{"uid":"cap_t3S6NJjfSXpmfyaQGRkvX","slug":"gedx402-llava-1-5-7b-image-captioning-6865c9d2","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://media.gedx402.com/v1/caption/llava-1.5-7b-hf","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"image":{"type":"string","description":"Base64-encoded image for multimodal input."},"prompt":{"type":"string","description":"Optional question or instruction about the image."},"max_tokens":{"type":"integer","description":"Maximum tokens in the vision model response."}}},"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_QLIMQWG-yNUY7zhgm7IT5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.554","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates a natural language caption or answers a question about a provided image using the LLaVA-1.5-7B multimodal vision-language model, paid via USDC on-chain with no API key required.","exampleAgentPrompt":"Look at this image (I'll send it as base64) and describe what you see in it — use up to 200 tokens for your answer.","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 data returns an error","Payment failure on-chain results in 402 response and no inference","Image too large or unsupported format may cause processing failure","Exceeding max_tokens limit silently truncates output","Network timeout on the Workers AI backend returns 5xx error"],"whenToPreferThis":"Choose this endpoint when you need pay-per-call image captioning or visual question answering with no API key setup, billed directly in USDC on Base, Polygon, Arbitrum, World, or Solana. Ideal for agents operating in crypto-native or serverless environments where managing API credentials is undesirable. Use when LLaVA-1.5-7B quality is sufficient for the task.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:32:51.832Z","isFirstParty":false}