Access OpenAI GPT models on Amazon Bedrock from Canada with cross-Region inference
Canadian organizations can now access OpenAI GPT-5.6, GPT-6, and GPT-6.1 models on Amazon Bedrock from the Canada (Central) and Canada West (Calgary) Regions using cross-Region inference. This post covers the models and inference profiles, how to set up permissions, and how to invoke them with the Responses, Chat Completions, and Converse APIs.
First seen by Oriel on .
AI summary
Amazon Bedrock cross-Region inference makes OpenAI GPT-5.6, GPT-6, and GPT-6.1 models available from Canadian AWS Regions, with routing profiles that define where requests are processed.
- Canada (Central) and Canada West support US geographic profiles for the listed models; global GPT-5.6 profiles are available only from Canada (Central).
- US geographic profiles route within Canada and the US, while global profiles can use supported commercial AWS Regions for a broader capacity pool.
- The models support the OpenAI Responses API, Chat Completions API, and Amazon Bedrock Converse API, with text and image inputs, tool calling, and a 1-million-token context window.
- Implicit prompt caching applies automatically to eligible prefixes of at least 1,024 tokens; cached reads receive discounted billing and do not count against tokens-per-minute quota.
- Quotas combine input and output tokens per model, with output adjusted by model-specific burndown rates; US geographic and global profiles have separate allocations.
#amazon bedrock #cross-region inference #openai models #prompt caching
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 64795cdbf69a431d795a47585bec95352a07ed61 | https://aws.amazon.com/blogs/machine-learning/access-openai-gpt-models-on-amazon-bedrock-from-canada-with-cross-region-inference/ Read discussion |