Smart Analyze Image

Analyze an image using an OpenRouter VLM (vision-language model). Returns structured metadata including description, tags, colors, and category suggestions.

How it works

Provide the Convex storageId of an already-uploaded image
The endpoint sends the image to an OpenRouter VLM for analysis
The VLM returns structured metadata (description, tags, colors, category)
Results can be used to auto-populate image metadata fields

When to use

After uploading an image, to auto-generate metadata
Before generating AI variations, to inform the prompt
In batch processing pipelines for automated tagging

VLM configuration

The model used for analysis is configured in the Convex dashboard:

Variable	Description
`OPENROUTER_API_KEY`	Required — API key for OpenRouter
`OPENROUTER_VLM_MODEL`	Optional — specific VLM model to use
`OPENROUTER_PROVIDER_SORT`	Optional — provider preference for routing