{"uid":"cap_rOfCsHglwjiPfXspN4INS","slug":"inference402-image-describe-91ed13a8","name":"Inference402 Image Describe","description":"Pay-per-call AI inference for agents: chat (Llama 3.3 70B / 3.1 8B), structured JSON, summarize, translate (incl. Egyptian Arabic), extract, classify, sentiment, keywords, rewrite, embeddings, moderation, vision and speech-to-text. USDC on Base mainnet over x402. No API key, no account.","url":"https://inference402.worlddata402.workers.dev/v1/image/describe?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"prompt":{"type":"string","maxLength":500,"description":"Optional extra instruction or question about the image"},"image_url":{"type":"string","format":"uri","description":"Public http(s) URL of a JPEG/PNG/WebP image ≤5MB"}}},"responseSchema":{"type":"json","example":{"model":"@cf/llava-hf/llava-1.5-7b-hf","objects":["cat","floor"],"description":"A ginger cat sitting on a wooden floor looking at the camera."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_hb8N9f77ts4wk9u2lUPjk","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","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 and returns a natural-language description plus detected objects, powered by LLaVA vision model, paid per-call in USDC.","exampleAgentPrompt":"Look at this image — https://example.com/photo.jpg — and tell me what objects are in it and give me a full description of the scene.","exampleUseCases":[{"title":"Automated product image tagging","prompt":"Here's a product photo URL: https://mystore.com/items/shirt42.jpg — can you list the objects you see and describe the image so I can use it as alt text and tags in my catalog?"},{"title":"Accessibility alt-text generation","prompt":"I need a descriptive caption for screen readers for this image: https://myblog.com/uploads/header-banner.png — please describe what's shown in detail."},{"title":"Scene-specific visual question answering","prompt":"Take a look at https://uploads.example.com/crime-scene-sketch.jpg and answer this specific question: are there any weapons or dangerous objects visible in the image?"}],"resultDescription":"Returns a JSON object containing the model identifier (e.g. '@cf/llava-hf/llava-1.5-7b-hf'), an array of detected object labels, and a natural-language description sentence summarizing the image contents.","failureModes":["Image URL is not publicly accessible or returns a non-200 response — endpoint cannot fetch the image","Image exceeds 5MB size limit — request rejected","Unsupported image format (non-JPEG/PNG/WebP) — may fail or produce degraded output","Payment not submitted in USDC on Base mainnet — 402 Payment Required returned","Ambiguous or low-resolution image — model may return generic or inaccurate description","Rate limit or worker timeout — transient 5xx error"],"whenToPreferThis":"Choose this endpoint when you need no-account, pay-per-call vision analysis of a public image URL and want structured JSON output including both an object list and a natural-language description. It is ideal for agents that handle sporadic image analysis tasks without committing to a subscription, and when payment via USDC on Base is acceptable. Prefer alternatives if you need private/uploaded image support, batch processing, or higher-resolution vision models.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T12:35:18.555Z","isFirstParty":false,"canonicalSlug":"inference402-image-describe-91ed13a8"}