📖 The AI Tool Bible

Exa

✓ Editorially verified

Web search API built for AI agents, with structured outputs and token-efficient highlights.

Freemium· Free playground; paid usage-based plans; enterprise on requestRAGProprietary neural + keyword search8.0 / 10

Visit website →

Best for

Pick Exa if you are wiring web retrieval into an AI agent and want a single API that returns clean, schema-shaped, token-efficient results.

Skip if

Skip it if you need a self-hosted or open-source search stack, or your retrieval is purely over internal documents.

Exa (formerly Metaphor) is a web search and retrieval API designed for AI agents and LLM applications that need fresh, structured web data. It offers fast keyword-and-neural search, automated crawling, JSON outputs against custom schemas, and a Highlights mode that extracts the relevant excerpts of a page so callers can cut up to 90% of tokens they would otherwise feed to a model. A Deep Research mode lets you trade latency for thoroughness.

The target customer is anyone building retrieval into an agent stack: Cognition, Cursor, HubSpot and Monday.com are cited on the homepage. Beyond general web search, Exa has vertical indexes for companies, people, and code repositories, which is the differentiator versus rolling your own SerpAPI + scraper pipeline. Pricing is usage-based with a free playground; production tiers are paid and enterprise plans include SSO, SOC 2 Type II, and zero-retention options.

It is proprietary and API-only, with an MCP server for plug-in use from Claude, Cursor and similar clients. If you want a pure open-source self-hosted search, look elsewhere; if you want managed retrieval that drops into an agent in an afternoon, this is one of the cleaner options.

Editor's take

Exa has quietly become the default web-search layer for serious agent builders, and the rebrand from Metaphor reflects that maturity. The Highlights and structured-output features pay for themselves in token savings alone, and the vertical indexes are a real moat. Worth a benchmark against your current SerpAPI + scraper stack.

— The AI Tool Bible editorial team

Pros

✅ Purpose-built for LLM/agent use, not retrofitted consumer search
✅ Highlights mode dramatically cuts tokens sent to the model
✅ Structured JSON outputs against custom schemas
✅ Vertical indexes for companies, people, and code
✅ SOC 2 Type II with zero-retention enterprise option

Cons

⚠️ Proprietary, closed source
⚠️ Pricing not transparent on homepage beyond the free playground
⚠️ Coverage and freshness depend on Exa's crawl, not yours

Use cases

agent-web-searchrag-retrievalcompany-researchpeople-searchcode-searchdeep-research

Explore related

Exa alternatives →All RAG Runs on api Tools with an API Free trial available More freemium tools

Compare with similar tools

Exa vs Pinecone

Side-by-side breakdown

Exa vs LlamaIndex

Side-by-side breakdown

Exa vs Elasticsearch Vector Search

Side-by-side breakdown

Pinecone

RAG · Hosted vector DB (not an LLM)

Managed vector database for production-scale similarity search.

Freemium· Free starter; serverless pay-as-you-go from $0.33/1M readsmanaged vector DBproduction RAG

LlamaIndex

RAG · BYO (Claude / GPT / open)

Data framework for connecting LLMs to your data.

Freemium· Free open-source; LlamaCloud paidRAGdata ingestion

Elasticsearch Vector Search

RAG · BYO embeddings (OpenAI, Cohere, Hugging Face, Mistral, Bedrock, Vertex, Azure) plus Elastic's built-in ELSER sparse model and E5 dense model

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine

Freemium· Free self-managed open-source core; Elastic Cloud Serverless usage-based (VCU-priced); Elastic Cloud Hosted from ~$95/mo (Standard) with Gold/Platinum/Enterprise tiers; custom Enterprise pricing.RAG chatbot over enterprise docsHybrid semantic + keyword product search

Snowflake Cortex

RAG · Anthropic Claude, Meta Llama, Mistral Large 2, Snowflake Arctic

Generative AI and RAG built into the Snowflake data cloud

Enterprise· Consumption-based via Snowflake credits; requires a Snowflake account. Free trial available at signup.snowflake.com. LLM function usage priced per credit per million tokens; Cortex Search and Analyst billed separately by credits consumed.Enterprise RAG chatbot over governed dataNatural-language SQL for business analysts

DataStax Astra DB

RAG · Bring-your-own embeddings; integrates with OpenAI, Cohere, Hugging Face, Mistral, NVIDIA NIM, and Vertex AI via server-side vectorize

Serverless vector and document database for production RAG and AI agents

Freemium· Free tier with generous monthly credits; Pay-as-you-go serverless consumption pricing (compute + storage + data transfer); Provisioned Capacity Units (PCUs) for predictable workloads; Enterprise plans with committed spend and private deployment options.RAG chatbot over enterprise documentsAgent long-term memory store

MongoDB Atlas Vector Search

RAG · Bring-your-own embeddings (OpenAI, Cohere, open models); native Voyage AI embeddings and rerankers

Vector search built into the operational database you're already using.

Freemium· Free M0 shared cluster / Pay-as-you-go on dedicated Atlas clusters (compute + storage + optional Search Nodes) / Enterprise Advanced self-managed licensingRAG over enterprise documentsProduct and content recommendation engines