Exa
5.0 out of 5 starsAverage Ratings 1 Rating
Average Ratings 0 Ratings
Description
The Exa API provides access to premier online content through an embeddings-focused search methodology.
By comprehending the underlying meaning of queries, Exa delivers results that surpass traditional search engines.
Employing an innovative link prediction transformer, Exa effectively forecasts connections that correspond with a user's specified intent.
For search requests necessitating deeper semantic comprehension, utilize our state-of-the-art web embeddings model tailored to our proprietary index, while for more straightforward inquiries, we offer a traditional keyword-based search alternative.
Eliminate the need to master web scraping or HTML parsing; instead, obtain the complete, clean text of any indexed page or receive intelligently curated highlights ranked by relevance to your query.
Users can personalize their search experience by selecting date ranges, specifying domain preferences, choosing a particular data vertical, or retrieving up to 10 million results, ensuring they find exactly what they need.
This flexibility allows for a more tailored approach to information retrieval, making it a powerful tool for diverse research needs.
Description
Keenable gives AI agents live web search from an index it crawls and ranks itself: 100B+ documents, under 250ms p95 in US East.
Agents get two tools: search_web_pages returns ranked results with title, URL and snippet, filtered by publish date, crawl date or site. fetch_page_content returns any page as clean markdown. One API key covers the REST API, the MCP server and the CLI for macOS, Linux and Windows. Integrations include LangChain, LlamaIndex, Haystack, Mastra, Vercel AI SDK and NVIDIA NeMo Agent Toolkit.
Quality is measured in public on NEEDLE, a benchmark rerun daily across search providers against an oracle ranking pooled from their results.
AI labs and inference platforms can move to dedicated capacity from $1 per 1,000 requests at 100 RPS, in the cloud or on-premises. Time Machine, in early access, rewinds both the corpus and the ranking to a past moment with one parameter, query_time.
API Access
Has API
No
API Access
Has API
Yes
Integrations
OpenClaw
Yes
AgentKey
Yes
BrainyAI
Yes
Claude Desktop
No
Claude for Legal
No
Convex
No
Dify
No
Disco.dev
Yes
Haystack
No
Hugging Face
No
Integrations
OpenClaw
Yes
AgentKey
No
BrainyAI
No
Claude Desktop
Yes
Claude for Legal
Yes
Convex
Yes
Dify
Yes
Disco.dev
No
Haystack
Yes
Hugging Face
Yes
Pricing Details
$100 per month
Free Trial
No
Free Version
No
Pricing Details
$4 / 1000 requests
For AI Agent builders and AI Enthusiasts: $4 / 1000 requests
For AI Labs and Inference platforms: $1 / 1000 requests at 100 RPS+
For AI Labs and Inference platforms: $1 / 1000 requests at 100 RPS+
Free Trial
Yes
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
Exa.ai
Country
United States
Website
exa.ai/
Vendor Details
Company Name
Keenable
Founded
2026
Country
United States
Website
keenable.ai/