Simple pricing, powerful code search
that scales with you

Your plan includes a single token quota shared across both embedding (indexing) and reranking (search). Whether SHARC is indexing your codebase or reranking search results, it draws from the same pool.

This gives you full flexibility — if you search more than you index, your quota adjusts naturally without hitting separate limits.

Rule-of-thumb: about 1 token per ~4 characters of source text.

SHARC persists Merkle snapshots (file-hash baselines) and compares hashes on subsequent index operations.

Unchanged files are skipped, and the active watcher applies incremental updates with hash checks instead of full re-indexing.

In normal workflows, ongoing token usage is mostly from changed files plus search traffic.

Usually no. After initial indexing, updates are incremental (add/modify/delete per file).

A full re-index is mainly for explicit force operations or specific migration/troubleshooting scenarios.

Start by estimating the initial index from your total source text size, then factor in weekly code churn and search volume.

If your team changes 2-5% of a repo per week, maintenance is typically a small fraction of the first index.

Most of your ongoing usage comes from search queries, not re-indexing.