AWS shows how to point the ChatGPT desktop app and Codex at Amazon Bedrock in AWS GovCloud (US), billed per token with no seat licenses
OpenAI's clients and model hosting are coming apart: the front end stays ChatGPT and Codex, while inference and billing run through the customer's own AWS account.
// Key points
- The ChatGPT desktop app, including Work for multi-step tasks and the Codex coding agent, can send inference to Bedrock in AWS GovCloud (US) through the Responses API; the sample configures us-gov-west-1 via the Bedrock Mantle endpoint.
- Two authentication paths: a Bedrock API key in AWS_BEARER_TOKEN_BEDROCK, which takes precedence over profiles, or the AWS SDK credential chain including IAM Identity Center; the same setup covers the Codex CLI and the VS Code, JetBrains and Xcode integrations.
- Pricing is pay-per-token with no seat licenses or per-developer commitments, and a zero data retention mode can be configured.
- The sample requirements.toml baseline turns off browser and computer use, memories, plugins, hooks, MCP servers and telemetry; the post notes that support for the endpoint, release and model must be confirmed with OpenAI, and changing the URL alone does not establish support.
Builder's takeThe same day AWS added the Responses, Converse and Chat Completions APIs plus cross-Region inference for OpenAI models in GovCloud, so the split between client and hosting is clear. For enterprise teams I care more about the requirements.toml: turn plugins, hooks and MCP off and enable them as needed, the same idea as Claude Code managed settings. Today's poisoned extension shows why off-by-default is right.
// Background · from #OpenAI
Full timeline →- Nov 1 OpenAI releases GPT-6 Rosalind for life sciences research, open only to approved organizations, at $15 input and $75 output per million tokens
- Nov 1 OpenAI publishes a community safety report and new protections for teens, strengthening violence prevention in ChatGPT
- Oct 31 OpenAI says it will honor a shared robots.txt signal that lets websites state their AI training preferences once