Parallel AI API Reference — Overview & Authentication

The Parallel AI REST API gives you programmatic access to every resource in your Parallel account — agents, conversations, smart lists, sequences, documents, audio, and more. All endpoints are served from a single base URL, return JSON, and follow consistent pagination and error conventions.

Base URL

https://api.parallellabs.app

Every endpoint path begins with /api/v0/. For example, to list your agents you call:

GET https://api.parallellabs.app/api/v0/agents

Authentication

The API supports two authentication methods.

Company API Key

Include your Company API Key in the X-API-Key request header. This is the simplest method and is scoped to your company account.

X-API-Key: YOUR_API_KEY

Personal Access Key (pak_)

Personal Access Keys begin with pak_. Pass the key as a Bearer token in the Authorization header. If the key is associated with multiple companies, also include the X-Company-ID header to specify which company context to use.

Authorization: Bearer pak_YOUR_PERSONAL_ACCESS_KEY
X-Company-ID: company_abc123

Keep your API keys secret. Never expose them in client-side code or public repositories. Rotate them immediately if you suspect they have been compromised.

Response Format

All responses — including errors — are JSON. Successful responses return the requested resource or a confirmation message. The HTTP status code indicates whether the request succeeded.

Error Format

When a request fails, the response body contains a single error field describing what went wrong:

{
  "error": "Agent not found"
}

HTTP Status Codes

Status	Meaning
`200 OK`	The request succeeded and the response body contains the result.
`201 Created`	A new resource was created successfully.
`400 Bad Request`	The request body or query parameters were invalid. Check the `error` message for details.
`401 Unauthorized`	Missing or invalid API key. Verify your credentials.
`403 Forbidden`	Your plan or role does not have access to this feature or resource.
`404 Not Found`	The requested resource does not exist.
`429 Too Many Requests`	You have exceeded the rate limit. Wait before retrying.
`500 Internal Server Error`	An unexpected error occurred on the server.

Pagination

List endpoints accept page and pageSize query parameters and return a consistent envelope:

Parameter	Type	Default	Description
`page`	integer	`1`	The page number to retrieve.
`pageSize`	integer	`10`	Number of items per page. Maximum is `100`.

Paginated response envelope:

{
  "items": [ /* array of resource objects */ ],
  "total": 42,
  "pages": 5,
  "hasNext": true
}

Field	Type	Description
`items`	array	The list of resource objects for the current page.
`total`	integer	Total number of matching resources across all pages.
`pages`	integer	Total number of pages at the current `pageSize`.
`hasNext`	boolean	`true` if there is at least one more page after this one.

API Resources

Agents

Create and manage AI agents with custom prompts, channels, and branding.

Chat

Send messages to agents and retrieve conversation histories.

Smart Lists

Manage contact lists and the contacts within them.

Sequences

Build and trigger multi-step automated messaging sequences.

Documents

Upload and manage knowledge base documents for your agents.

Audio / Media

Transcribe audio and manage media assets.

Browser

Extract web content for use in agent knowledge bases.

Keys

Create and manage Company API Keys and Personal Access Keys.

MCP

Connect external tools and data sources via the Model Context Protocol.

​Base URL

​Authentication

​Company API Key

​Personal Access Key (pak_)

​Response Format

​Error Format

​HTTP Status Codes

​Pagination

​API Resources

Agents

Chat

Smart Lists

Sequences

Documents

Audio / Media

Browser

Keys

MCP

Base URL

Authentication

Company API Key

Personal Access Key (pak_)

Response Format

Error Format

HTTP Status Codes

Pagination

API Resources