AI & Models · Integration
Dumpling AI
Add Dumpling AI to your product for your customers, and give your AI agents governed access to it.
Dumpling AI exposes a flat set of task endpoints under app.dumplingai.com/api/v1 rather than a REST resource tree, with names that read as verbs such as get-youtube-transcript, search, scrape and doc-to-text, and every one of them is POST only, so a GET returns 405 rather than a helpful error. Authentication is a Bearer API key on the request, and there is no per-object addressing to speak of: you send input and receive the finished output in the same response, which means slow targets show up as long-running HTTP calls rather than as a job you poll. Billing is credit based per call and different endpoints cost different amounts, so cost control belongs in your calling code and not in a rate limiter. Because the responses are already parsed into structured fields rather than raw HTML, implementers often skip their own extraction layer and then discover they need the original when a site changes. fastn holds each customer's Dumpling AI key, keeps it out of your application, and handles the per-tenant rotation and upkeep.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Dumpling AI key so their credits, not yours, pay for the extraction work.
Pull a transcript for a video URL a user pastes in, and store it against their record.
Run a web search or page scrape as an enrichment step inside your own onboarding flow.
Convert an uploaded document to text before indexing it in your product's own search.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent fetch and summarise a page or transcript on demand, with each call charged and audited per tenant.
Have an agent run a bounded search for a named topic and return sources rather than conclusions.
Allow an agent to extract text from a customer-supplied document before it drafts anything from it.
Example prompt
Get me the transcript of this video and pull out the three pricing claims it makes.
Set up Dumpling AI in 4 steps
- 01Enable the Dumpling AI connector from your fastn dashboard.
- 02Have each customer authorise their own Dumpling AI account, so calls run under their credentials rather than a shared key.
- 03Decide which models, requests and outputs your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Dumpling AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Dumpling AI integration without building it. Your customers connect their own Dumpling AI 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 Dumpling AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Dumpling AI 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
Often used alongside
Tools the same teams tend to run next to Dumpling AI, across other categories.
Dumpling AI integration FAQ
How do I add a Dumpling AI integration to my product?
Enable the Dumpling AI connector in your fastn dashboard, then let each customer authenticate their own Dumpling AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Dumpling AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Dumpling AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Dumpling AI 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 Dumpling AI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Let an agent fetch and summarise a page or transcript on demand, with each call charged and audited per tenant.
Who maintains the Dumpling AI integration?
fastn does. When Dumpling AI 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 Dumpling AI API key and quota does each call use?
Each customer authorises their own Dumpling AI 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 Dumpling AI integration?
A common starting point: let a customer connect their own Dumpling AI key so their credits, not yours, pay for the extraction work. 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 Dumpling AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Dumpling AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Dumpling AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.