - type: 'null' description: >- Block or suspension details, if applicable. Null if the author is enabled. status: type: string enum: - enabled - suspended - blocked description: Current author status trust_level: type: object properties: level: type: number description: Author trust level (-1, 0, 1, 2, 3, or 4) manual: type: boolean description: >- True if the trust level was set manually by a moderator required: - level - manual additionalProperties: false required: - id - block - status - trust_level additionalProperties: false - type: 'null' description: >- The author of the content if your account has authors enabled. Requires you to send authorId when submitting content. evaluation: type: object properties: flagged: type: boolean description: Whether the content was flagged by any policy. flag_probability: type: number description: The probability that the content should be flagged. severity_score: type: number description: >- The severity score of the content. A higher score indicates more severe content. unicode_spoofed: description: Whether the content was flagged for Unicode spoofing. type: boolean shadow_flagged: description: >- Whether the content would have been flagged by analyze-only policies (flag: false). type: boolean required: - flagged - flag_probability - severity_score additionalProperties: false description: >- The evaluation of the content after running the channel policies. recommendation: type: object properties: action: type: string enum: - review - allow - reject description: The action to take based on the recommendation reason_codes: type: array items: type: string enum: - severity_reject - severity_review - author_block - dry_run - trusted_allow - untrusted_severity - rule_match - rule_default - rule_fallback - client_override description: >- The reason code for the recommendation. Can be used to display a reason to the user. matched_rules: description: >- Rules that matched during evaluation, if rules engine is active. type: array items: type: object properties: key: type: string name: type: string required: - key - name additionalProperties: false required: - action - reason_codes additionalProperties: false description: >- The recommendation for the content based on the evaluation. policies: type: array items: oneOf: - type: object properties: id: type: string description: The unique identifier for the classifier output. type: type: string const: classifier probability: type: number minimum: 0 maximum: 1 flagged: type: boolean flagged_fields: description: >- The keys of the flagged fields if submitting an object. type: array items: type: string labels: type: array items: type: object properties: id: type: string probability: type: number minimum: 0 maximum: 1 flagged: type: boolean required: - id - probability - flagged additionalProperties: false data: description: >- Optional structured data produced by the policy. For face detection: { count, faces: [{ confidence, gender, age }] }. type: object propertyNames: type: string additionalProperties: {} required: - id - type - probability - flagged additionalProperties: false description: Classifier policy. title: Classifier output - type: object properties: id: type: string type: type: string const: entity_matcher probability: type: number minimum: 0 maximum: 1 flagged: type: boolean flagged_fields: type: array items: type: string matches: type: array items: type: object properties: probability: type: number minimum: 0 maximum: 1 match: type: string span: minItems: 2 maxItems: 2 type: array items: type: integer minimum: -9007199254740991 maximum: 9007199254740991 reasons: description: >- Stable codes explaining why a URL was flagged (URL Risk only). type: array items: type: string signals: description: >- Observable properties of a URL (URL Risk only). Absent for allow/block list matches. type: object properties: brand_impersonation: anyOf: - type: object properties: brand: type: string method: type: string enum: - registered_domain_token - subdomain_token required: - brand - method additionalProperties: false - type: 'null' has_suspicious_characters: type: boolean is_link_shortener: type: boolean domain_age_days: anyOf: - type: integer minimum: -9007199254740991 maximum: 9007199254740991 - type: 'null' has_email_setup: anyOf: - type: boolean - type: 'null' redirect_count: anyOf: - type: integer minimum: -9007199254740991 maximum: 9007199254740991 - type: 'null' final_url: anyOf: - type: string - type: 'null' bot_protection: anyOf: - type: boolean - type: 'null' is_reported: type: boolean required: - brand_impersonation - has_suspicious_characters - is_link_shortener - domain_age_days - has_email_setup - redirect_count - final_url - bot_protection - is_reported additionalProperties: false entity_type: description: >- Sub-type of the entity match — e.g. the NER key (email, phone, name, …) for PII matches. Absent for URL Risk and wordlist matches where the type is already encoded in the parent label. type: string required: - probability - match - span additionalProperties: false required: - id - type - probability - flagged - matches additionalProperties: false description: Entity matcher policy. title: Entity matcher output description: Policy output schema. type: object description: >- Results of all policies in the channel. Sorted by highest probability. insights: type: array items: oneOf: - type: object properties: id: type: string const: sentiment type: type: string const: insight probability: type: number minimum: 0 maximum: 1 value: anyOf: - type: string enum: - positive - neutral - negative - type: 'null' required: - id - type - probability - value additionalProperties: false description: Sentiment insight title: Sentiment insight - type: object properties: id: type: string const: language type: type: string const: insight probability: type: number minimum: 0 maximum: 1 value: anyOf: - type: string - type: 'null' required: - id - type - probability - value additionalProperties: false description: Language insight title: Language insight type: object description: Results of all insights enabled in the channel. meta: type: object properties: status: type: string enum: - success - partial_success timestamp: type: number channel_key: type: string description: >- The unique key of the channel where the content was handled. Either the channel provided by you or automatically routed. usage: type: number processing_time: type: string required: - status - timestamp - channel_key - usage additionalProperties: false description: Metadata about the moderation request errors: description: Policies that had errors type: array items: type: object properties: id: type: string message: type: string required: - id - message additionalProperties: false required: - content - author - evaluation - recommendation - policies - insights - meta additionalProperties: false '400': description: Invalid input data content: application/json: schema: $ref: '#/components/schemas/error.BAD_REQUEST' '401': description: Authorization not provided content: application/json: schema: $ref: '#/components/schemas/error.UNAUTHORIZED' '403': description: Insufficient access content: application/json: schema: $ref: '#/components/schemas/error.FORBIDDEN' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/error.INTERNAL_SERVER_ERROR' security: - Authorization: [] x-codeSamples: - lang: JavaScript source: >- import ModerationAPI from '@moderation-api/sdk'; const client = new ModerationAPI({ secretKey: process.env['MODAPI_SECRET_KEY'], // This is the default and can be omitted }); const response = await client.content.submit({ content: { text: 'text', type: 'text' } }); console.log(response.author); - lang: Python source: |- import os from moderation_api import ModerationAPI client = ModerationAPI( secret_key=os.environ.get("MODAPI_SECRET_KEY"), # This is the default and can be omitted ) response = client.content.submit( content={ "text": "text", "type": "text", }, ) print(response.author) - lang: Ruby source: >- require "moderation_api" moderation_api = ModerationAPI::Client.new(secret_key: "My Secret Key") response = moderation_api.content.submit(content: {text: "text", type: :text}) puts(response) - lang: PHP source: >- content->submit( content: ['text' => 'text', 'type' => 'text'], authorID: 'authorId', channel: 'channel', clientAction: [ 'action' => 'review', 'behavior' => 'override', 'reason' => 'reason', 'source' => 'source', ], contentID: 'contentId', conversationID: 'conversationId', doNotStore: true, metadata: ['foo' => 'bar'], metaType: 'profile', policies: [['id' => 'toxicity', 'flag' => true, 'threshold' => 0]], timestamp: 0, ); var_dump($response); } catch (APIException $e) { echo $e->getMessage(); } - lang: C# source: >- using System; using ModerationApi; using ModerationApi.Models.Content; ModerationApiClient client = new(); ContentSubmitParams parameters = new() { Content = new Text("text") }; var response = await client.Content.Submit(parameters); Console.WriteLine(response); components: schemas: error.BAD_REQUEST: type: object properties: message: type: string description: The error message example: Invalid input data code: type: string description: The error code example: BAD_REQUEST issues: description: An array of issues that were responsible for the error example: [] type: array items: type: object properties: message: type: string required: - message additionalProperties: false required: - message - code additionalProperties: false title: Invalid input data error (400) description: The error information example: code: BAD_REQUEST message: Invalid input data issues: [] error.UNAUTHORIZED: type: object properties: message: type: string description: The error message example: Authorization not provided code: type: string description: The error code example: UNAUTHORIZED issues: description: An array of issues that were responsible for the error example: [] type: array items: type: object properties: message: type: string required: - message additionalProperties: false required: - message - code additionalProperties: false title: Authorization not provided error (401) description: The error information example: code: UNAUTHORIZED message: Authorization not provided issues: [] error.FORBIDDEN: type: object properties: message: type: string description: The error message example: Insufficient access code: type: string description: The error code example: FORBIDDEN issues: description: An array of issues that were responsible for the error example: [] type: array items: type: object properties: message: type: string required: - message additionalProperties: false required: - message - code additionalProperties: false title: Insufficient access error (403) description: The error information example: code: FORBIDDEN message: Insufficient access issues: [] error.INTERNAL_SERVER_ERROR: type: object properties: message: type: string description: The error message example: Internal server error code: type: string description: The error code example: INTERNAL_SERVER_ERROR issues: description: An array of issues that were responsible for the error example: [] type: array items: type: object properties: message: type: string required: - message additionalProperties: false required: - message - code additionalProperties: false title: Internal server error error (500) description: The error information example: code: INTERNAL_SERVER_ERROR message: Internal server error issues: [] securitySchemes: Authorization: type: http scheme: bearer ````