Access OpenAI GPT models on Amazon Bedrock from Canada with cross-Region inference
Amazon Bedrock now enables Canadian customers to invoke OpenAI GPT‑5.6, GPT‑6, and GPT‑6.1 models from Canada (Central) and Canada West (Calgary) via cross‑Region inference, routing requests to US regions while preserving North‑America data residency. The models (e.g., GPT‑6.1 Sol, GPT‑6 Astra, GPT‑5.6 Luna) support text + image inputs, a 1‑million‑token context window, reasoning mode, tool calling, and prompt caching. Engineers can call these models through the OpenAI Responses API, Chat Completions API, or Amazon Bedrock Converse API on the `bedrock-runtime` endpoint without managing destination routing. This expands capacity and helps sustain throughput during demand spikes for production generative‑AI workloads.
⚡ Key Takeaways
- Models available: GPT‑6.1 Sol, GPT‑6 Astra, GPT‑6 Sol, GPT‑6 Luna, GPT‑5.6 Sol, GPT‑5.6 Terra, GPT‑5.6 Luna.
- Inference profiles: `us.*` (US geographic) and `global.*` logical identifiers replace raw model IDs.
- Prompt caching is supported for GPT‑5.6, GPT‑6, and GPT‑6.1 on Bedrock.
- Calls are made to the `bedrock-runtime` endpoint using OpenAI Responses API, Chat Completions API, or Bedrock Converse API.
- Data residency: processing occurs in North America; cross‑Region routing is handled by Bedrock, not the application.
Engineers can now leverage the latest OpenAI foundation models from Canadian regions without redesigning their routing logic, gaining access to larger capacity pools and maintaining compliance with North‑American data‑residency requirements.
✅ Practical Steps
- Configure your IAM permissions to allow `bedrock-runtime:InvokeModel` in the Canadian source Region.
- Invoke a model by calling the OpenAI Responses API, Chat Completions API, or Bedrock Converse API on the `bedrock-runtime` endpoint, specifying the appropriate inference profile (e.g., `us.gpt-6.1-sol`).
- Request a quota increase via the AWS console if you anticipate demand spikes, then monitor observability signals in your source Region.
Want the full story? Read the original article.
Read on AWS ML Blog ↗