Analyze one or more images with a vision-capable model on OpenRouter and return the analysis as text. Use this whenever you need to know what is in an image but you cannot see it yourself.

Default mode is detailed and thorough (high reasoning effort, high-quality model, automatic retry and fallback). Pass quick: true for a fast, cheap answer (quick model, ~1024-token output, minimal reasoning) — e.g. a yes/no, a caption, or an object check.

Accepts an http(s) URL, local file path, file:// URI, data: URI, or raw base64 (PNG, JPEG, WebP, or GIF only); pass an array of up to 5 to compare images (state the comparison in the prompt). Long analyses are truncated at 25000 characters.

List vision-capable models currently available on OpenRouter, so you or the user can pick one for image analysis. Use it to find a valid model ID (e.g. when a configured model fails) or when asked which models are available. Narrow with 'search' (substring on provider or family, e.g. 'gemini', 'qwen') and paginate with limit/offset. Returns model IDs with context length and input price.

Diagnose vision analysis configuration problems. Reports whether the OpenRouter API key is set and where it was loaded from, which models would be used (default, quick, fallback), and the configured size/time limits. The key is only shown masked. Run this when analysis fails with a missing-key or configuration error.