{"uid":"cap__A1BK0q6AXcLhPrzyXRfh","slug":"citiview-image-describe-ocr-vision-llm-7d965f79","name":"Citiview Image Describe & OCR (Vision LLM)","description":"Describe an image and read every piece of visible text in it (vision LLM). Send a public image URL or base64 image; optional custom question. Works for receipts, screenshots, signs and charts. Also callable as GET with the same fields as query parameters.","url":"https://agents.citiviewgroup.com/v1/image/describe?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string","description":"Public image URL (jpeg, png, webp, gif; max 8 MB)"},"prompt":{"type":"string","description":"Optional question about the image"},"image_base64":{"type":"string","description":"Alternative to url"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.009","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":"$0.009/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.009","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.009","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vPAQ7OfnJJxBx_woQ9ArU","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.009","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyzes a public image URL or base64-encoded image using a vision LLM to describe its contents and extract all visible text, with optional custom questions.","exampleAgentPrompt":"Can you read all the text and describe everything you see in this receipt image? Here's the URL: https://example.com/receipt.jpg","exampleUseCases":[{"title":"Receipt data extraction for expenses","prompt":"I have a photo of a restaurant receipt at https://example.com/receipt.jpg — can you read all the text on it and tell me the total amount, itemized charges, and date?"},{"title":"Screenshot content analysis","prompt":"Here's a screenshot URL https://example.com/screenshot.png — what does it show and can you extract all the visible text from it?"},{"title":"Chart or infographic interpretation","prompt":"I have a chart image at https://example.com/chart.png — can you describe what it shows and read all the numbers and labels on it?"}],"resultDescription":"A natural language description of the image contents along with all visible text extracted from the image. If a custom prompt/question was provided, the response also includes a direct answer to that question based on what the vision LLM sees in the image.","failureModes":["Image URL is not publicly accessible or returns 404 — no content can be fetched","Image exceeds 8 MB size limit — request rejected","Unsupported image format (not jpeg, png, webp, or gif) — processing fails","Base64 string is malformed or corrupted — decoding error","Image contains no readable text — description returned but OCR yields empty result","Network timeout fetching remote image URL — transient failure","Payment of 0.01 USDC not received — 402 response, endpoint not called"],"whenToPreferThis":"Choose this endpoint when you need to extract text (OCR) from images, describe visual content, or answer specific questions about an image — especially for receipts, screenshots, signs, charts, or documents. It is ideal when the image is already hosted at a public URL or available as base64, and you need both visual description and text extraction in a single call. Prefer this over dedicated OCR tools when you also need semantic understanding of the image content, not just raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-14T06:46:53.499Z","isFirstParty":false,"canonicalSlug":"citiview-image-describe-ocr-vision-llm-7d965f79"}