> ## Documentation Index > Fetch the complete documentation index at: https://docs.gowinston.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI text detection > The Human Score is a metric used by Winston AI to estimate the likelihood that a given piece of content was generated by an AI tool versus being written by a human. ## OpenAPI ````yaml POST /v2/ai-content-detection openapi: 3.0.1 info: title: Winston AI API description: Winston AI API specification license: name: MIT version: 4.11.4 servers: - url: https://api.gowinston.ai/ security: - bearerAuth: [] paths: /v2/ai-content-detection: post: description: >- The Human Score is a metric used by Winston AI to estimate the likelihood that a given piece of content was generated by an AI tool versus being written by a human. requestBody: description: The Ai content detection request V2 content: application/json: schema: $ref: '#/components/schemas/AiContentDetection' required: true responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/AiContentDetection-response' '400': description: Bad Request content: application/json: schema: type: object properties: error: type: string default: BAD_REQUEST description: type: string default: >- The request was invalid and could not be processed. Make sure you pass valid arguments. '401': description: Unauthorized content: application/json: schema: type: object properties: error: type: string default: UNAUTHORIZED description: type: string default: >- Pass a valid API key in the Authorization header as a Bearer token. '402': description: Payment Required (insufficient credits) content: application/json: schema: type: object properties: error: type: string default: PAYMENT_REQUIRED description: type: string default: >- Insufficient credits. Make sure you have enough credits to make the request. '403': description: Forbidden content: application/json: schema: type: object properties: error: type: string default: FORBIDDEN description: type: string default: >- The request was forbidden. Make sure you pass a valid URL or document that we can access. '415': description: Unsupported Media Type content: application/json: schema: type: object properties: error: type: string default: UNSUPPORTED_MEDIA_TYPE description: type: string default: >- The request content type is not supported. Make sure you pass a valid content type. '429': description: Too Many Requests content: application/json: schema: type: object properties: error: type: string default: TOO_MANY_REQUESTS description: type: string default: You have exceeded the rate limit. Please try again later. '500': description: Internal Server Error content: application/json: schema: type: object properties: error: type: string default: INTERNAL_SERVER_ERROR description: type: string default: An unexpected error occurred. Please try again later. '503': description: Service Unavailable content: application/json: schema: type: object properties: error: type: string default: SERVICE_UNAVAILABLE description: type: string default: >- The service is currently unavailable. Please try again later. components: schemas: AiContentDetection: type: object required: - text properties: text: description: >- The text to scan. It is required except if you supply a website or a file. Minimum 300 characters. Texts under 600 characters may produce unreliable results and should be avoided. Maximum 150 000 characters per request. type: string file: description: >- A publicly accessible URL to a file to scan. The file must be publicly available online (not a local file path) so our API can access it. The file must be in plain .pdf, .doc or .docx format. The file has priority over the text, so if you give a text and a file, it's the file that will be scanned. type: string website: description: >- A website URL to scan. If you supply a website, the API will fetch the content of the website and scan it. The website must be publicly accessible. It's important to know that the website has priority over the text and the file, so if you give a text, a file and a website, it's the website that will be scanned. type: string version: description: >- The model version to use. Our latest and most accurate version is "4.14". Using "latest" will make sure you are always using the latest version. Options: 4.14, 4.13, 4.12, 4.11, 4.10, 4.9, 4.8, 4.7, 4.6, 4.5, 4.4, 4.3, 4.2, 4.1, 4.0, 3.1, 3.0, 2.0, latest. Default: 4.14. Note: Version 3.1 is identical to 3.0 but preserves newline characters in the returned sentences, while 3.0 removes them. type: string sentences: description: >- Whether the response should include an array of sentences and their scores. Default: true. type: boolean language: description: >- 2 letter language code. Default: auto. If you put 'auto', the API will automatically detect the language based on the text. Supported languages: English (en), French (fr), Spanish (es), Portuguese (pt), Dutch (nl), German (de), Polish (pl), Italian (it), Romanian (ro), Indonesian (id), Tagalog (tl), Russian (ru), Bulgarian (bg) and Chinese simplified (zh). type: string default: auto AiContentDetection-response: type: object properties: status: description: >- This is a standard HTTP status code. A 200 status means the request was successful. type: integer score: description: >- A "human" score between 0 and 100. A low score means our system believes that the text is written by AI, and a higher score means that the system believes that the text is written by a Human. type: integer sentences: description: >- This is an array of sentence objects. Each object contains two fields: text and score. Please note that assessments on smaller samples are less accurate than the general score. type: object properties: text: description: >- The text field contains the actual text of the sentence that was analyzed. type: string score: description: >- The score field within each sentence object indicates the sentiment score assigned to that particular sentence by the AI. type: integer input: description: >- The type of input we scan based on the input you provided. It can be `text | file | website` . type: string attack_detected: type: object description: >- An object with two boolean properties indicating if the text contains zero-width spaces or homoglyph attacks. properties: zero_width_space: type: boolean description: Indicates if the text contains zero-width spaces. homoglyph_attack: type: boolean description: Indicates if the text contains homoglyph attacks. readability_score: description: >- A readability score between 0 and 100 that indicates how easy it is to read and understand the text based on the provided language. A higher score means the text is more readable and easier to understand. type: integer credits_used: description: >- The credits_used field represents the number of credits consumed for processing your request. Each word that is processed by the API consumes one credit. type: integer credits_remaining: description: >- The credits_remaining field shows how many credits you have left in your account after your request has been processed. type: integer version: description: >- The model version used to generate the prediction based on the input you provided. type: string language: description: >- The language of the text detected. It can be `en | fr | es | pt | nl | de | pl | it | ro | id | tl | ru | bg | zh`. type: string securitySchemes: bearerAuth: type: http scheme: bearer ````