Regions & Endpoints

Configure regional base URLs, LLM availability by region, and dedicated cluster headers.

The Platform API is deployed across multiple regions to minimize latency and support data residency requirements. Each region operates independently with its own compute and AI routing.

Available Regions

Region	Location
US East	Virginia, USA
Asia Pacific	Sydney, Australia
Europe	Frankfurt, Germany
Canada	Montreal, Canada

Clients connect to the same base URL and are routed to the nearest region automatically. AI-backed services (enrichment, form auto-correction, OCR) route to the AI endpoint closest to the serving region, reducing round-trip latency for voice and enrichment workloads.

Amigo provides region-specific API endpoints to support data residency and latency requirements. If your organization is provisioned in a specific region, use the corresponding base URL. For organizations on dedicated clusters, you can also target your cluster explicitly via the x-mongo-cluster-name header.

Classic API endpoints. The regional endpoints below are for the Classic API at api.amigo.ai. The Platform API has its own regional endpoints, listed in Platform API Regional Endpoints below.

Regional Base URLs

Region	Location	Base URL
US	N. Virginia (us-east-1)	https://api.amigo.ai
CA	Montreal (ca-central-1)	https://api-ca-central-1.amigo.ai
EU	Frankfurt (eu-central-1)	https://api-eu-central-1.amigo.ai
AU	Sydney (ap-southeast-2)	https://api-ap-southeast-2.amigo.ai

Contact your Amigo representative for regional availability and upcoming regions.

Region matching required. Use the regional base URL that matches your organization's data residency. Requests to a mismatched region return "Organization not found" errors.

Platform API Regional Endpoints

The Platform API is available through regional endpoints that keep all traffic within the workspace's region. This includes Data-MCP queries, which execute entirely within the regional infrastructure.

Region	Platform API Base URL
US	https://api.platform.amigo.ai
CA	https://api-ca-central-1.platform.amigo.ai
EU	https://api-eu-central-1.platform.amigo.ai
AU	https://api-ap-southeast-2.platform.amigo.ai

The global endpoint (api.platform.amigo.ai) still works for all regions and routes to the correct regional infrastructure based on the workspace's configured region. Use regional endpoints when your compliance requirements mandate that API traffic stay within a specific jurisdiction.

LLM Regional Availability

Not all LLMs are deployed in every region. When selecting version set presets, make sure the preset's LLMs are available in your target region.

Tier	US	CA	EU	AU
Economy	✓	✓	✓	✓
Standard	✓	✓	✓	✓
Premium	✓	Partial	✓	Partial

Use forge channel llm-info to see the full model catalog, and forge channel validate-preset <preset> <channel> --region <region> to verify compatibility before deployment.

Premium model regional restriction.

Some premium-tier models are only available in US and EU regions. The following presets use these models and cannot be deployed to CA or AU:

• text_premium

• async

• async_premium

Use economy or standard presets for CA and AU regions.

Global Deployment Map

cURL example

curl -X GET \
  -H "Authorization: Bearer <YOUR_JWT_TOKEN>" \
  "https://api-ca-central-1.amigo.ai/v1/<your-org-id>/organization/"

SDK configuration

Specify the regional base URL via the SDK base_url or baseUrl setting.

Python

from amigo_sdk import AmigoClient

with AmigoClient(
    api_key="<key>",
    api_key_id="<key-id>",
    user_id="<user>",
    organization_id="<org>",
    base_url="https://api-ca-central-1.amigo.ai",
) as client:
    org = client.organization.get()

TypeScript

Environment variables

You can also set the regional endpoint via environment variables.

# US
AMIGO_BASE_URL=https://api.amigo.ai

# CA
# AMIGO_BASE_URL=https://api-ca-central-1.amigo.ai

# EU
# AMIGO_BASE_URL=https://api-eu-central-1.amigo.ai

# AU
# AMIGO_BASE_URL=https://api-ap-southeast-2.amigo.ai

Dedicated Clusters

Some enterprises run on dedicated, isolated clusters. In these cases, include x-mongo-cluster-name to direct requests to your assigned cluster.

Cluster name. Your Amigo team provides the exact cluster name if your tenant uses a dedicated cluster. Do not guess this value.

Header: x-mongo-cluster-name: <cluster-name>

When to use:

• Required: organization provisioning (Create Organization)

• Recommended: early provisioning flows when the organization may not yet be discoverable via the global config

• Optional: normal operations for established organizations. Most endpoints do not require it once your org is fully set up.

cURL example (dedicated cluster)

curl -X PUT \
  -H "Authorization: Bearer <YOUR_JWT_TOKEN>" \
  -H "x-mongo-cluster-name: <your-dedicated-cluster-name>" \
  -H "Content-Type: application/json" \
  "https://api-eu-central-1.amigo.ai/v1/<your-org-id>/organization/" \
  -d '{
    "org_name": "Example Corp",
    "title": "Example Corp AI",
    "main_description": "Intelligent assistants for Example Corp",
    "sub_description": "Personalized, compliant AI",
    "user_dimensions": [],
    "logo": "<base64>",
    "square_logo": "<base64>",
    "favicon": "<base64>",
    "signup_page_headshot": "<base64>",
    "default_user_preferences": {},
    "onboarding_instructions": ["Welcome to Example Corp AI"],
    "azure_devops_team_name": "example-team"
  }'

SDK examples (dedicated cluster)

Python

# If your SDK version exposes a raw HTTP method, include the header
# for organization provisioning requests. Otherwise, use cURL as shown above.

TypeScript

Recommendations

Best practices

1. Confirm your organization's region with your Amigo representative and set the matching base URL.

2. For dedicated cluster tenants, store your cluster name in a secure configuration store.

3. Include the x-mongo-cluster-name header where instructed for dedicated clusters.

Troubleshooting "Organization not found"

If you see this error:

• Verify you are calling the correct regional base URL.

• For provisioning flows, make sure the x-mongo-cluster-name header is set (if you are on a dedicated cluster).