Configure the ChatGPT desktop app with Amazon Bedrock in AWS GovCloud (US)
The ChatGPT desktop app is now available on Amazon Bedrock in AWS GovCloud (US). This post walks through a controlled local deployment that routes model inference to Amazon Bedrock in AWS GovCloud (US-West) using API-mode sign-in, a managed device policy, a named AWS profile, and network restrictions, so a security team can validate it before broader use.
First seen by Oriel on .
AI summary
The walkthrough configures the ChatGPT desktop app and Codex to route model inference through Amazon Bedrock in AWS GovCloud (US), with administrator-managed policies and restricted network access.
- The setup uses the Responses API at the Amazon Bedrock Mantle endpoint in us-gov-west-1, authenticated through a Bedrock API key or the AWS SDK credential chain, including AWS SSO.
- Administrators set enforced controls in requirements.toml, while config.toml selects the approved model, AWS profile, provider, and app behavior; both files must exist before launch.
- The example policy allows only the approved Bedrock endpoint, disables other external connections and many network-enabled features, and uses API-mode sign-in.
- The guide covers verifying the provider, troubleshooting identity and policy issues, and rolling back failed tests; AWS GovCloud use does not itself authorize a workload.
- The article describes regional processing, per-token pricing without seat licenses, and support for zero data retention, while leaving organizations responsible for their own security and authorization reviews.
#amazon bedrock #aws govcloud #codex #identity and access management
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 698175f4da06f51671986617198b154f2e828670 | https://aws.amazon.com/blogs/machine-learning/configure-the-chatgpt-desktop-app-with-amazon-bedrock-in-aws-govcloud-us/ Read discussion |