Start searching for free
Run up to 1,000 requests per month for free
Use cases
Search
Real-time search data with token efficient page contents
Web search tool calls for agents
Webpage text and highlights
Configurable latency: 180ms to 1s
Deep Search
Research with structured outputs optimized for complex queries
Multi-step agent workflows
Answers with structured outputs
Web grounded citations
Contents
Full page web contents, with highlights optimized for AI
Full page contents for LLM context
Token efficient highlights
Configurable livecrawl policies
Monitors
Track new events and updates across the web
Identify fresh events on the web
Runs searches at a specified cadence
Receive updates with webhooks
Answer
Fast web grounded answers with streaming responses
Low latency answers
Web grounded citations
Streaming responses
Use cases
Coding agents
Search over millions of GitHub repos, docs, and Stack Overflow with high-accuracy code retrieval.
- Search docs, repos, and changelogs in real time
- Use sub-200ms search options inside latency-sensitive agent loops
- Ground code generation with current package and API references
Exa Search
Customer Stories
Cursor uses Exa to get the latest docs for more accurate code
Coding agents use Exa for low latency search across millions of repos.
Endpoint pricing
| Endpoint | Search | Deep Search | Deep-Reasoning Search | Contents | Monitors | Answer |
|---|---|---|---|---|---|---|
| Base price, with up to 10 results(per 1k requests) | $7 | $12 | $15 | $1(per 1k pages) | $15 | $5 |
| Cost per additional result above 10(per 1k requests) | $1 | $1 | $1 | - | $1 | $1 |
| AI page summaries(per 1k pages) | $1 | $1 | $1 | $1 | $1 | $1 |
Enterprise
For high volume, custom datasets, enterprise security, and more.
Powerful search
Enterprise-Grade Support
Custom Pricing
Startup and Education Grants
Build comprehensive web search into your startup or education project—for free.
$1000 worth of free credits
Build, launch, and test search