iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Amazon Bedrock is not another ChatGPT account in Codex’s account switcher. To use your personal ChatGPT-backed setup and Bedrock, switch Codex’s model-provider configuration: use ChatGPT authentication for the personal route, or configure Codex to send supported model requests through Bedrock with AWS credentials. Each route has separate authentication, billing, administration, and feature support.
What “switching” means in Codex
ChatGPT’s account switcher is for ChatGPT accounts. OpenAI says it supports up to two accounts in one session on ChatGPT web, but is not supported in Codex desktop or the native ChatGPT mobile apps. It does not add Bedrock to ChatGPT’s account menu. OpenAI’s account-switching guide explains that the accounts remain independent.
Codex can instead use Amazon Bedrock as its model provider. The client remains Codex, but the request path, credentials, billing, and service administration change. OpenAI describes Bedrock as a separately configured provider in its Codex and Amazon Bedrock overview.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →| What changes | Personal ChatGPT-backed Codex | Codex through Amazon Bedrock |
|---|---|---|
| Provider selection | ChatGPT-backed sign-in and configuration | Local Codex setting: model_provider = "amazon-bedrock" |
| Authentication | Personal ChatGPT authentication | Bedrock API key or AWS SDK credentials |
| Billing and administration | ChatGPT account and plan context | AWS account, billing, IAM permissions, model access, quotas, and Region |
| Feature availability | Depends on the applicable Codex configuration | Some OpenAI-hosted cloud features are unavailable; API support depends on model, endpoint, Region, and account configuration |
| Support responsibility | OpenAI for Codex client behavior | OpenAI for client setup; AWS or your administrator for credentials, access, quotas, billing, Regions, and Bedrock service behavior |
Configure Codex to use Amazon Bedrock
Before editing configuration, choose a model that your AWS account can use in the intended Region. Bedrock model availability and access requirements vary; check AWS’s model access documentation and the current OpenAI Bedrock configuration guide. Do not assume an example model ID is available in your account or Region.
#1 Best Overall
- High-Performance AI Processor：The MS-02 Ultra features an Intel Core Ultra 9 285HX (24C/24T, up to 5.5 GHz, 13 TOPS NPU), delivering fast and efficient performance for AI inference, algorithm development, and media workloads. A PCIe x16 expansion slot supports desktop-class GPU upgrades for advanced model training and accelerated computing tasks. It's ideal for creators, engineers, and teams handling intensive parallel workloads.
- 4 × M.2 PCIe 4.0 + 4 × DDR5 SODIMM slots:Four DDR5 SODIMM slots support up to 256 GB of memory, while ECC helps maintain data integrity in mission-critical environments. Four PCIe 4.0 M.2 slots support up to 24 TB of storage, supporting RAID 0/1/5/10, combining high-speed performance with data protection. It allows for the creation of independent scratch disks, media libraries, and project drives, providing high-throughput for production workflows.
- PCIe & USB 4.0 v2: Up to three PCIe slots can be equipped, including a dual-slot x16 GPU. The main slot supports PCIe 5.0, meeting the needs of high-bandwidth creative and computing workloads. USB 4.0 v2 (80Gbps) supports high-bandwidth external storage and displays.
- Ultra-fast Networking: Wi-Fi 7 further enhances wireless performance with next-generation speeds and low-latency stability. Intelligent bandwidth switching optimizes throughput in different network environments, ensuring optimal performance for enterprise or local networks. Dual 25GbE ports (providing up to approximately 3.125 GB/s bandwidth, about 25 times faster than traditional 1GbE), enabling seamless large-scale file transfers and parallel computing. 10GbE and 2.5GbE ports, with support for Intel vPro technology, ensure enterprise-grade remote management and deployment flexibility.
- Server-grade thermal architecture: Utilizing a dedicated CPU/GPU airflow design, equipped with a 6-pipe dual-fan cooler, it maintains stable performance even under sustained loads, delivering up to 140W Turbo power while maintaining a 100W TDP, and operating with noise levels as low as 36 dB. An integrated 350W power supply ensures stable and reliable output for demanding computing tasks and fully loaded extended configurations.
1. Choose an authentication method
- Bedrock API key: set
AWS_BEARER_TOKEN_BEDROCKto the supported Bedrock API key. When this variable is set, Codex checks it before falling back to SDK credentials. - AWS SDK credential chain: use an AWS identity available through shared AWS configuration, environment variables, AWS SSO, a named profile, or federated credentials. Do not use
OPENAI_API_KEYfor the Bedrock provider.
2. Set the provider, model, and Region
Edit ~/.codex/config.toml and configure the provider as amazon-bedrock. A minimal configuration needs a supported model ID and a Region; the exact TOML fields and format are in OpenAI’s configuration instructions. Their example uses model = "openai.gpt-5.6-sol", model_provider = "amazon-bedrock", and wire_api = "responses", but treat the model ID as an example, not a guarantee of availability. For API-key authentication, set the Bedrock Region in Codex configuration. With SDK credentials, set a Region explicitly or ensure the AWS SDK can resolve one through configuration, environment, or profile.
3. Make credentials visible to desktop or IDE Codex
Desktop and IDE applications may not inherit variables set in an interactive shell. If Codex cannot see the required variables, put them in ~/.codex/.env as described in OpenAI’s configuration guide. Protect that file as a secret, especially if it contains a Bedrock API key.
4. Restart and verify
- Save the configuration and any environment-file changes.
- Restart the Codex desktop app or VS Code extension so it reloads the settings.
- In the Codex CLI, run
/statusto verify the active configuration. In desktop or IDE Codex, start a new session after restarting and confirm that it is using the intended provider.
Switch back to your personal ChatGPT-backed setup
There is no OpenAI-documented account-switch button for changing Codex from Bedrock back to ChatGPT. Restore the personal ChatGPT-backed configuration by undoing the Bedrock-specific settings you added and then relaunching Codex. Back up ~/.codex/config.toml before editing so you can restore it if the app does not behave as expected.
An AWS-published tutorial by Matheus Guimaraes describes removing the Bedrock configuration block used in that tutorial and restarting Codex. The author reports that conversations and generated files remained visible during a macOS test; that is one person’s result, not a guarantee for every system, Codex version, or configuration. The tutorial also offers optional shell commands to automate switching. These are third-party scripts, not an OpenAI-supported account-switch feature; inspect any script and its changes before running it. Read the tutorial.
Rank #3
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
Troubleshoot a failed Bedrock request
- Check the provider and model ID. Confirm
model_provideris set toamazon-bedrock, the model ID is exact, and the request is being routed through Bedrock. - Check the Region. Ensure Codex or the AWS SDK resolves the intended Region and that the selected model and endpoint are available there.
- Check which credentials Codex sees.
AWS_BEARER_TOKEN_BEDROCKtakes precedence over the SDK credential chain. For desktop and IDE apps, check~/.codex/.envif shell variables are not inherited. - Check AWS authorization and access. Confirm the identity has the required permissions, the account can access the model, and quotas or prerequisites are not blocking the request. AWS notes that access arrangements differ by model; some require additional account-level steps or prerequisites. See AWS model access guidance.
- Check API capability. A capability described for an OpenAI-hosted API is not necessarily available through Bedrock. Support varies by model and endpoint; consult OpenAI’s OpenAI on Amazon Bedrock documentation.
- Restart after configuration edits. Restart the desktop app or IDE extension, then begin a new session.
Contact OpenAI for Codex client setup and local behavior. For AWS identity, IAM, model access, quotas, billing, regional availability, or Bedrock request and backend issues, contact your AWS administrator or AWS Support.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Understand the AWS-side implications
Bedrock requests are managed and billed through AWS, not through the ChatGPT plan. AWS owns the relevant account permissions, model-access settings, quotas, and regional availability. OpenAI’s Bedrock documentation describes the integration and directs users to AWS for service-side administration. Model and endpoint capabilities can differ from the OpenAI-hosted path, so confirm that the specific Codex workflow you need is supported before relying on it.
Quick Recap
Best Value
- 【High-Performance APU】The MS-S1 MAX features an AMD Ryzen AI Max+ 395 APU, integrating a Zen 5 architecture CPU (up to 5.1GHz, 16C/32T, 64M L3 Cache), an RDNA 3.5 GPU, and an NPU (50 TOPS). The total system output is 126 TOPS. It provides powerful parallel computing capabilities for demanding AI workflows. It is ideal for running local LLMs, multimodal models, and computationally intensive tasks
- 【128GB UMA Memory】Equipped with up to 128GB of LPDDR5x-8000MT/s unified memory, it enables the CPU and GPU to access a shared, high-bandwidth memory pool with extremely low latency. Ideal for large-scale AI inference, 3D workloads, and complex timelines in video editing. It eliminates traditional VRAM bottlenecks, ensuring smoother data transfer during high-intensity computations. The UMA design maximizes performance stability under high loads
- 【Flexible Expansion】The MS-S1 MAX features USB4 V2 (up to 80Gbps), dual 10GbE LAN, HDMI 2.1 (up to 8K60), a full-length PCIe x16 expansion slot, and dual M.2 slots supporting up to 16TB RAID 0/1. Wi-Fi 7 provides stronger signal coverage and a more stable wireless experience. The slide-out design facilitates upgrades and maintenance. It easily adapts to personal, studio, or rack-mount enterprise environments
- 【High-Efficiency Cooling System】Utilizing an aerospace-grade aluminum alloy chassis, copper base plate, six heat pipes, dual turbine fans, and advanced PCM thermal conductive material, it maintains stable cooling performance even under continuous load. This system supports 130W continuous power and 160W peak power operation, with a built-in 320W power supply. It boasts multiple global certifications including CCC, FCC, UL, CE, and UKCA, ensuring stable and reliable operation in various environments
- 【Cluster Design】Two MS-S1 MAX units can be configured as a dual-unit cluster to run a large 235B Q4 model locally, achieving an output speed of 10.87 tok/s. Supporting 2U rack deployment, multiple MS-S1 MAX units can be cascaded into a distributed cluster to create a high-efficiency AI computing center. A cluster of four MS-S1 MAX units successfully ran a DeepSeek-R1 671B Q4 large model. A reserved cluster power-on interface allows for unified start-up and shutdown
Rank #4
- FAST RUNS IN THE FAMILY — The 16-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
- BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
- MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Free tools Windows power users keep installed
One-click scans. No signup required.
