AI & Models · Integration
Parallel
Add Parallel to your product for your customers, and give your AI agents governed access to it.
Parallel exposes a Task API and a Search API for web research, authenticated with an API key sent in a header rather than a bearer token. Task runs are asynchronous: you submit a task specification with an output JSON schema, get back a run id, and poll that run until it reaches a terminal state, which for deep processors can take minutes rather than seconds. The processor you choose trades cost and latency against how much of the web is read, so the same task specification behaves very differently depending on that one field. What surprises implementers is that results come back with a basis attached, giving per-field citations and reasoning, so storing only the flattened output throws away the evidence your customers will later ask for. fastn holds each customer's Parallel key, keeps the long-running polls off your own workers, and handles token upkeep so you are not rebuilding credential storage per tenant.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Parallel account so research runs are billed and rate-limited against their key, not yours
Enrich newly created CRM records by submitting a task with a fixed output schema and writing the returned fields back
Run scheduled market or competitor briefs and store the cited basis alongside each answer for review
Offer an in-app research box where end users describe what they need and the structured result populates a form
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent submit a research task with a schema you control and refuse free-form output that does not match it
Have an agent poll long-running runs and post a summary only once the run reaches a terminal state
Audit per tenant which prompts were submitted, which processor tier was used and what citations came back
Example prompt
Run a Parallel task to find the current pricing tiers for these five competitors and return them with sources.
Set up Parallel in 4 steps
- 01Enable the Parallel connector from your fastn dashboard.
- 02Have each customer authorise their own Parallel 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 Parallel integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Parallel integration without building it. Your customers connect their own Parallel 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 Parallel update is not your on-call problem.
- One integration serves your product and your agents. The same governed Parallel 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 Parallel, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeParallel integration FAQ
How do I add a Parallel integration to my product?
Enable the Parallel connector in your fastn dashboard, then let each customer authenticate their own Parallel account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Parallel client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Parallel account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Parallel 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 Parallel 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 submit a research task with a schema you control and refuse free-form output that does not match it
Who maintains the Parallel integration?
fastn does. When Parallel 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 Parallel API key and quota does each call use?
Each customer authorises their own Parallel 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 Parallel integration?
A common starting point: let a customer connect their own Parallel account so research runs are billed and rate-limited against their key, not yours. 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 Parallel integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Parallel does not change your per-connector cost. You can start free with 3 connected accounts.
Add Parallel to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.