DeepTable
DeepTable converts human-formatted Excel spreadsheets into relational tables prepared for SQL workflows.
What DeepTable is
DeepTable converts human-formatted Excel spreadsheets into relational tables prepared for SQL workflows. Its cloud API accepts Excel .xlsx files up to 100MB and can produce SQLite, Parquet, or CSV output. The provider says its LLM-powered engine interprets spreadsheet structure, relationships, merged cells, complex layouts, and visual formatting. Each output value includes a reference to its source cell, allowing values to be traced back to the spreadsheet. Listed use cases include preparing data for RAG pipelines, supporting AI agents that process business spreadsheets, SaaS spreadsheet ingestion, and enterprise internal tools. Developers can use TypeScript, Python, or Go libraries, as well as a CLI; API and Linux are the listed platforms. DeepTable is provided by Totoy GmbH, based in Vienna, Austria. It is in private beta, and the maker invites AI engineering teams to book a demo. The provider says user data is not used to train or fine-tune AI models. Users choose how long uploaded files and processing results are retained and can delete them at any time. Data is protected with encryption in transit and at rest. AI providers are restricted from training on user data and may retain it for up to 30 days for abuse monitoring and legal compliance. Pricing is available on request.
Good
- Accepts Excel .xlsx files up to 100MB.
- Outputs SQLite, Parquet, or CSV.
- Output values reference their source cells.
- Offers TypeScript, Python, and Go libraries plus a CLI.
Watch out
- Private beta; the maker invites teams to book a demo.
- Pricing is available on request.
- API input must be Excel .xlsx format.
- AI providers may retain data for up to 30 days.
Who it suits
DeepTable suits AI engineering teams and developers who need to turn Excel spreadsheets into structured data for SQL-oriented workflows. Its listed use cases include RAG pipelines, spreadsheet ingestion, and internal tools.
Verdict
DeepTable focuses on spreadsheet conversion, with structured outputs and source-cell traceability. Consider its private-beta status, Excel-only API input, and stated AI-provider retention when evaluating it.
The facts
Each one read from DeepTable's own pages, with the date it was checked.
What it does
- AI provider retention
- The privacy policy says AI providers are restricted from training on user data and may retain it for up to 30 days for abuse monitoring and legal compliance.checked 9 Oct 2026
- API input format
- The API reference says uploaded files must be Excel .xlsx files.checked 4 Oct 2026
- Cell traceability
- The site says every output value includes a reference to its source cell.checked 4 Oct 2026
- Data retention
- Uploaded spreadsheets and processing results are kept while the user chooses to keep them and can be deleted at any time.checked 9 Oct 2026
- Developer tools
- The maker provides Python, TypeScript, and Go libraries, plus a CLI.checked 9 Oct 2026
- Input limit
- The API accepts Excel (.xlsx) files up to 100MB.checked 9 Oct 2026
- Output formats
- Structured data can be downloaded as SQLite, Parquet, or CSV.checked 9 Oct 2026
- Parsing
- Its LLM-powered engine analyzes spreadsheet structure, relationships, and meaning, including merged cells, complex layouts, and visual formatting.checked 9 Oct 2026
- Privacy and AI training
- The privacy policy says DeepTable does not use uploaded spreadsheets, processing results, or other user data to train or fine-tune AI models.checked 4 Oct 2026
- Purpose
- DeepTable converts messy, human-formatted spreadsheets into clean, relational SQL-ready tables.checked 9 Oct 2026
- SDKs and CLI
- The API reference lists TypeScript, Python, and Go libraries plus a CLI tool.checked 4 Oct 2026
- Security
- The privacy policy says data is encrypted in transit and at rest, and uploaded user data is not used to train or fine-tune AI models.checked 9 Oct 2026
- Support and availability
- The maker says DeepTable is in private beta and invites AI engineering teams to book a demo; a support email is listed as [email protected].checked 9 Oct 2026
- Supported input
- The API documentation says uploaded files must be Excel (.xlsx) format.checked 9 Oct 2026
- Traceability
- The product says each output value includes a reference to its source cell.checked 9 Oct 2026
- Use cases
- The maker describes use for RAG pipelines, AI agents, SaaS spreadsheet ingestion, and enterprise internal tools.checked 9 Oct 2026
- What it does
- DeepTable converts messy, human-formatted spreadsheets into clean, relational SQL-ready tables.checked 4 Oct 2026
The company
- Company
- DeepTable is a service provided by Totoy GmbH, whose legal notice lists its address in Vienna, Austria.checked 9 Oct 2026
- Headquarters
- Vienna, Austriachecked 28 Sep 2026
Alternatives to DeepTable
- 1
Microsoft Planner
Free planAndroidiOSWebAPI7.9Free plan - 2
EasyMorph
Free planWebAPISelf-hostedWindows7.7From $600 a year - 3
DataCleaner
Free planOpen sourceAPILinuxmacOSSelf-hosted7.4Free plan - 4

AWS Glue DataBrew
WebAPI7.2 - 5
Microsoft Project
Free planWebAPIWindows7.2Free plan - 6
qsv
Free planWebLinuxmacOSWindows6.9From $99.99 a month