{"uid":"cap_9ifTkRhAk7ulxxRNniuoW","slug":"openverbs-html-strip-17a322d5","name":"OpenVerbs HTML Strip","description":"Remove all HTML tags, returning the plain text content. Entities are decoded to real characters by default (set decodeEntities=false to keep them encoded).","url":"https://html.openverbs.com/v1/strip","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["html"],"properties":{"html":{"type":"string","maxLength":200000,"description":"HTML markup to strip."},"decodeEntities":{"type":"boolean","description":"Decode entities to characters. Default true."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_jlqLvOUb4CGCFxYuJkmI2","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Strips all HTML tags from markup, returning plain text with HTML entities decoded to real characters by default","exampleAgentPrompt":"Strip all the HTML tags from this markup and give me back just the plain readable text with entities decoded: '<p>Hello &amp; welcome to <b>OpenVerbs</b>!</p>'","exampleUseCases":[{"title":"Clean scraped web page content","prompt":"I just scraped a webpage and the content is full of HTML tags — can you strip all the tags from this HTML and give me just the plain text? '<div class=\"article\"><h1>Top 10 Tips</h1><p>Here are our <strong>best</strong> &amp; most popular tips...</p></div>'"},{"title":"Prepare HTML email body for NLP","prompt":"I have an HTML email body I need to analyze for sentiment, but the model needs plain text. Strip all the HTML tags from this and decode the entities: '<html><body><p>Dear Customer, we&#39;re thrilled to announce our new product line &mdash; enjoy 20% off!</p></body></html>'"},{"title":"Extract text from CMS content block","prompt":"Our CMS stores content in HTML format but I need the raw text for search indexing. Remove all HTML tags from this block and keep entity decoding on: '<section><h2>About Us</h2><p>We&#39;ve been serving clients since 2010 &amp; counting.</p></section>'"}],"resultDescription":"The endpoint returns the plain text content of the submitted HTML, with all tags removed and HTML entities decoded to their real characters (e.g. &amp; becomes &, &#39; becomes '). If decodeEntities is set to false, entities remain in their encoded form.","failureModes":["Missing required 'html' field returns a 400 validation error","Input HTML exceeding 200,000 characters is rejected","Malformed JSON body results in a parse error","Invalid method or bodyType enum value causes a 422 error","Network or service unavailability returns a 5xx error"],"whenToPreferThis":"Choose this endpoint when you need to convert HTML markup to plain text and want entity decoding handled automatically. It is ideal for preprocessing scraped web content, cleaning HTML emails before NLP analysis, or indexing CMS content. Prefer this over the sibling sanitize endpoint when you want no HTML at all in the output, and over the decode-entities-only endpoint when your input contains full HTML markup with tags.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:34:21.848Z","isFirstParty":false}