Exa
"Web search, built for AI agents. One API for search, crawling, and research agents." [1]
Exa is a REST API for web search, content crawling, and research agents, designed specifically as a grounding and retrieval layer for LLM applications and AI agents. It offers neural search, full-page content extraction, news and research paper search, scheduled monitors, and an answer-with-citations endpoint, with SDKs for Python, JavaScript, and an MCP server. Pricing is usage-based at $1.00 per 1,000 requests, with a free tier of 20,000 requests per month and self-serve signup; an enterprise plan is available. The service holds SOC 2 Type 2 and HIPAA certifications, and customers include Cursor, Notion AI, HubSpot, and Databricks.
Best for / Avoid if
Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)
Scores
- 65 / 100Agent friendliness
- 100 / 100Pricing transparency
- 85 / 100Setup speed
- 55 / 100Docs quality
- 100 / 100Procurement ease
- 40 / 100Trust readiness
Pricing & procurement
- Pricing model
- Usage-based
- Published pricing
- ✓ Yes
- Free tier
- ✓ Yes
- Free tier details
- 20,000 requests per month recurring monthly allowance at no cost; includes web search tool calls, webpage text and highlights, and configurable latency (180ms to 1s).
- Self-serve signup
- ✓ Yes [2]
- Requires sales call
- ✗ No
- Enterprise plan
- ✓ Yes [3]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Free | Search requests (recurring monthly allowance) | 20,000 requests/month | $0 | source |
| Pay-as-you-go | Search (includes text + highlights for up to 10 results) | 1,000 requests | $7 | source |
| Pay-as-you-go | Search — additional results above 10 | 1,000 requests | $1 | source |
| Pay-as-you-go | Deep Search (Exa Deep) | 1,000 requests | $12 | source |
| Pay-as-you-go | Deep-Reasoning Search (Exa Deep Reasoning) | 1,000 requests | $15 | source |
| Pay-as-you-go | Deep Search / Deep-Reasoning — additional results above 10 | 1,000 requests | $1 | source |
| Pay-as-you-go | Answer endpoint (base, includes up to 10 results) | 1,000 requests | $5 | source |
| Pay-as-you-go | Answer endpoint — additional results above 10 | 1,000 requests | $1 | source |
| Pay-as-you-go | Contents (per content type: text or highlights) | 1,000 pages | $1 | source |
| Pay-as-you-go | AI page summaries add-on (all endpoints) | 1,000 pages | $1 | source |
| Pay-as-you-go | Monitors (scheduled searches with webhook delivery) | 1,000 requests | $15 | source |
| Agent — Low effort | Agent fixed-effort request | request | $0.025 | source |
| Agent — Medium effort | Agent fixed-effort request | request | $0.1 | source |
| Agent — High effort | Agent fixed-effort request | request | $0.5 | source |
| Agent — X-High effort | Agent fixed-effort request | request | $1 | source |
| Agent (usage-based) | Agent Compute Units | ACU | $0.1 | source |
| Agent (usage-based) | Search tool calls | search call | $0.005 | source |
| Agent (usage-based) | Email enrichment | $0.02 | source | |
| Agent (usage-based) | Phone enrichment | phone number | $0.07 | source |
| Websets Free | Websets credits (recurring monthly allowance, limited to 25-result websets) | 1,000 credits/month | $0 | source |
| Websets Core | Websets subscription (8,000 credits/month) | month | $49 | source |
| Websets Pro | Websets subscription (100,000 credits/month) | month | $449 | source |
Capabilities
- Supported actions
- web_search, get_contents, find_similar, answer_with_citations, stream_answer, deep_research, monitors_scheduled_search, news_search, company_search, people_search, research_paper_search, financial_report_search, structured_output_extraction [4]
- Regions
- global [5]
- Input types
- natural language query, URL, JSON output schema, domain filters, date range filters, category filters, system prompt, user location (ISO country code) [6]
- Output types
- JSON, full page text (markdown), token-efficient highlights, LLM-generated summaries, structured JSON via outputSchema, grounded answers with citations, server-sent events (streaming), webhook delivery (Monitors)
- Webhooks
- ✓ Yes [7]
- Sandbox / test mode
- ✗ No [8]
- SDK languages
- Python, JavaScript, MCP (npm) [9]
- MCP server
- ✓ Yes [10]
Trust & compliance
- SOC 2
- SOC 2 Type II [11]
- HIPAA
- ✓ Yes [12]
- GDPR
- – Unknown
- ISO 27001
- – Unknown
- PCI DSS
- – Unknown
- Published SLA
- ✗ No [13]
- Rate limits
- /search: 10 QPS; /contents: 100 QPS; /answer: 10 QPS; /research/v1 (legacy): 15 concurrent tasks [14]
- Known restrictions
- company and people category indexes do not support date or domain exclusion filters, maximum 100 results per request (contact sales for higher), find_similar endpoint is deprecated (still functional), Zero Data Retention requires enterprise plan agreement, Monitors webhook URLs must be final destinations - redirects are not followed [15]
Developer surface
Integration
Adoption & maturity
- Launched
- 2021-01-01
- Notable customers
- Cursor, Cognition, HubSpot, OpenRouter, monday.com, CodeRabbit, 11x, Notion AI, Databricks
Other Web Search APIs
Firecrawl
The API to search, scrape, and interact with the web at scale.
Brave Search API
"The Brave Search API provides developers with access to Brave Search results and enables building AI products, chatbots, coding assistants, and AI-search engines with real-time web data."
Tavily Search API
"Real-time search, extraction, research, and web crawling through a single, secure API."
Linkup
"Production-grade Web Search API for AI"
Jina AI Search Foundation (DeepSearch / Reader)
"Your Search Foundation, Supercharged."
Parallel Search API
"The highest accuracy web search for your AI"
References
- ↑Description: exa.ai
- ↑Self-serve signup: exa.ai
- ↑Enterprise plan: exa.ai
- ↑Supported actions: exa.ai · exa.ai
- ↑Regions: exa.ai
- ↑Input types: exa.ai
- ↑Webhooks: exa.ai
- ↑Sandbox: exa.ai
- ↑SDK languages: exa.ai
- ↑MCP server: exa.ai · exa.ai
- ↑SOC 2: exa.ai
- ↑HIPAA: exa.ai
- ↑Published SLA: exa.ai
- ↑Rate limits: exa.ai
- ↑Known restrictions: exa.ai · exa.ai
Change history
- 2026-06-15 Score Docs Quality: 15 → 55
- 2026-06-15 Score Agent Friendliness: 30 → 65
- 2026-06-14 Llms Txt Present: No → Yes
- 2026-06-14 Llms Txt URL: (none) → https://docs.exa.ai/llms.txt
- 2026-06-14 Has Structured Data: (none) → Yes
- 2026-06-14 Robots Allows Agents: (none) → Yes
- 2026-06-14 Changelog URL: (none) → https://docs.exa.ai/changelog
- 2026-06-14 API Reference URL: (none) → https://docs.exa.ai/docs/reference/search-api-guide
- 2026-06-14 Capabilities: {} → {"news":true,"semantic":true,"ai_answer":true,"agent_ready":true,"zero_retentio…
- 2026-06-14 Summary Md: (none) → Exa is a REST API for web search, content crawling, and research agents, design…
- 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-14 Score Agent Friendliness: (none) → 30
- 2026-06-14 Score Pricing Transparency: (none) → 100
- 2026-06-14 Score Setup Speed: (none) → 85
- 2026-06-14 Score Docs Quality: (none) → 15
- 2026-06-14 Score Procurement Friction: (none) → 100
- 2026-06-14 Score Trust Readiness: (none) → 40
- 2026-06-14 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
- 2026-06-14 Llms Txt Present: (none) → No
- 2026-06-14 Docs URL: (none) → https://docs.exa.ai
- 2026-06-14 Status Page URL: (none) → https://status.exa.ai
- 2026-06-14 Rendering: (none) → static
- 2026-06-14 Enterprise Plan Available: set to Yes
- 2026-06-14 SOC 2: set to type_2
- 2026-06-14 HIPAA: set to Yes
- 2026-06-14 SLA Published: set to No
- 2026-06-14 Data Retention Policy URL: set to https://exa.ai/privacy-policy
- 2026-06-14 Documented Rate Limits: set to /search: 10 QPS; /contents: 100 QPS; /answer: 10 QPS; /research/v1 (legacy): 15…
- 2026-06-14 Rate Limit Requests: set to 10
- 2026-06-14 Rate Limit Window: set to second
- 2026-06-14 Known Restrictions: set to company and people category indexes do not support date or domain exclusion fil…
- 2026-06-14 Auth Methods: set to api_key
- 2026-06-14 Auth Docs URL: set to https://exa.ai/docs/reference/search-api-guide
- 2026-06-14 API Style: set to rest
- 2026-06-14 Base URL: set to https://api.exa.ai
- 2026-06-14 Versioning Scheme: set to none
- 2026-06-14 Stability: set to ga
- 2026-06-14 Deprecation Policy URL: set to https://exa.ai/docs/changelog/may-2026-api-deprecations
- 2026-06-14 MCP URL: set to https://mcp.exa.ai/mcp
- 2026-06-14 Quickstart URL: set to https://exa.ai/docs/reference/quickstart
- 2026-06-14 Idempotency Supported: set to No
- 2026-06-14 Error Format: set to vendor-specific
- 2026-06-14 Webhook Signing: set to HMAC-SHA256 (Exa-Signature header, t= timestamp + v1= signature)
- 2026-06-14 Webhook Events URL: set to https://exa.ai/docs/websets/api/webhooks/event-types
- 2026-06-14 Requires Verification: set to No
- 2026-06-14 Starting Price Usd: set to 1
- 2026-06-14 Price Basis: set to 1,000 requests
- 2026-06-14 Slug: set to exa
- 2026-06-14 Launched At: set to 2021-01-01
- 2026-06-14 Notable Customers: set to Cursor, Cognition, HubSpot, OpenRouter, monday.com, CodeRabbit, 11x, Notion AI,…
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/exa \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/exa/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'