{"uid":"cap__HoDgrG3G1mVKoKEGSuU2","slug":"gedx402-llava-1-5-7b-image-captioning-f7ddbfef","name":"GEDX402 LLaVA-1.5-7B Image Captioning","description":"x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.","url":"https://ged-x402-media.jvalamis.workers.dev/v1/caption/llava-1.5-7b-hf","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"image":{"type":"string"},"prompt":{"type":"string"},"max_tokens":{"type":"integer"}}},"responseSchema":{"type":"json","example":{"description":"A sunset over mountains."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.554","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":"$0.554/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.554","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.554","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_B7GZTaLeALuL1cvipCC-6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.554","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates a natural language caption or answer for a given image using the LLaVA-1.5-7B vision-language model, paid via USDC on-chain","exampleAgentPrompt":"Describe what's happening in this image for me — here's the base64-encoded photo — and answer the question 'What objects are visible in the foreground?' using up to 200 tokens.","exampleUseCases":null,"resultDescription":"A JSON object containing a 'description' field with a natural language caption or answer about the image, e.g. {\"description\": \"A sunset over mountains.\"}","failureModes":["Invalid or malformed base64 image returns an error","Image too large for model context","Payment not received or insufficient USDC causes 402 rejection","max_tokens exceeded model limits","Unsupported image format"],"whenToPreferThis":"Use this endpoint when you need no-API-key image captioning or visual Q&A via a pay-per-call USDC micropayment on Base, Polygon, Arbitrum, World, or Solana — ideal for agents that want to avoid API key management and pay only per inference call using LLaVA-1.5-7B.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-07-17T21:58:14.493Z","lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:41:56.867Z","isFirstParty":false}