Skip to main content
Lightdrift is an image search engine built to be called by software, not browsed by people. Describe the image you need in text and get ranked, usable images back. Every result carries a machine-readable rights answer, so your agent knows what it can do with the file before it uses it. Retrieval only: no generation, no checkout, no marketplace. One API, billed per query.

​
What it does

  • Text search — natural-language intent over a 10M-image corpus, keyword and visual lanes combined and reranked.
  • Similar-image expansion — start from any result and find more like it.
  • Hard filters — commercial use, license, source, dimensions, orientation, format, year.
  • Rights on every result — license, permission flags, and a ready-to-use attribution string, as declared by the source.
On the roadmap, not yet shipped: search by uploaded image, multimodal (image + text) queries, negative constraints, and design-direction filters.

​
Start here

Quickstart

Get an API key and run your first search in under a minute.

API reference

Every endpoint, with an interactive playground and code samples.

Rights answers

How to read the rights object and what Lightdrift does and does not promise.

Connect Images MCP

One URL for Claude Code, Cursor, Claude, or Codex. Sign in and search.

Connect Docs MCP

Give your agent documentation and API guidance. No sign-in required.

Plans and limits

Credit purchases, automatic upgrades, and request limits for every plan.