Start for free with over $120 in credits per year
Use cases
Starter
$20 credits on sign-up with $10 credits every month. No payment method required
Includes:
Data
Everything in starter, plus:
Data
Enterprise
Tailored for your organization to solve for large scale requirements and enterprise needs
Everything in developer, plus:
Data
Web search tool calls for agents
Webpage text and highlights
Configurable latency: 180ms to 1s
Asynchronous deep research runs
Structured outputs with citations
Access leading data providers
Full page contents for LLM context
Token efficient highlights
Configurable livecrawl policies
Multi-step agent workflows
Answers with structured outputs
Web grounded citations
Identify fresh events on the web
Runs searches at a specified cadence
Receive updates with webhooks
Search over millions of GitHub repos, docs, and Stack Overflow with high-accuracy code retrieval.
Exa Search
Customer Stories
Coding agents use Exa for low latency search across millions of repos.
| 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 | - |
| AI page summaries(per 1k pages) | $1 | $1 | $1 | $1 | $1 | - |
Agent pricing
By default, Agent uses effort: auto. Compute and tool usage scale to the task. Choose a fixed effort mode for predictable per-request pricing.
For request parameters, run lifecycle events, and examples, see the Agent docs.
Usage components
Fixed effort modes*
*Contact enrichment for emails and phone numbers is billed separately.
Pull live data from specialized third-party providers through a single Exa integration. Billed on top of Agent usage.
Self-serve providers
Available on request
Benefits
Build comprehensive web search into your startup or education project—for free.
$1000 worth of free credits
Build, launch, and test search