{"uid":"cap_h8no7xkhXo3QIzhvMZmWn","slug":"image-caption-generator-single-sentence-ad47182a","name":"Image Caption Generator (Single Sentence)","description":"Generate one English sentence describing a supplied image.","url":"https://manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/api/v1/image/caption","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"contentType":{"enum":["image/jpeg","image/png"]},"imageBase64":{"type":"string","pattern":"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?$","maxLength":13981016,"minLength":8}}},"responseSchema":{"type":"json","example":{"image":{"width":200,"height":120,"contentType":"image/png"},"caption":{"text":"A red circle and the word hello on a white background.","confidence":0.92},"language":"en"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_L7k-H3t9i37MiR6u9KTdb","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates one descriptive English sentence summarizing the content of a supplied image (JPEG or PNG, base64-encoded).","exampleAgentPrompt":"Can you generate a one-sentence English caption describing what's in this JPEG image? Here's the base64-encoded image data: [base64string]","exampleUseCases":[{"title":"Alt-text generation for web images","prompt":"I need a one-sentence description for this PNG image so I can use it as alt-text on my website — here's the base64-encoded image."},{"title":"Auto-captioning product photos","prompt":"I have a JPEG photo of one of our products encoded in base64 — can you generate a single descriptive English sentence that captures what's shown in it?"},{"title":"Image summarization for content moderation","prompt":"Here's a base64-encoded JPEG image uploaded by a user — give me one sentence describing what's in it so I can log it for review."}],"resultDescription":"A single English sentence that describes the visual content of the supplied image, returned as a text string.","failureModes":["Invalid or malformed base64 string returns a validation error","Unsupported content type (e.g. image/gif or image/webp) rejected — only image/jpeg and image/png accepted","Base64 payload exceeding ~13.9 MB max length is rejected","Corrupt or undecodable image binary returns an error","Payment failure or missing x402 payment header returns 402 response"],"whenToPreferThis":"Choose this endpoint when you need a concise, single-sentence natural language caption for an image and don't need additional metadata like bounding boxes, visual tags, or detected objects. For richer analysis including tags and object locations, prefer the sibling endpoint that returns a caption plus visual tags and objects. Best suited for alt-text generation, content logging, or lightweight image summarization pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:33:52.370Z","isFirstParty":false}