Access OpenAI GPT models on Amazon Bedrock from Canada with cross-Region inference

This article explains how to access OpenAI GPT models from Canadian AWS regions using Amazon Bedrock's cross-Region inference (CRIS) capability.

• OpenAI GPT-5.6, GPT-6, and GPT-6.1 models available from Canada (Central) and Canada West (Calgary) regions
• Cross-Region inference routes requests to supported destination regions while maintaining data residency controls
• Two profile types available: US geographic profiles (Canada and US only) and global profiles (broader capacity pool)
• Access models via OpenAI Responses API, Chat Completions API, or Amazon Bedrock Converse API
• Models support text/image inputs, 1-million-token context window, reasoning mode, tool calling, and prompt caching
• Quotas measured in tokens per minute (TPM) per model; request increases via Service Quotas console
• Observability through CloudTrail, CloudWatch metrics, and model invocation logging in source region
• Data at rest stays in source region; only transient inference computation occurs in destination region

Canadian organizations can now build generative AI applications with latest OpenAI models while maintaining data residency and compliance requirements.