AI & Models · Integration
DeepL
Add DeepL to your product for your customers, and give your AI agents governed access to it.
Embed a DeepL integration so your customers can translate text and documents from inside your product using their own DeepL account and their own glossaries, rather than a shared key you have to meter yourself. Requests are made per tenant so usage is attributable to the customer that caused it, and every call is logged. fastn handles each customer's credentials and API upkeep, so adding a customer is configuration rather than a release.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers translate content inside your product using their own DeepL account and language pairs.
Submit documents for translation and read the translated result back into your product.
Apply each customer's own glossary so their product and brand terms translate consistently.
Trigger the next step in your product when a document translation finishes.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent translates a customer message before drafting a reply in the right language.
An agent submits a document for translation within governed permissions, with the action audited.
An agent reacts to a completed translation and files the result where your workflow expects it.
Example prompt
Translate this support reply into German using the customer's glossary and show me the original alongside it.
Set up DeepL in 4 steps
- 01Open the DeepL connector from your fastn dashboard.
- 02Have each customer authenticate their DeepL account with their own API key.
- 03Map the language pairs and glossaries your product uses, then enable actions and triggers.
- 04Call them from your product, or expose them to an agent through the MCP server.
Why teams use the DeepL integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a DeepL integration without building it. Your customers connect their own DeepL 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 DeepL update is not your on-call problem.
- One integration serves your product and your agents. The same governed DeepL 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
DocparserWorks well with
Notion
ConfluenceOften used alongside
Tools the same teams tend to run next to DeepL, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeDeepL integration FAQ
How do I add a DeepL integration to my product?
Enable the DeepL connector in your fastn dashboard, then let each customer authenticate their own DeepL account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no DeepL client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own DeepL account?
Yes. Every connection is scoped to the individual customer, so each authorises their own DeepL 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 DeepL 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 translates a customer message before drafting a reply in the right language.
Who maintains the DeepL integration?
fastn does. When DeepL 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 DeepL API key and quota does each call use?
Each customer authorises their own DeepL 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 DeepL integration?
A common starting point: translate content inside your product using their own DeepL account and language pairs. 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 DeepL integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding DeepL does not change your per-connector cost. You can start free with 3 connected accounts.
Add DeepL to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.