Join CRM Contacts
Merge contact lists with different email domains, name variations, and typos, when the primary keys come from different systems.
$4.90 • 99.9% accuracy • 1,000+ contacts
Merge
Match datasets when joins need research
A matcher figures out which rows belong together, even when names, IDs, and spellings differ. Join tables or deduplicate without matching keys.
Case studies
Associate Related Entities
Merge tables when the rows represent different types of related entities, like vendors to products, or companies to CEOs.
$9 • 91.1% accuracy • 2,000 products
📊
Company → Ticker • CEO → Company
S&P 500 Entity Matching
Match companies to tickers, CEOs to companies. Cascade from exact → fuzzy → LLM → web.
$1 • 100% accuracy • 438 companies
Give your AI a team of matchers
Claude Code
claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp Then ask Claude to merge your data.
Python SDK
pip install futuresearch
from futuresearch import merge
result = merge(
left=contacts,
right=companies,
criteria="Match contact's
company to company name"
)Pricing
Start with $20 in free credits. No credit card required. Pay only for what you use—costs scale with match complexity.
| Task | Rows | Cost/row | Accuracy |
|---|---|---|---|
| Company → Ticker | 438 | 0.23¢ | 100% |
| Contact matching | 1,176 | 0.42¢ | 99.9% |
| Product → Vendor | 1,996 | 0.45¢ | 91.1% |
Why costs vary
Matchers use a cascade strategy: exact match → fuzzy match → LLM → web search. Simple matches (exact strings) are nearly free. Complex matches (Photoshop → Adobe) require LLM reasoning. Ambiguous matches may trigger web research. You only pay for the intelligence each row needs.
Start merging your data
Start with $20 free credit. No credit card required.