Similarity of two texts in [0,1]. Methods: `jaccard` (word-set overlap, default), `levenshtein` (normalized edit distance) — both pure & deterministic — and `cosine-embed` (cosine of Cloudflare Workers AI embeddings @cf/baai/bge-m3, semantic; model named). Compare two texts (dedup, matching) without handling embeddings yourself. cosine-embed 503s unbilled if the AI binding is unavailable. Caps: jaccard 200k, levenshtein 5k, cosine 4k chars.

Payment Options