Set up OpenAI ChatGPT Codex with LiteLLM on Amazon ECS and Amazon Bedrock
TL;DR
Deploy a customer-operated LiteLLM gateway on Amazon ECS with AWS Fargate, connect it to an OpenAI model on Amazon Bedrock, and configure Codex to route requests through the gateway's Responses API with scoped identities, budgets, rate limits, and telemetry. We also compare direct IAM Identity Center access and a managed Portkey deployment.
Nauti's Take
The practical value for small teams is centralized control over access, spending, and usage data. Before testing, verify whether a self-managed LiteLLM gateway provides enough governance in your AWS account, and compare Bedrock model costs, latency, and operational overhead with Portkey or direct IAM access.
Sources
