Amazon Bedrock adds cross‑Region inference for OpenAI GPT models in Canada
Amazon Bedrock now lets Canadian developers call the latest OpenAI foundation models – GPT‑5.6 (Sol, Terra, Luna), GPT‑6 (Astra, Sol, Luna) and GPT‑6.1 Sol – through cross‑Region inference (CRIS). The models accept text and image inputs, support a 1‑million‑token context window, reasoning mode, tool calling and prompt caching, and are reachable from the Canada (Central) and Canada West (Calgary)…
Key points
- Amazon Bedrock routes OpenAI GPT‑5.6, GPT‑6 and GPT‑6.1 calls from Canada via cross‑Region inference.
- Models support text and image inputs, a 1‑million‑token context window, tool calling and prompt caching.
- Two inference profile types (us. and global.) let users choose North‑America‑only or broader capacity pools.
CRIS works by routing a request from a source Canadian region to a destination region in North America. Two profile types are offered: a US‑geographic profile (prefixed us.) that keeps inference within Canada and the United States, and a global profile (prefixed global.) that can draw on any commercial AWS region where the model is deployed. Quotas are measured in tokens per minute per model, with separate allocations for each profile type, and users can request increases via the Service Quotas console. All traffic travels over AWS’s private backbone encrypted with TLS 1.2+, and data at rest stays in the source region, with only transient computation occurring in the destination region.
Model page: GPT-6 →
The story so far
2 episodes →- Amazon Bedrock adds cross‑Region inference for OpenAI GPT models in Canadathis story
Access OpenAI GPT models on Amazon Bedrock from Canada with cross-Region inference
AWS Machine Learning Blog · 20 October 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Roopesh Ramklass. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Smartsheet launches MCP Server for AI agents to manage work data on AWS · 1 src
- Octave Reliance builds secure multi-tenant AI foundation on Amazon Bedrock · 1 src
- BriefCatch expands into unified legal writing suite with verification tools · 1 src
- OpenAI’s health AI aims to cut medical guideline lag from 17 years to hours · 1 src
- Perplexity publishes guide on AI gateway mechanics and limits · 1 src
Comments
via GitHub Discussions