Exa

Neural web search API for agents

Free tier + paidSearch, vector & RAGexa.ai

What it is

A web search API built on an embeddings index rather than a keyword index, so you query by meaning and describe the page you want instead of guessing keywords. Returns cleaned page contents, highlights and AI summaries in the same call, plus an Answer endpoint that cites its sources.

Why it earns a slot

When an agent needs sources rather than blue links, Exa hands back full extracted text in one round trip. The recurring $10 monthly credit means a small agent never sees a bill.

Know before you commit

Neural search costs more per query than SERP resellers and can miss exact-string lookups — switch to keyword or auto mode for those. Rate limited to 5 QPS on the free tier.

Getting started

npm i exa-js

Field notes

0 from the community

Loading notes…

Field check

Unverified

Pricing snapshot

$20 free credits at signup (about 2,800 searches) plus $10 in free credits every month, no card. Search $7 per 1K requests for 10 results, $1 per 1K extra results, Contents $1 per 1K pages per content type, Answer $5 per 1K requests.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Exa (https://exa.ai) for this project, then use it only if it fits what we are already building.
Context: Neural web search API for agents. A web search API built on an embeddings index rather than a keyword index, so you query by meaning and describe the page you want instead of guessing keywords. Returns cleaned page contents, highlights and AI summaries in the same call, plus an Answer endpoint that cites its sources.
Reviewer notes (general, not written for this codebase): When an agent needs sources rather than blue links, Exa hands back full extracted text in one round trip. The recurring $10 monthly credit means a small agent never sees a bill.
Watch out for: Neural search costs more per query than SERP resellers and can miss exact-string lookups — switch to keyword or auto mode for those. Rate limited to 5 QPS on the free tier.
Pricing: $20 free credits at signup (about 2,800 searches) plus $10 in free credits every month, no card. Search $7 per 1K requests for 10 results, $1 per 1K extra results, Contents $1 per 1K pages per content type, Answer $5 per 1K requests.
Setup: npm i exa-js
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/exa

Neighbourhood

How Exa sits against the rest of the atlas — swaps, companions and the tools builders actually save alongside it.

Instead of thisFuse.js MiniSearch Pagefind Algolia Brave Search API Chroma Cloudflare Vectorize Elastic Cloud Jina AI LanceDB

Also in Search, vector & RAG

Algolia

algolia.com

Hosted keyword search API

Free tier + paidSearch, vector & RAG

Free: 10K search requests/mo + 50K records. Grow: $0.50 per 1K searches + $0.40 per 1K records (10K searches / 100K records included). Grow Plus $1.75 per 1K searches. Elevate with NeuralSearch is custom.

Open dossier

Brave Search API

brave.com

Independent web index search API

PaidSearch, vector & RAG

$5/month in free credits applied automatically; no standing free query allowance. Search $5 per 1K requests at 50 QPS. Answers $4 per 1K requests plus $5 per million input/output tokens at 2 QPS. Enterprise custom.

Open dossier

Chroma

trychroma.com

Embedded vector DB + cloud

Free tier + paidSearch, vector & RAG

OSS free (Apache 2.0). Chroma Cloud Starter: $0/mo base with $5 free credits, then usage. Team $250/mo + usage with $100 credits. Rates: $2.50 per GiB written, $0.33 per GiB-month stored, $0.0075 per TiB queried, $0.09 per GiB returned.

Open dossier

Cloudflare Vectorize

developers.cloudflare.com

Serverless vector DB on Workers

Free tier + paidSearch, vector & RAG

Workers Free: 5M stored vector dimensions, 30M queried dimensions/mo. Workers Paid ($5/mo): 10M stored and 50M queried included, then $0.05 per 100M stored dimensions and $0.01 per million queried dimensions.

Open dossier