Create Integration

POST /integrations

Python

Default

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",
)

# Add a new integration
integration = portkey.integrations.create(
    name="openai-production",
    ai_provider_id="openai",
    key="sk-..."
)

print(integration)

200

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "slug": "<string>"
}

Authorizations

x-portkey-api-key · string · header · required

Body

application/json

name · string · required

Human-readable name for the integration

Example:

"Production OpenAI"

ai_provider_id · string · required

ID of the base AI provider

Example:

"openai"

slug · string

URL-friendly identifier (auto-generated if not provided)

Pattern: ^[a-zA-Z0-9_-]+$

Example:

"production-openai"

key · string

API key for the provider (if required)

Example:

"sk-..."

description · string

Optional description of the integration

Example:

"Production OpenAI integration for customer-facing applications"

workspace_id · string

Workspace ID (for workspace-scoped integrations)

Example:

"ws-my-team-1234"

configurations · OpenAI · object

Provider-specific configuration object

OpenAI

Azure OpenAI

AWS Bedrock

Vertex AI

Azure AI

Workers AI

AWS Sagemaker

Hugginface

Cortex

Custom Base URL

Show child attributes

create_default_provider · boolean · default: true

Whether to automatically create a default provider when creating a workspace-scoped integration. Defaults to true.

default_provider_slug · string

Custom slug for the auto-created default provider. Only applicable for workspace-scoped integrations. If the slug already exists in the workspace, the request will fail with a validation error.

Maximum string length: 255

Pattern: ^[a-zA-Z0-9_-]+$

Response

200 - application/json

Successful response

id · string<UUID>

slug · string