Exa is web search and data infrastructure built for AI. A single API lets your applications and agents find the exact content they need on the web and turn it into clean, structured, up-to-date data.
Exa gives your applications and agents a single API to find the exact content they need on the web and turn it into clean, structured, up-to-date data. Core capabilities include:
Search: find the most relevant webpages using Exa's embeddings-based and keyword search.
Contents: retrieve clean, parsed, token-efficient content from any page or search result.
Research: run deep, multi-step research that returns grounded answers with citations and structured outputs.
Exa continually expands its capabilities across search, crawling, and research. See the documentation for the latest features and endpoints.
Pricing: usage is billed in Exa API credits (1 credit = $1.00 USD). Credits are consumed across Search, Contents, Research, and other Exa APIs according to the Exa rate card at https://exa.ai/pricing. Prepaid contracts and private offers commit a credit balance (e.g. a $2,000 contract = 2,000 credits).
For custom pricing, EULA, or a private contract, please contact sales@exa.ai.
Highlights
One API for search, crawling, and research, built for AI agents
Business-grade web search and content retrieval at any scale
Structured, up-to-date web data your applications can rely on
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
This listing offers one pricing dimension: the ExaSearch Contract, billed in units. You commit to a contract for search API access rather than paying per request as you go. Buying through this single dimension gives you a set unit quantity under one agreement. There are no separate tiers, instance sizes, or add-on dimensions to choose between here. To size your commitment or arrange volume terms, work directly with the vendor.
Top-of-mind questions for buyers
What counts as one ExaSearch unit for billing under this contract?
Units map to search API usage. The API meters requests, page contents retrieved, and research runs. Web search requests and deep search requests bill per thousand requests. Full page content retrieval bills per thousand pages. Async research runs bill per run, based on the effort level you set.
What drives my usage under this contract — search requests, page contents, or research runs?
Several activity types draw down your contract. Web search and deep search bill per thousand requests. Page content retrieval bills per thousand pages. Async agent runs bill per run, scaling with compute units, search tool calls, and any contact enrichment. All applicable charges apply together as you use the API.
How does cost change when I run deeper research versus fast searches?
Fast web search and page retrieval bill at set per-thousand rates. Deep search and reasoning workflows cost more per thousand requests because they run multi-step processes. Async agent runs can use a fixed effort mode for predictable per-request pricing, or auto mode where compute scales to the task.
exa.ai+1
Helpful?
Vendor refund policy
All fees are non-cancellable and non-refundable except as required by law.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
MCP
API
Exa provides an official Model Context Protocol (MCP) server, allowing MCP-compatible assistants and agents (including Codex, Cursor, Claude Code, and any other MCP client) to use Exa as a native tool.
Configure your MCP client to connect to <https://mcp.exa.ai/mcp>
Authenticate using an Exa API key created in the Exa Dashboard (<https://dashboard.exa.ai>). All MCP requests consume Exa API credits from your organization's prepaid balance according to the standard API pricing.
Email support is available Monday through Friday at support@exa.ai. Documentation, API references, and integration guides are available at https://docs.exa.ai. For custom pricing, enterprise agreements, EULA, or private contracts, contact sales@exa.ai.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
The Exa MCP Server brings Exa's web search and data infrastructure directly to AI agents through MCP. Give agents access to clean, structured, up-to-date web data.
The Brave Search API is the largest commercially-available developer tool for programmable Web search used to connect apps and AI to the global internet.
Used to power AI systems, AI Agents, research tools, data pipelines, and more, You.com's Research API is a single API call that researches a question and returns a complete, cited answer. Leveraging AI, the API reads multiple sources, cross-references what it finds, and synthesizes everything into a structured response with inline citations.Most applications that need web-grounded answers today require building a pipeline: search for results, fetch and parse pages, feed content to an LLM, handle citations. The Research API replaces that pipeline. You send a question, set a research effort level, and get back a Markdown-formatted answer with numbered citations tied to sources, ready to render or feed downstream. There is no additional parsing, ranking, or synthesis required on your end.
Self-managed Solr is complex, unreliable, and slows innovation. Managed Search delivers built-in compliance and reliability so you release faster, cut risk, and make search predictable. SLA-backed uptime and automated operations free your talent from infrastructure work so you can scale with confidence.
Comprehensive Industry Research, Though Some Results Are Outdated
Reviewed on Oct 14, 2026
Review provided by G2
What do you like best about the product?
I use Exa to research recent developments in my industry. It pulls daily articles from around the world about AI in my sector, which is hugely useful in my role. I get more detailed insights, links, and articles than I can generate with LLMs, with hundreds of online sources instead of just an overview summary. I like having an extensive list of links to pick from and compare, and the comprehensive search finds relevant articles from all over, even when they don’t contain my search term. Exa is much more thorough than Claude and ChatGPT, and I found the initial setup very easy.
What do you dislike about the product?
Sometimes when I search for new articles, Exa also brings up old or outdated ones.
What problems is the product solving and how is that benefiting you?
Exa gives me much more detailed insights, links, and articles than I can get from LLMs.
Daniel M.
Efficient Semantic Search for Accurate, Relevant Results
Reviewed on Oct 14, 2026
Review provided by G2
What do you like best about the product?
I mainly use Exa to find accurate, high-quality information. It saves me a lot of time by finding relevant links and clean text directly. I like how efficient it is and how it understands what I need. I value the semantic search feature, and switching between teams makes it easier to manage different projects. The initial setup was very simple.
What do you dislike about the product?
Nothing.
What problems is the product solving and how is that benefiting you?
I use Exa to search for accurate, high-quality information. It saves me a lot of time by finding relevant links and clean text directly. Its semantic search is efficient and understands what I need, and it makes it easier to manage different projects.
Prateek M.
Fast, High-Quality Search Results with a Clean, Uncluttered UI
Reviewed on Oct 14, 2026
Review provided by G2
What do you like best about the product?
It gets the job done really well. The best part is the quality of the search results, and it’s very fast—results come back quickly, and the pages are clean and easy to read. The dashboard UI is also solid and uncluttered. On top of that, it was very easy for us to set up because the documentation was clear and genuinely helpful. They also offer integrations, like with LangChain, and they have MCPs as well, which worked out of the box for us.
What do you dislike about the product?
Everything is fine overall, and there’s nothing particularly significant to point out. The only real issue for me is the cost, which goes up when you want full-page content. One other small thing is that their AI summaries can be a bit generic, but that’s a minor concern.
What problems is the product solving and how is that benefiting you?
In our workflows, we needed search results we could rely on to keep everything dependable and ensure our downstream systems run properly, and Exa delivers exactly that for us. Their support docs are very solid, so it’s straightforward to set up, experiment with, and use the tool in practice it saves alot of our time.
Kierra G.
Exa Review
Reviewed on Oct 14, 2026
Review provided by G2
What do you like best about the product?
I like that you can search on the main page by latency and category.
What do you dislike about the product?
There’s a long wall of customer logos but only one real testimonial, from Cognition. The case studies are linked rather than summarized, so the homepage never shows a concrete before-and-after result.
What problems is the product solving and how is that benefiting you?
Google-style results are ten blue links tuned for clicking. An LLM needs the relevant content itself, not a list of pages it then has to fetch and read
Pedro G. R.
Deep Web Search, Seamless Claude Access—Could Be Smoother and Cheaper
Reviewed on Oct 14, 2026
Review provided by G2
What do you like best about the product?
I like that Exa's web search is comprehensive and goes deeper than most web searches. It can find researchers on a topic, which is really helpful, and I find the web search instrumental. I also like the MCP connector to Claude because I can access Exa directly from my Claude desktop without signing in to Exa. The initial setup was super easy.
What do you dislike about the product?
At times, Exa is a bit clunky, and I’d really appreciate it if they lowered the price.
What problems is the product solving and how is that benefiting you?
I use Exa through Claude for web search. It goes deeper than most searches and can find researchers on a topic. I like that it’s comprehensive, and the MCP connector gives me direct access from Claude desktop without signing in.