AI & Models · Integration
Perplexity
Add Perplexity to your product for your customers, and give your AI agents governed access to it.
Embed a Perplexity integration so your product can ask a question and get an answer grounded in current web sources with citations attached, without you maintaining another model client. Perplexity's API exposes chat completions against its Sonar models, and the useful part for a product is that answers come back with the sources they were drawn from, so a user can check them. fastn handles the credential per customer or per workspace, retries, timeouts and API upkeep, and the same governed connection serves in-product features and your agents so you are not wiring model access twice.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Add a research or answer feature to your product that returns citations alongside the answer rather than an unsourced paragraph.
Let each customer use their own Perplexity key so usage and cost sit with them rather than pooled in one account.
Choose the model per feature so a quick lookup and a deeper research call do not have to use the same one.
Keep prompts and calls server side behind fastn so no model credential is exposed in your client.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent looks up current information and cites its sources before it acts on the answer.
An agent checks a claim against live sources within governed permissions, with every call audited.
An agent gathers background on a company or topic and passes the cited result to the next workflow step.
Example prompt
Research this company's recent funding and product launches and give me the sources for each point.
Set up Perplexity in 4 steps
- 01Open the Perplexity connector from your fastn dashboard.
- 02Add your own Perplexity API key, or have each customer add theirs.
- 03Choose the models and default parameters 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 Perplexity integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Perplexity integration without building it. Your customers connect their own Perplexity 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 Perplexity update is not your on-call problem.
- One integration serves your product and your agents. The same governed Perplexity 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
CohereWorks well with
PineconeOften used alongside
Tools the same teams tend to run next to Perplexity, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudePerplexity integration FAQ
How do I add a Perplexity integration to my product?
Enable the Perplexity connector in your fastn dashboard, then let each customer authenticate their own Perplexity account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Perplexity client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Perplexity account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Perplexity 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 Perplexity 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 looks up current information and cites its sources before it acts on the answer.
Who maintains the Perplexity integration?
fastn does. When Perplexity 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 Perplexity API key and quota does each call use?
Each customer authorises their own Perplexity 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 Perplexity integration?
A common starting point: add a research or answer feature to your product that returns citations alongside the answer rather than an unsourced paragraph. 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 Perplexity integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Perplexity does not change your per-connector cost. You can start free with 3 connected accounts.
Add Perplexity to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.