Home
Exa
Exa
Exa is a web search API and AI research platform built specifically for LLMs and agents — semantic and keyword search across the open web with token-efficient highlights, structured outputs, sub-200ms latency tiers, and verticals for code, companies, news, people, research, and financials. The platform pairs the core Search, Contents, and Answer endpoints with Research (asynchronous deep research), Agent (managed multi-step agents at four effort modes), Monitors (scheduled searches with webhooks), and Websets (curated, enrichable result collections). Customers include Cognition (Devin), HubSpot, Monday, Databricks, AWS, and Cursor; Exa raised a $250M Series C to build the search engine for AIs. Open SDKs in Python and JavaScript, an MCP server, Google Sheets and n8n integrations, and a free tier of 1,000 requests/month round out the surface.
7 APIs
7 Capabilities
19 Features
AI Search Web Search Neural Search LLM Agents Research Websets
Exa publishes 7 APIs on the APIs.io network, including Search API, Research API, Monitors API, and 4 more. Tagged areas include AI, Search, Web Search, Neural Search, and LLM.
The Exa catalog on APIs.io includes 7 machine-runnable capabilities and 1 JSON-LD context.
Exa’s developer surface includes developer portal, documentation, getting-started guide, signup flow, sandbox, pricing, changelog, and 29 more developer resources.
Exa's prompt-engineered Search API performs semantic and keyword web search optimized for LLM and agent consumption. Returns a list of relevant results with URLs, titles, author...
Asynchronous multi-step deep-research tasks. Submit a research instruction, Exa orchestrates a Deep Search agent across the live web with structured outputs and web-grounded cit...
Schedule recurring Exa searches and receive webhook notifications when fresh matching content appears on the web. Supports create, list, get, update, delete, batch actions, manu...
Run an Exa-hosted research agent at four effort modes — low ($0.025), medium ($0.10), high ($0.50), and x-high ($2.00) — with built-in web search, content retrieval, structured ...
Curated, enrichable collections of web results scoped to a query, vertical (companies, people, news, research), or imported list. Compose searches, attach LLM-driven enrichments...
Lightweight team-info endpoint at /v0/teams/me — returns the authenticated team identity and metadata for the API key.
Admin API for managing API keys within a team — create, list, get, update, delete keys with optional per-key rate limits and budgets, plus a per-key usage endpoint at GET /api-k...
Run Capabilities with Naftiko — Deploy and orchestrate these API capabilities using Naftiko Fleet.
Run with Naftiko
Exa Agent API — Agent. 6 operations. Lead operation: Create a run. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Monitors API — Monitors. 16 operations. Lead operation: Create a Monitor. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Research API — Research. 3 operations. Lead operation: List research requests. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Search API — Search. 3 operations. Lead operation: Search. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Team Management API — Team Management. 6 operations. Lead operation: Create API Key. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Team API — Team. 1 operations. Lead operation: Get Team Info. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Exa Websets API — Websets. 31 operations. Lead operation: Create a Webset. Self-contained Naftiko capability covering one Exa business surface.
Run with Naftiko
Run Capabilities with Naftiko — Deploy and orchestrate these API capabilities using Naftiko Fleet.
Run with Naftiko
Neural and keyword web search built specifically for LLMs and agents
Token-efficient highlights — claimed ~90% reduction in LLM context cost vs full page text
Latency tiers — fast (~180ms), auto (~1s), deep (~10s)
Verticals — Code, Companies, News, People, Research, Financials
Structured outputs with web-grounded citations
Contents API for full-page text, summaries, highlights, and subpages
Answer endpoint — LLM-grounded answers with sources, streaming optional
Research API — asynchronous deep-research tasks
Agent API — managed research agents with low/medium/high/x-high effort modes
Monitors API — scheduled searches with webhook notifications
Websets — curated, enrichable result collections with imports and webhooks
Webhooks for Webset events, enrichments, monitor runs, and agent runs
Team Management API with per-key rate limits, budgets, and usage reporting
Official SDKs in Python (exa-py) and JavaScript / TypeScript (exa-js)
Exa MCP server and Websets MCP server for agent tool integration
n8n node, Google Sheets extension, Zed editor extension
Free tier — 1,000 requests/month
Pay-as-you-go from $7 per 1,000 search requests; $1 per 1,000 content pages
$1,000 startup/education grant program
0 classes · 12 properties
JSON-LD
Sources
aid: exa-ai
url: https://raw.githubusercontent.com/api-evangelist/exa-ai/refs/heads/main/apis.yml
apis:
- aid: exa-ai:exa-search-api
name: Exa Search API
tags:
- AI
- Search
- Web Search
- Neural Search
- LLM
humanURL: https://exa.ai/docs/reference/search-api-guide
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs/reference/search-api-guide
type: Documentation
- url: https://exa.ai/docs/reference/search
type: Documentation
- url: https://exa.ai/docs/reference/contents-api-guide
type: Documentation
- url: https://exa.ai/docs/reference/answer
type: Documentation
- url: openapi/exa-search-api-openapi.yml
type: OpenAPI
- url: json-schema/exa-search-result-schema.json
type: JSONSchema
- url: json-ld/exa-ai-context.jsonld
type: JSONLD
- type: NaftikoCapability
url: capabilities/search-search.yaml
description: Exa's prompt-engineered Search API performs semantic and keyword web search optimized for LLM and
agent consumption. Returns a list of relevant results with URLs, titles, authors, published dates, relevance
scores, and optional token-efficient highlights, summaries, or full text via the bundled Contents API. The
Answer endpoint returns an LLM-generated answer grounded in web citations. Verticals include Code, Companies,
News, People, Research, and Financials. Latency tiers run from fast (180ms) to auto (~1s) to deep (~10s).
- aid: exa-ai:exa-research-api
name: Exa Research API
tags:
- AI
- Search
- Research
- Agents
- Deep Search
humanURL: https://exa.ai/docs/reference/research/overview
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs/reference/research/overview
type: Documentation
- url: https://exa.ai/docs/reference/research/create-a-task
type: Documentation
- url: https://exa.ai/docs/reference/research/get-a-task
type: Documentation
- url: https://exa.ai/docs/reference/research/list-tasks
type: Documentation
- url: openapi/exa-research-api-openapi.yml
type: OpenAPI
- type: NaftikoCapability
url: capabilities/research-research.yaml
description: Asynchronous multi-step deep-research tasks. Submit a research instruction, Exa orchestrates a
Deep Search agent across the live web with structured outputs and web-grounded citations, and you poll for
the completed report. Lives under /research/v1 with create, get, and list operations.
- aid: exa-ai:exa-monitors-api
name: Exa Monitors API
tags:
- AI
- Search
- Monitors
- Webhooks
- Scheduled
humanURL: https://exa.ai/docs/reference/monitors-api-guide
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs/reference/monitors-api-guide
type: Documentation
- url: https://exa.ai/docs/reference/monitors/create-a-monitor
type: Documentation
- url: https://exa.ai/docs/reference/monitors/list-monitors
type: Documentation
- url: openapi/exa-monitors-api-openapi.yml
type: OpenAPI
- type: NaftikoCapability
url: capabilities/monitors-monitors.yaml
description: Schedule recurring Exa searches and receive webhook notifications when fresh matching content
appears on the web. Supports create, list, get, update, delete, batch actions, manual trigger, and run
history. Two API versions are exposed — the original /monitors namespace and the newer /v0/monitors surface
aligned with Websets.
- aid: exa-ai:exa-agent-api
name: Exa Agent API
tags:
- AI
- Agents
- Search
- LLM
humanURL: https://exa.ai/docs/reference/agent-api-guide
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs/reference/agent-api-guide
type: Documentation
- url: https://exa.ai/docs/reference/agent-api/create-a-run
type: Documentation
- url: https://exa.ai/docs/reference/agent-api/get-a-run
type: Documentation
- url: openapi/exa-agent-api-openapi.yml
type: OpenAPI
- type: NaftikoCapability
url: capabilities/agent-agent.yaml
description: Run an Exa-hosted research agent at four effort modes — low ($0.025), medium ($0.10), high
($0.50), and x-high ($2.00) — with built-in web search, content retrieval, structured outputs, and event
streaming. Create, list, get, cancel, delete, and stream events from runs under /agent/runs.
- aid: exa-ai:exa-websets-api
name: Exa Websets API
tags:
- AI
- Search
- Websets
- Enrichment
- Webhooks
- Imports
humanURL: https://exa.ai/docs/websets/api-guide
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs/websets/api-guide
type: Documentation
- url: https://exa.ai/docs/websets/api/overview
type: Documentation
- url: https://exa.ai/docs/websets/api/websets/create-a-webset
type: Documentation
- url: openapi/exa-websets-api-openapi.yml
type: OpenAPI
- url: json-schema/exa-webset-item-schema.json
type: JSONSchema
- type: NaftikoCapability
url: capabilities/websets-websets.yaml
description: Curated, enrichable collections of web results scoped to a query, vertical (companies, people,
news, research), or imported list. Compose searches, attach LLM-driven enrichments, evaluate items, subscribe
to webhooks for asynchronous events, and import seed lists. Endpoints under /v0/websets, /v0/webhooks,
/v0/events, and /v0/imports.
- aid: exa-ai:exa-team-api
name: Exa Team API
tags:
- AI
- Search
- Team
- Account
humanURL: https://exa.ai/docs
baseURL: https://api.exa.ai
properties:
- url: https://exa.ai/docs
type: Documentation
- url: openapi/exa-team-api-openapi.yml
type: OpenAPI
- type: NaftikoCapability
url: capabilities/team-team.yaml
description: Lightweight team-info endpoint at /v0/teams/me — returns the authenticated team identity and
metadata for the API key.
- aid: exa-ai:exa-team-management-api
name: Exa Team Management API
tags:
- AI
- Search
- Administration
- API Keys
- Team Management
humanURL: https://admin-api.exa.ai/team-management
baseURL: https://admin-api.exa.ai/team-management
properties:
- url: https://exa.ai/docs
type: Documentation
- url: openapi/exa-team-management-api-openapi.yml
type: OpenAPI
- type: NaftikoCapability
url: capabilities/team-management-team-management.yaml
description: Admin API for managing API keys within a team — create, list, get, update, delete keys with
optional per-key rate limits and budgets, plus a per-key usage endpoint at GET /api-keys/{id}/usage. The
foundation for per-workload cost allocation and FinOps reporting against Exa.
name: Exa
tags:
- AI
- Search
- Web Search
- Neural Search
- LLM
- Agents
- Research
- Websets
kind: contract
image: https://kinlane-productions2.s3.amazonaws.com/apis-json/apis-json-logo.jpg
access: 3rd-Party
common:
- type: Portal
url: https://exa.ai
- type: Documentation
url: https://exa.ai/docs
- type: GettingStarted
url: https://exa.ai/docs/getting-started
- type: Documentation
url: https://exa.ai/docs/reference/search-api-guide
- type: SignUp
url: https://dashboard.exa.ai
- type: Sandbox
url: https://dashboard.exa.ai/playground
- type: Pricing
url: https://exa.ai/pricing
- type: ChangeLog
url: https://exa.ai/changelog
- type: Blog
url: https://exa.ai/blog
- type: StatusPage
url: https://status.exa.ai
- type: TermsOfService
url: https://exa.ai/terms
- type: PrivacyPolicy
url: https://exa.ai/privacy
- type: Support
url: https://exa.ai/contact
- type: LinkedIn
url: https://www.linkedin.com/company/exa-ai
- type: GitHubOrganization
url: https://github.com/exa-labs
- type: SDK
url: https://github.com/exa-labs/exa-py
name: Python SDK
- type: SDK
url: https://github.com/exa-labs/exa-js
name: JavaScript / TypeScript SDK
- type: Tool
url: https://github.com/exa-labs/exa-mcp-server
name: Exa MCP Server
- type: Tool
url: https://github.com/exa-labs/websets-mcp-server
name: Websets MCP Server
- type: Tool
url: https://github.com/exa-labs/zed-exa-mcp-extension
name: Zed Exa MCP Extension
- type: Tool
url: https://github.com/exa-labs/exa-for-sheets
name: Exa for Google Sheets
- type: Tool
url: https://github.com/exa-labs/n8n-integration
name: Exa n8n Integration
- type: CodeExamples
url: https://github.com/exa-labs/exa-hallucination-detector
name: Exa Hallucination Detector
- type: CodeExamples
url: https://github.com/exa-labs/company-researcher
name: Company Researcher
- type: CodeExamples
url: https://github.com/exa-labs/exa-deepseek-chat
name: Exa + DeepSeek R1 Chat
- type: CodeExamples
url: https://github.com/exa-labs/exa-o3mini-chat
name: Exa + OpenAI o3-mini Chat
- type: CodeExamples
url: https://github.com/exa-labs/answer-chat-app
name: Exa Answer Chat App
- type: CodeExamples
url: https://github.com/exa-labs/jfk-files-app
name: JFK Files Chat
- type: CodeExamples
url: https://github.com/exa-labs/research-paper-app
name: Research Paper App
- type: CodeExamples
url: https://github.com/exa-labs/websets-news-monitor
name: Websets News Monitor
- type: Authentication
url: https://exa.ai/docs/getting-started/authentication
- type: OpenAPI
url: https://exa.ai/docs/exa-spec.json
- type: OpenAPI
url: https://exa.ai/docs/team-management-spec.yaml
- url: plans/exa-ai-plans-pricing.yml
type: Plans
- url: rate-limits/exa-ai-rate-limits.yml
type: RateLimits
- url: finops/exa-ai-finops.yml
type: FinOps
- type: Features
data:
- Neural and keyword web search built specifically for LLMs and agents
- Token-efficient highlights — claimed ~90% reduction in LLM context cost vs full page text
- Latency tiers — fast (~180ms), auto (~1s), deep (~10s)
- Verticals — Code, Companies, News, People, Research, Financials
- Structured outputs with web-grounded citations
- Contents API for full-page text, summaries, highlights, and subpages
- Answer endpoint — LLM-grounded answers with sources, streaming optional
- Research API — asynchronous deep-research tasks
- Agent API — managed research agents with low/medium/high/x-high effort modes
- Monitors API — scheduled searches with webhook notifications
- Websets — curated, enrichable result collections with imports and webhooks
- Webhooks for Webset events, enrichments, monitor runs, and agent runs
- Team Management API with per-key rate limits, budgets, and usage reporting
- Official SDKs in Python (exa-py) and JavaScript / TypeScript (exa-js)
- Exa MCP server and Websets MCP server for agent tool integration
- n8n node, Google Sheets extension, Zed editor extension
- Free tier — 1,000 requests/month
- Pay-as-you-go from $7 per 1,000 search requests; $1 per 1,000 content pages
- $1,000 startup/education grant program
sources:
- https://exa.ai
- https://exa.ai/pricing
- https://exa.ai/docs/reference/search-api-guide
- https://exa.ai/docs/websets/api-guide
- https://exa.ai/docs/llms.txt
- https://github.com/exa-labs
updated: '2026-05-25'
created: '2026-05-25T00:00:00.000Z'
modified: '2026-05-25'
position: Consuming
description: Exa is a web search API and AI research platform built specifically for LLMs and agents — semantic
and keyword search across the open web with token-efficient highlights, structured outputs, sub-200ms latency
tiers, and verticals for code, companies, news, people, research, and financials. The platform pairs the core
Search, Contents, and Answer endpoints with Research (asynchronous deep research), Agent (managed multi-step
agents at four effort modes), Monitors (scheduled searches with webhooks), and Websets (curated, enrichable
result collections). Customers include Cognition (Devin), HubSpot, Monday, Databricks, AWS, and Cursor; Exa
raised a $250M Series C to build the search engine for AIs. Open SDKs in Python and JavaScript, an MCP server,
Google Sheets and n8n integrations, and a free tier of 1,000 requests/month round out the surface.
maintainers:
- FN: Kin Lane
email: [email protected]
X: apievangelist
url: https://apievangelist.com
specificationVersion: '0.16'