by Exa Labs
Search API that ranks the web by meaning for AI agents and retrieval pipelines, with Lite, Auto and Deep search modes, an asynchronous research Agent and an official MCP server. A free Starter plan with monthly credits needs no payment method.
Pick Exa when a program, not a person, reads the results: one search endpoint covers Lite ($4 per 1,000 requests), Auto and Deep modes and returns clean page text, and the Agent API runs asynchronous research with citations. Look elsewhere if keyword ranking is enough or your queries are sensitive, since zero data retention is Enterprise-only.
Neural semantic search that retrieves conceptually similar results without keyword matching; Exa's own comparison page reports 81% against Tavily's 71% on WebWalker multi-hop retrieval, a vendor-run test.
Exa runs its own crawler and neural index rather than reselling a third-party search engine, which lets it add dedicated people, company and scholarly-works indexes. The core technique, vector embeddings, is not unique to Exa, so the lock-in comes from developer integrations rather than from the technology.
Main trade-off
Usage-based pricing climbs fast at scale: 100,000 requests/month at standard rates costs $700+, and the 10 QPS default rate limit forces teams to build retry queuing rather than offering self-serve upgrades.
| Plan | Monthly price | What it includes |
|---|---|---|
| Starter (Free) | Free | $10 monthly credit and a one-time $10 sign-up bonus, no payment method, every endpoint and all four indexes, 10 Search QPS, 50 agent concurrency |
| Websets Starter | $49/mo | 8,000 credits a month, up to 100 results per Webset |
| Websets Pro | $449/mo | 100,000 credits a month, up to 1,000 results per Webset |
| Developer (Pay as you go) | Pay as you go | Per-request billing by card or bank, standard email support, SOC 2 Type II, up to 25 Search QPS, self-serve Exa Connect providers |
| Enterprise | Custom | Custom MSA and DPA, zero data retention (a $12,000 annual API-credit commitment), SOC 2 Type II and HIPAA, SSO and SCIM, SLAs, custom QPS, up to 1,000 results per search |
Exa runs two pricing systems. The API has no subscription and bills per request; the rates below were read from exa.ai/pricing and the pricing docs on 12 November 2026. Lite search, launched on 19 October 2026, is $4 per 1,000 requests and Auto search is $7 per 1,000 requests, each for up to 10 results, plus $1 per 1,000 for each result beyond ten. Answer is $5 per 1,000. Deep Search is $12 per 1,000 for deep-lite and deep, and $15 per 1,000 for deep-reasoning. Monitors are $2 per 1,000 requests. Contents is $1 per 1,000 pages per content type, and AI page summaries add $1 per 1,000 pages, so a search that also pulls full page text lands near $8 per 1,000. Agent runs at a fixed effort cost $0.012 (minimal), $0.025 (low), $0.10 (medium), $0.50 (high) or $1.00 (xhigh) per run; the auto and ultra modes are metered at $0.10 per Agent Compute Unit and $0.005 per search tool call instead. Email enrichment is $0.02 and phone enrichment $0.07, billed separately. The free Starter plan adds $10 in credits every month plus a $10 onboarding bonus and asks for no payment method; Developer bills the same rates pay-as-you-go. Websets is a separate subscription at $49/month for 8,000 credits or $449/month for 100,000 credits, with a custom Enterprise tier. Enterprise API pricing is custom, with volume discounts and invoice billing, and zero data retention carries a $12,000 annual commitment in API credits.
| Feature | Starter (Free) | Websets Starter | Websets Pro | Developer (Pay as you go) | Enterprise |
|---|---|---|---|---|---|
| Payment method required | No | Yes | Yes (free trial offered) | Card or bank account | Monthly invoicing |
| Search rate limit | 10 Search QPS | No | No | Up to 25 Search QPS | Custom Search QPS |
| Agent concurrency | 50 | No | No | 50 | Custom |
| Credits / results | All endpoints, all four indexes | 8,000 credits/mo, 100 results per Webset, 2 seats | 100,000 credits/mo, 1,000 results per Webset, 10 seats | All endpoints, all four indexes | Up to 1,000 results per search, 5,000 per Webset |
| Zero data retention | No | No | No | No | ✓ ($12,000 annual commitment) |
| Compliance | No | No | No | SOC 2 Type II | SOC 2 Type II and HIPAA, custom MSA and DPA |
| SSO / SCIM | No | No | No | No | ✓ |
| Support | No | Standard | Standard | Standard email | Dedicated Slack channel and SLAs |
| MCP server, Claude Connector, ChatGPT plugin | ✓ | No | No | ✓ | ✓ |
| Exa Connect data providers | No | No | No | Self-serve | Premium providers, bring your own |
Exa is a neural web search API for AI agents and RAG pipelines, and Hokai rates it 4 out of 5: retrieval gains that rest on Exa's own benchmarks, a free Starter plan and an official MCP server, held back by default training use of submitted queries on self-serve plans and a low default search rate limit.
Search API with Lite, Auto and Deep modes
POST /search accepts lite, auto, deep-lite and deep, plus the legacy fast, instant and deep-reasoning types, and filters by category, publish date and up to 1,200 domains.
Deep Search and Agent for deep research
Deep Search answers on the search endpoint (deep-lite at a consistent 4-second latency), while Agent runs asynchronously at /agent/runs across seven effort modes with schema-validated JSON output and citations.
Four indexes, not one web crawl
Web, people, company and scholarly-works indexes are all open on the free Starter plan, and the publication category gained 350 million publications on 23 July 2026, so agents query a pre-filtered vertical instead of generic open-web results.
Contents: clean text instead of HTML
Returns parsed page text, query-relevant highlights and AI summaries for URLs you already hold, with configurable livecrawl and a much higher default query rate than the search endpoint.
MCP server, Claude Connector and ChatGPT plugin
A free Model Context Protocol server plus a Claude Connector, a ChatGPT plugin and 50+ integrations, all on the free tier, so Claude, Cursor and VS Code reach Exa search without custom API glue.
Monitors and Exa Connect
Monitors run saved searches on a schedule (one hour is the minimum interval) at $2 per 1,000 requests and push new results by webhook, and Exa Connect, launched 24 June 2026, routes Agent requests to data providers such as Similarweb and Fiber.ai.
| Tool | Price from | Free plan | Runs on | Rating |
|---|---|---|---|---|
| $49/mo | Yes | Web | 4.0 | |
| $17/mo | Yes | Web · iOS · Android · Mac · Windows | 4.4 | |
| AlgoliaAlgolia indexes and searches your own content at millisecond speed and is the right answer for site or in-app search. Exa searches the open web for research and agent grounding, and cannot search a dataset you have not published. | -- | Yes | Web · iOS · Android · Mac · Windows | 4.0 |
| $20/mo | Yes | Web | -- |
Proprietary neural web index built and crawled by Exa Labs.
Exa's Search API charges $4 per 1,000 requests for Lite search and $7 for Auto, each returning up to ten results, according to its pricing page on 12 November 2026. Answer calls are $5 per 1,000, Deep Search runs $12 per 1,000 (deep-lite and deep) or $15 per 1,000 (deep-reasoning), and pulling page text adds $1 per 1,000 pages. Agent runs at a fixed effort range from $0.012 to $1.00 each. Websets starts at $49 a month, and Enterprise is quoted by sales.
The free Starter plan gives a $10 credit each month and a one-off $10 onboarding bonus, with no payment method needed. At the $7-per-1,000 Auto rate the monthly credit covers roughly 1,400 searches, and Exa's pricing docs put it at up to 2,500 Lite searches. It includes every endpoint, all four indexes and the MCP server.
Tavily is the closest agent-first rival and leans on LangChain and LlamaIndex integrations; Nebius agreed to buy it on 10 February 2026 and it still runs under its own brand. You.com sells a search API for grounding language models. Perplexity's Sonar API returns a cited answer in a single call. Algolia fits when you are searching your own content rather than the open web.
Exa's own comparison page reports 81% against Tavily's 71% on WebWalker multi-hop retrieval, but that is a vendor-run evaluation, so test both on your own queries. Exa runs its own neural index with people, company and publication verticals and ships an official MCP server for Claude and Cursor. Tavily integrates more tightly with LangChain out of the box and has been owned by Nebius since 2026.
Minutes. Sign up at exa.ai with no card, copy an API key, then send POST https://api.exa.ai/search with the key in an x-api-key header and a JSON body holding your query. The type defaults to auto; add contents with text set to true to get page text in the same call. The exa-py and exa-js SDKs wrap the same endpoint, and the free MCP server exposes it inside Claude or Cursor.
Exa is an AI-native web search API built by Exa Labs (San Francisco, founded 2021) for large language models, autonomous agents, and retrieval-augmented generation pipelines. Harvard classmates Will Bryk (CEO) and Jeffrey Wang started the company roughly a year before ChatGPT launched, betting that AI needed a search engine built for machine consumption rather than human browsing.
The core mechanism is embeddings-based retrieval: Exa encodes every indexed page as a dense vector using its own trained neural networks, then runs nearest-neighbour lookups when a query arrives, surfacing pages whose vectors sit closest to the query. That captures conceptual proximity keyword search misses. Every request returns clean extracted text rather than raw HTML, cutting the token overhead of the downstream LLM call.
The Exa Search API is one endpoint, POST https://api.exa.ai/search, authenticated with an API key sent in an x-api-key or Authorization: Bearer header. Its type field sets the trade-off: auto is the default and balances quality against speed, fast trims latency for interactive work, instant targets sub-200ms agent loops, and three deep types are covered in the next paragraph. One call returns up to 100 results with title, URL, published date and author, filtered by category (company, people, news, publication, financial report or personal site), by publish date, and by up to 1,200 included or excluded domains. Page text, highlights and summaries come back in the same request through the contents option, and every response reports its own dollar cost. Separate endpoints handle /contents for URLs you already hold, /answer for a cited answer to a question, Monitors for scheduled searches delivered by webhook, and the Agent API.
Exa sells deep research two ways. Deep Search stays on the /search endpoint: deep-lite returns synthesised results at a consistent 4-second latency, deep runs multi-step research with synthesis, and deep-reasoning adds stronger reasoning for analysis and decision work. That last type is also the replacement for the old /research endpoint, which Exa retired on 1 April 2026 according to its changelog. Exa Agent, released on 16 June 2026, is the asynchronous route: you create a run with POST /agent/runs, then stream it or poll it, and it returns a written answer, JSON validated against an outputSchema you supply, and the citations behind both. Five fixed effort modes run from minimal to xhigh. auto is metered with a default cap of $5 a run, and ultra, added on 24 September 2026 for large list building and exhaustive multi-source research, is metered with a default cap of $20 that the caller can raise or lower.
There are three account plans. Starter is free with no payment method and includes every endpoint, all four indexes (web, people, company and scholarly works, the last expanded by 350 million publications on 23 July 2026), the MCP server, a Claude Connector and a ChatGPT plugin. Developer is pay-as-you-go and lifts search throughput to 25 queries per second. Enterprise adds zero data retention, HIPAA, SSO and SCIM, SLAs, custom indexes and larger result sets per search. Websets, the no-code dataset product, is a separate subscription. Exact rates for all of it sit in the Pricing section below.
Exa plugs into an agent stack rather than replacing one. The official MCP server connects it to Claude and Cursor, which Exa names as a customer using it to fetch current documentation, and the Python and JavaScript SDKs sit comfortably under LangChain or LlamaIndex retrieval code. For the wider field, browse the retrieval infrastructure category or read Hokai's guide to retrieval infrastructure tools. The neighbouring API choices are weighed in Algolia vs You.com and Context.dev vs You.com, and the 2026 AI tool ecosystem guide places Exa in the wider stack. On 12 November 2026 we called Exa's hosted MCP endpoint at mcp.exa.ai with no API key: it listed two tools, web_search_exa and web_fetch_exa, and one search for its own Lite pricing returned Exa's pricing page with "From $4/1k requests". That is one query, not a retrieval-quality test.
Who should not buy it: if a person, not a program, reads the result, Perplexity gives a cited answer with no integration work. If the job is searching your own catalogue or docs, Algolia is the right tool, because Exa only searches the public web. On the API side, You.com and Context.dev are the head-to-heads worth running against your own queries before committing. Also read the privacy terms before sending anything sensitive: on Starter and Developer, Exa may use submitted queries to improve and train its models, and zero data retention is sold only on Enterprise. Exa's Vanta trust centre carries SOC 2 Type II and a HIPAA attestation dated 17 June 2026, with the audit reports behind an access request.
Product facts on this page (pricing, plans, integrations, compliance) are read from Exa Labs's own pages and documentation. The verdict is Hokai's reading of them, not the vendor's claim.