Use Codex with Amazon Bedrock

Configure Codex to use OpenAI models available through Amazon Bedrock. In this setup, Codex runs locally and sends model requests to Bedrock using AWS-managed authentication and access controls.

How it works

When you configure Codex with Amazon Bedrock as the model provider, the OpenAI-hosted Responses API isn’t in the request path. Codex sends model requests to Amazon Bedrock, and Bedrock provides an OpenAI-compatible Responses API implementation for supported OpenAI models.

Before you start

Make sure you have:

• Access to supported OpenAI models in Amazon Bedrock.
• An AWS Region where the selected model is available.
• Authentication for the Amazon Bedrock Mantle path configured for the AWS account.

Configure Codex

Add the amazon-bedrock model provider for the Amazon Bedrock Mantle path to ~/.codex/config.toml. Supplying a model is optional. Select a supported model explicitly when needed.

model_provider = "amazon-bedrock"

Authentication options

Codex supports two Bedrock authentication paths. It checks them in this order:

1. Bedrock API key.
2. AWS SDK credential chain.

Option 1: Bedrock API key

Set the Bedrock API key in the environment Codex reads. You must specify a Region when using API-key authentication.

export AWS_BEARER_TOKEN_BEDROCK=<your-bedrock-api-key>
export AWS_REGION=us-east-2

Option 2: AWS SDK credentials

Use this path when your organization manages Bedrock access through the AWS SDK credential chain. Codex can use these standard AWS SDK credential sources:

1. Shared AWS config and credentials files.

   aws configure

2. Environment variables.

   export AWS_ACCESS_KEY_ID=<your-access-key-id>
   export AWS_SECRET_ACCESS_KEY=<your-secret-access-key>
   export AWS_SESSION_TOKEN=<your-session-token>

3. AWS Management Console credentials.

   aws login

4. AWS SSO or a named profile.

   aws sso login --profile codex-bedrock
   export AWS_PROFILE=codex-bedrock

5. Federated identity configured with credential_process. For corporate SSO or OIDC federation, configure the AWS profile outside Codex and let the AWS SDK resolve credentials. Put browser login, token exchange, caching, and refresh in your AWS profile’s credential_process helper.

Desktop app and VS Code extension

Desktop apps and IDE extensions may not inherit environment variables from the shell. Put required values in ~/.codex/.env, then restart the app or extension.

export AWS_BEARER_TOKEN_BEDROCK=<your-bedrock-api-key>
export AWS_REGION=us-east-2

Verify setup

• In Codex CLI, open /status and confirm Codex is using the amazon-bedrock model provider.
• In the desktop app or VS Code extension, start a new session after restarting the app.
• Confirm the selected model is available in the configured AWS Region and that the AWS identity has permission to access it.

Supported models

Use exact model IDs:

openai.gpt-5.5
openai.gpt-5.4

Model availability varies by AWS Region. Before selecting a model, see model support by AWS Region.

Feature availability

This configuration supports local Codex workflows. Some features that depend on OpenAI-hosted cloud services, hosted tools, or cloud-managed discovery aren’t currently available.

Troubleshooting

If setup fails, check the following:

• The model ID exactly matches a supported model.
• You specify an AWS Region where the model is available.
• The Bedrock API key or AWS credentials are valid and not expired.
• The AWS identity has permission to access the selected Bedrock model.
• AWS_BEARER_TOKEN_BEDROCK isn’t set to an expired or unintended key.
• For desktop app or VS Code extension usage, required environment variables are present in ~/.codex/.env.

Support boundaries

OpenAI Support can help with Codex client setup, configuration, local CLI behavior, desktop app behavior, IDE extension behavior, and the local Codex product experience.

For AWS credentials, IAM permissions, Bedrock model access, quotas, billing, regional availability, Bedrock request failures, AWS service logs, or Bedrock service behavior, contact the customer’s AWS administrator or AWS Support.