AI & Models · Integration
BigML
Add BigML to your product for your customers, and give your AI agents governed access to it.
BigML's API is versioned by release name in the path, so calls go to bigml.io/andromeda/source and similar, and credentials are supplied as username and api_key query parameters rather than a header. Everything is a resource with a typed id such as source/5f..., dataset/..., model/..., ensemble/... and prediction/..., and the pipeline is strictly ordered: a source becomes a dataset, a dataset trains a model, and a model produces predictions or a batchprediction. Resource creation is asynchronous and each resource carries a status object with a numeric code, so a client must poll until the code reaches FINISHED before using the resource, and treating an HTTP 201 as completion is the classic mistake. Resources default to private and have to be shared explicitly, and there is a separate production versus development distinction on some accounts that affects billing. Batch predictions write their output as a new dataset or downloadable file rather than returning rows inline. fastn stores each customer's username and key, handles the asynchronous polling and keeps the connection maintained.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own BigML account so models train under their credentials and their data stays theirs
Create a source and dataset from a customer's exported records and kick off training from your UI
Score new records against a customer's chosen model and store the prediction with your own entity
Run a batch prediction over a dataset and surface the resulting output file to the customer
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Ask an agent which of a tenant's models finished training and what their evaluation scores are
Have an agent score a single record against a named model and explain the fields that drove it
Let an agent start a batch prediction job, with the run audited per tenant against that tenant's own key
Example prompt
Which of my BigML models has the best evaluation score for churn, and what does it predict for this customer?
Set up BigML in 4 steps
- 01Enable the BigML connector from your fastn dashboard.
- 02Have each customer authorise their own BigML 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 BigML integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a BigML integration without building it. Your customers connect their own BigML 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 BigML update is not your on-call problem.
- One integration serves your product and your agents. The same governed BigML 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
Anthropic Claude
OpenAI
Azure OpenAIOften used alongside
Tools the same teams tend to run next to BigML, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeBigML integration FAQ
How do I add a BigML integration to my product?
Enable the BigML connector in your fastn dashboard, then let each customer authenticate their own BigML account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no BigML client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own BigML account?
Yes. Every connection is scoped to the individual customer, so each authorises their own BigML 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 BigML integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Ask an agent which of a tenant's models finished training and what their evaluation scores are
Who maintains the BigML integration?
fastn does. When BigML 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 BigML API key and quota does each call use?
Each customer authorises their own BigML 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 BigML integration?
A common starting point: let a customer connect their own BigML account so models train under their credentials and their data stays theirs. 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 BigML integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding BigML does not change your per-connector cost. You can start free with 3 connected accounts.
Add BigML to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.