AI & Models · Integration
OpenAI
Add OpenAI to your product for your customers, and give your AI agents governed access to it.
Embed an OpenAI integration so each of your customers can bring their own OpenAI account instead of drawing down a single key you own and pay for. The connector covers the calls a product actually makes: model listing, chat completions, embeddings, image generation and file upload for the features that need it. Each customer supplies their own API key and organisation, so usage bills to them, their rate limits apply to them alone, and one customer's traffic cannot exhaust another's allowance. Keys are stored encrypted per tenant and every call is logged, which is what makes an in-product AI feature reviewable after the fact. fastn owns the credential handling, retries, rate limits and API upkeep, and the same governed connection is what your AI agents use.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers connect their own OpenAI account so the AI features in your product run on their key, their models and their spend.
Generate embeddings for a customer's own content so search and similarity features work per tenant without a shared index.
List the models a customer's account can actually reach so your product offers the right options rather than a hard-coded list.
Keep per-customer keys, organisations and usage isolated so one tenant's traffic never draws down another's rate limit.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent calls a completion on the customer's own OpenAI account within the limits you set, with every call logged.
An agent creates embeddings for newly added content so later questions are answered from that tenant's own material.
An agent reports how much a customer's connected OpenAI account has been used by your product over a period.
Example prompt
Summarise these support threads using our own OpenAI account and tell me how many tokens it took.
Set up OpenAI in 4 steps
- 01Enable the OpenAI connector in your fastn dashboard.
- 02Have each customer supply their own OpenAI API key so calls run under their account and allowance.
- 03Configure the models, prompts and request options your product uses, per customer.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the OpenAI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an OpenAI integration without building it. Your customers connect their own OpenAI 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 an OpenAI update is not your on-call problem.
- One integration serves your product and your agents. The same governed OpenAI 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
Azure OpenAI
Hugging FaceOften used alongside
Tools the same teams tend to run next to OpenAI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeOpenAI integration FAQ
How do I add an OpenAI integration to my product?
Enable the OpenAI connector in your fastn dashboard, then let each customer authenticate their own OpenAI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no OpenAI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own OpenAI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own OpenAI 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 OpenAI 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 calls a completion on the customer's own OpenAI account within the limits you set, with every call logged.
Who maintains the OpenAI integration?
fastn does. When OpenAI 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 OpenAI API key and quota does each call use?
Each customer authorises their own OpenAI 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 OpenAI integration?
A common starting point: connect their own OpenAI account so the AI features in your product run on their key, their models and their spend. 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 OpenAI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding OpenAI does not change your per-connector cost. You can start free with 3 connected accounts.
Add OpenAI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.