FAQs
Common questions about the Task API
Platform
Create a project in the Platform and copy the key from Settings > API Keys.
Go to Platform > Usage for real-time request counts, spend, and task-level detail.
Owners can invite users under Settings > Team. Choose “Viewer” or “Editor” roles.
Subject to our Terms of Service - you own the output you create with Parallel, including the right to reprint, sell, and merchandise.
API
Yes — Task Run Results from one execution can map to Task Run Input fields in another execution. For example, in one Task Run, you can identify the address of a business using a simple processor. Then, in the next Task Run you identify additional details about the business, given business name and address.
In each Task Output object, there is a description field where you can add instructions to limit a query to a set of sources.
Parallel is focused on reasoning and retrieval over the public web. For now, we only access what can be reached on the public web without authentication (e.g. signing in with credentials).
Our strength is reasoning and retrieval over text. We can recognize some on‑page images (e.g. detect customer logos), but we don’t accept images as inputs or return them as outputs yet.
Yes — we have a generous rate limit of 2000 requests (POST or GET) per minute. Our API is built for high‑volume, parallel execution - even on self‑serve plans.
Our web research is up to date to the current day. We are able to access live web links at the time of your query to ensure data is as real time as possible.
Parallel focuses on public web information. You can pass private data into a task as an input variable or post‑process the output on your side, but we don’t pull it natively. In the future we plan on building tools that will allow you to more easily point Parallel to your own sources.
Billing & Payments
Pay only for what you run. Each processor has a fixed price per 1,000 task runs (see Platform->Pricing for more details). You always know the exact cost before you call the API.
Example: If you run 10,000 basic research tasks, it will cost $5 per 1,000 tasks = $50 total. There are no token, data-volume, compute fees, or platform fees.
Yes. Pre-load your account with credit and then consume against that balance. We highly recommend you enable auto‑reload to avoid interruptions. If your balance hits $0 you’ll receive error P001: Insufficient Balance.
We do. Contact us at partnerships@parallel.ai for committed‑use or enterprise tiers.
Security & Compliance
Yes. Parallel is SOC-II Type 1 and Type II certified as of April 2025. Email us at partnerships@parallel.ai to request access to our full report in Trust Center.
All data is encrypted in transit (TLS 1.2+) and at rest in US-based data centers.
No. Parallel focuses on public web information. You can pass private data into a task as an input variable or post‑process the output on your side, but we don’t pull it natively. In the future we plan on building tools that will allow you to more easily point Parallel to your own sources.
Private‑cloud and on‑prem options are available for qualified enterprise customers—ask our team at partnerships@parallel.ai.
Never. Inputs and outputs remain yours. We do not use customer data to train any models. See our Terms of Service for details.