{"uid":"cap_9eg5_3ObKf3RBW5yuyesn","slug":"agentrxi-vision-ask-moondream-3-1-87c0a1f3","name":"AgentRXI Vision Ask (Moondream 3.1)","description":"Ask a question about an image (Moondream 3.1 vision model): read signs and screens, count things, describe a scene or check a photo. Without a question it writes a caption (short, normal or long). Priced $0.003 + up to $0.003 by max_tokens (default 512, max 1,024). Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/vision/ask?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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":{"question":{"type":"string","description":"Leave out for a caption"},"image_url":{"type":"string"},"reasoning":{"type":"boolean"},"image_base64":{"type":"string"},"caption_length":{"type":"string","description":"short, normal, long"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.004536","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":"$0.004536/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004536","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004536","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_0ip1U8-N3uLOEV-9tJTsr","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.004536","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Answers a question about an image using the Moondream 3.1 vision model, or generates a caption if no question is provided","exampleAgentPrompt":"Look at this image — https://example.com/menu.jpg — and tell me what the daily specials are by reading the text on the chalkboard sign.","exampleUseCases":[{"title":"Reading text from a screenshot","prompt":"I have a screenshot at https://example.com/screenshot.png — can you read what the error message says on the screen?"},{"title":"Counting items in a photo","prompt":"Here's a photo of a warehouse shelf: https://example.com/shelf.jpg — how many boxes are stacked on it?"},{"title":"Auto-captioning an image for accessibility","prompt":"Write a long descriptive caption for this image at https://example.com/product.jpg so I can use it as alt text — use the 'long' caption length."}],"resultDescription":"Returns a text answer to the posed question about the image, or a short/normal/long caption if no question was given. The response reflects Moondream 3.1's vision understanding — including OCR-style text reading, object counting, scene description, and visual Q&A.","failureModes":["Invalid or inaccessible image URL returns an error","Image too large or unsupported format may fail","Ambiguous questions may yield vague or incorrect answers","max_tokens cap of 1024 may truncate long descriptions","base64 and image_url both provided may cause conflict or one being ignored","No image provided results in an error"],"whenToPreferThis":"Choose this endpoint when you need to ask a specific question about an image (e.g. read text, count objects, verify content) or generate a caption of controlled length. It uses the Moondream 3.1 model which is optimized for fast, lightweight visual Q&A. Prefer it over general-purpose LLM vision APIs when you want pay-per-call pricing without a subscription, or when you need captioning with explicit length control.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:18.160Z","isFirstParty":false,"canonicalSlug":"agentrxi-vision-ask-moondream-3-1-87c0a1f3"}