AI & Models · Integration
Nanonets
Add Nanonets to your product for your customers, and give your AI agents governed access to it.
Embed a Nanonets integration so your product can turn the documents its customers send it into structured data without you training and hosting extraction models. Nanonets accepts PDFs, images and Office files and returns extracted fields, tables and text as JSON, so an invoice, receipt or form becomes records your product can act on. Nanonets processes documents rather than storing your customers' document libraries, so the connector is about calls and results: fastn handles per-tenant credentials, retries, polling for asynchronous results and usage attribution, so extraction bills and audits to the right customer.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers connect their own Nanonets account so extraction runs under their credentials and their usage.
Submit a document from your product and receive extracted fields and tables as structured JSON.
Route low-confidence results to a human review step in your product instead of accepting a bad value.
Handle asynchronous processing and retries for you, so a slow document does not block your request path.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent extracts the fields it needs from a document before it continues a workflow.
An agent reads confidence scores and asks a human when a value is uncertain.
An agent submits a batch of documents within governed permissions, with each call attributed per tenant.
Example prompt
Extract the supplier, invoice number, date and line items from this invoice and flag any field below 80 percent confidence.
Set up Nanonets in 4 steps
- 01Open the Nanonets connector from your fastn dashboard.
- 02Connect each customer's own Nanonets credentials, stored encrypted per tenant.
- 03Choose the extraction models and output fields your product uses, then enable the actions you need.
- 04Call them from your product, or expose them to an agent through the MCP server.
Why teams use the Nanonets integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Nanonets integration without building it. Your customers connect their own Nanonets account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Nanonets update is not your on-call problem.
- One integration serves your product and your agents. The same governed Nanonets connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
Klippa DocHorizon
Google Document AI
Azure AI Document IntelligenceOften used alongside
Tools the same teams tend to run next to Nanonets, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeNanonets integration FAQ
How do I add a Nanonets integration to my product?
Enable the Nanonets connector in your fastn dashboard, then let each customer authenticate their own Nanonets account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Nanonets client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Nanonets account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Nanonets account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Nanonets integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent extracts the fields it needs from a document before it continues a workflow.
Who maintains the Nanonets integration?
fastn does. When Nanonets changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose Nanonets API key and quota does each call use?
Each customer authorises their own Nanonets account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Nanonets integration?
A common starting point: connect their own Nanonets account so extraction runs under their credentials and their usage. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Nanonets integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Nanonets does not change your per-connector cost. You can start free with 3 connected accounts.
Add Nanonets to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.