Your model, your key, your bill — visible
A model provider in DataLens is a connection like a database: it has credentials, an environment and a status. Flow AI steps hold one by id, so switching provider is a connection change rather than an edit to every node.
How it works
Bring your own credentials
Your key, your account, your relationship with the provider. The platform is not reselling you tokens.
A connection, not a setting
Credentials are tested, stored once and referenced by id — so a rotation touches one place.
Every call accounted for
Cost, tokens, latency, cache hits and failures per step, with the platform’s pre-run estimate alongside the actual.
Environment-aware
A release promoted to another environment binds to that environment’s provider connection rather than carrying a key with it.
What happens after it lands
Once rows are in the catalogue, the connector that produced them stops mattering. The dataset is profiled, can be cleaned, modelled, put in a flow, governed and published exactly like every other dataset — which means switching how data arrives never means rebuilding what happens to it afterwards.
Questions about this connector
Which providers can I connect?
The connection holds a provider, an endpoint and a credential, so major hosted providers and compatible endpoints are configured the same way.
Who pays for the AI calls?
You do, directly to your provider, using your own key. DataLens reports what each step cost so the bill is not a surprise.
Can I see what a flow will cost before running it?
The platform estimates before the run and records the actual afterwards, and the AI Operations surface reports where the two diverge.
Other ways in
CSV & Excel upload
Drag a file in and start working. Profiled on arrival, no schema declared up front.
Database
Read from your existing relational database and pull tables in as datasets.
REST API
Point at an endpoint, map the response shape, and land it as rows.
FTP & SFTP
Collect the drops that still arrive as files on a server.
CDC sync
Change data capture, so the dataset follows the source instead of ageing.
CRM
Bring customer records across without exporting them to a spreadsheet first.
Data lake
Read from — and write back to — object storage you already own.
Documents
PDFs and documents stored whole, for retrieval and generation rather than rows.
See it on your own data
DataLens is in private beta. Bring a file, a database or an API and work through the whole lifecycle in one sitting.
Request beta access