All projects matching “vision”

Calculate real estate investment metrics from property financials. Required: purchase_price, monthly_rent, down_payment_percent. Returns cap_rate, cash_on_cash, DSCR, gross_rent_multiplier, monthly_cashflow, mortgage, expenses, and annual_noi. Optional inputs have smart defaults (7% rate, 30yr term, 8% vacancy, 10% management). Not financial advice.

Routes requests across open-weight models using task fit, tool calling, vision, JSON format, context, output capacity, provider availability, and price. Send POST application/json with model set to ai-open-models/auto and a non-empty messages array. task_type is optional; when omitted, Auto classifies the request. Supports function tools, JSON responses, and mixed text/image messages using public

Render any public web page in a real headless Chrome and return a PNG/JPEG screenshot (base64 JSON, or raw image with ?raw=1). Viewport up to 1920x1920, optional full-page capture up to 8000px tall, optional wait for late content. Use when an agent needs to see what a page actually looks like (visual check, JS-rendered content, layout/UI review, evidence capture, feeding a vision model) rather tha

Answer questions about an image or describe what it shows (Llama 3.2 11B vision), fixed price $0.008 USDC. Use this when the input is an image; use /chat for text-only questions. POST JSON body {image (required, base64 or data:image/... URI, max 4 MB decoded, PNG/JPEG/GIF/WEBP), prompt (optional question, defaults to describing the image), max_tokens (optional 1-512, default 256)}. Returns {text}.

Downloads one HTTPS image through the hub SSRF guard, then asks the configured OpenAI vision model for strict structured JSON. It reports observed features and readable markings, at most five ranked type candidates, and conductor material, core count or cross-section only where the image supports them; unknown values remain null or unknown. The result is identification assistance, not an electrica

Analyze any image URL using GPT-4o-mini vision. Returns structured analysis based on the mode: describe (full description), ocr (text extraction), chart (data/trend extraction), ui (interface analysis), identify (object/subject ID), or qa (answer a specific question about the image). Input must be a publicly accessible image URL (JPEG, PNG, GIF, WebP). $0.261/call.

Extract raw artifacts from images: OCR text and detected objects. No interpretation, just clean machine-readable data. Powered by GPT-4o Vision. Payment via USDC on base.

Finds up to 100 faces in a JPEG or PNG at a URL with Amazon Rekognition and describes each: position, estimated age range, emotions, smile, glasses, beard, eyes and mouth open, pose and image quality. It does not identify anyone or compare faces.

Analyze a meal photo for visible foods, estimated food-group shares, missing groups, plant diversity and a balance score. Returns JSON with one practical suggestion. No receipt, Replate account or receipt verification is required. Visual estimates only; no exact calories or medical assessment. (0.01 USDC)