{"slug": "get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock", "title": "Get started with OpenAI GPT-5.5, GPT-5.4 models, and Codex on Amazon Bedrock", "summary": "Amazon Web Services announced the general availability of OpenAI GPT-5.5, GPT-5.4 models, and the Codex coding agent on Amazon Bedrock. The new models are designed for coding, reasoning, and complex professional workloads, while Codex enables AI-powered software development tasks such as writing, refactoring, and debugging code. All processing stays within the selected Bedrock Region for customers with data residency requirements, with per-token pricing and no seat licenses.", "body_md": "[AWS News Blog](https://aws.amazon.com/blogs/aws/)\n\n# Get started with OpenAI GPT-5.5, GPT-5.4 models, and Codex on Amazon Bedrock\n\n|\n|\n\nAs we [previewed in What’s Next with AWS 2026](https://www.aboutamazon.com/news/aws/bedrock-openai-models?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el), we’re announcing the general availability of OpenAI GPT-5.5, GPT-5.4 models, and Codex on [Amazon Bedrock](https://aws.amazon.com/bedrock/?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el), giving you access to frontier models and a coding agent for software development.\n\nAccording to OpenAI, GPT-5.5 and GPT-5.4 models are excellent for coding, reasoning, agentic workflows, and complex professional work. You can use GPT-5.5 for the hardest customer workloads and GPT-5.4 for the best price-performance. You can call them through `Responses`\n\nAPI on Amazon Bedrock’s next-generation inference engine built for high performance, reliability, and security.\n\nCodex is the OpenAI coding agent for AI-powered software development. According to OpenAI, more than 4 million developers use Codex every week to write, refactor, debug, test, and validate code across large codebases. With GPT-5.5 powering inference, Codex introduces a new class of intelligence optimized for complex, long-horizon developer workflows. You can use the Codex App, the Codex CLI, and IDE integrations with Visual Studio Code, JetBrains, and Xcode, with all model inference routed through the `Responses`\n\nAPI on Amazon Bedrock.\n\nFor customers with data residency requirements, all processing stays within the Bedrock Region you select. You pay per token with no seat licenses and no per-developer commitments.\n\n__GPT-5.5 and GPT-5.4 models on Bedrock in action__\n\nYou can access the model programmatically using the OpenAI `Responses`\n\nAPI to call the `bedrock-mantle`\n\nendpoints through the OpenAI SDK, command-line tools such as `curl`\n\n.\n\nLet’s start with OpenAI SDK for Python. Install OpenAI SDK.\n\n```\npip install -U openai\n```\n\nSet the environment variables for authentication.\n\n```\nexport OPENAI_BASE_URL=\"https://bedrock-mantle.us-east-2.api.aws/openai/v1\"\nexport OPENAI_API_KEY=\"<BEDROCK_API_KEY>\"\nexport BEDROCK_OPENAI_MODEL_ID=\"openai.gpt-5.5\"\n```\n\nHere is a sample Python code to call GPT-5.5 model on Bedrock:\n\n``` python\nimport os\nfrom openai import OpenAI\n \nclient = OpenAI(\n    base_url=os.environ[\"OPENAI_BASE_URL\"],\n    api_key=os.environ[\"OPENAI_API_KEY\"],\n)\n \nresponse = client.responses.create(\n    model=os.environ[\"BEDROCK_OPENAI_MODEL_ID\"],\n    input=[\n        {\n            \"role\": \"developer\",\n            \"content\": \"You are a software engineer with excellent AWS cloud knowledge. Be concise and practical.\",\n        },\n        {\n            \"role\": \"user\",\n            \"content\": \"Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions.\",\n        },\n    ],\n    reasoning={\"effort\": \"medium\"},\n    text={\"verbosity\": \"low\"},\n)\n \nprint(response.output_text)\n```\n\nYou can call directly the model endpoint using `curl`\n\n.\n\n```\ncurl \"$OPENAI_BASE_URL/responses\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"openai.gpt-5.5\",\n    \"input\": [\n      {\n        \"role\": \"developer\",\n        \"content\": \"You are a software engineer with excellent AWS cloud knowledge.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions.\"\n      }\n    ],\n    \"reasoning\": {\"effort\": \"medium\"},\n    \"text\": {\"verbosity\": \"low\"}\n  }'\n```\n\nYou can use the `Responses`\n\nAPI when you want to use model-managed multi-turn state, need hosted tools, function tools, or richer tool orchestration, and run background or long-running work. To learn more, visit the [OpenAI Cookbook Responses examples](https://github.com/openai/openai-cookbook/tree/main/examples/responses_api) and [getting started guide](https://developers.openai.com/cookbook/examples/partners/aws/openai_models_with_amazon_bedrock).\n\n__Using OpenAI Codex with GPT-5.5 on Amazon Bedrock__\n\nYou can download Codex CLI, Codex App or Codex VS Code extension and get started with the Bedrock for model inference. Codex supports two Bedrock authentication pathways: [Amazon Bedrock API key](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html) or AWS SDK credential chain. If you set `AWS_BEARER_TOKEN_BEDROCK`\n\n, Codex uses it first; otherwise Codex falls back to AWS SDK credential chain.\n\nSet `AWS_BEARER_TOKEN_BEDROCK`\n\nin the environment that Codex will read:\n\n```\nexport AWS_BEARER_TOKEN_BEDROCK=<your-bedrock-api-key>\n```\n\nThen, configure your preferred Region and set the model ID to `openai.gpt-5.5`\n\nin `~/.codex/config.toml`\n\n, which is required for Bedrock API-key authentication. You can also choose `openai.gpt-5.4`\n\n, `openai.gpt-oss-120b`\n\n, or `openai.gpt-oss-20b`\n\n. For the desktop app or VS Code extension, put any environment variables the app needs in `~/.codex/.env`\n\n.\n\n```\nmodel = \"openai.gpt-5.5\"\nmodel_provider = \"amazon-bedrock\"\n[model_providers.amazon-bedrock.aws]\nregion = \"us-east-2\"\n```\n\nRestart the desktop app or VS Code extension after changing `~/.codex/config.toml`\n\nor `~/.codex/.env`\n\n. In Codex CLI, you should see a `/status`\n\ntab that looks like this:\n\nIn Codex App, you can use GPT-5.5 model through Amazon Bedrock inference.\n\nTo learn more about how to configure Codex to use OpenAI models on Amazon Bedrock, visit [Use Codex with Amazon Bedrock](https://developers.openai.com/codex/amazon-bedrock).\n\n**Things to know**\n\nLet me share some important technical details that I think you’ll find useful.\n\n**Model latency**: OpenAI model information positions GPT-5.5 as fast and GPT-5.4 as medium speed, but customer-perceived latency depends on reasoning effort, output length, tool calls, background mode, Region, quotas, throttling, prompt size, and cache hits. Start GPT-5.5 at`medium`\n\neffort. Start GPT-5.4 with effort set explicitly rather than relying on its`none`\n\ndefault.**Scaling and capacity**: Bedrock’s new inference engine is designed to rapidly provision and serve capacity across many different models. When accepting requests, we prioritize keeping steady state workloads running, and ramp usage and capacity rapidly in response to changes in demand. During periods of high demand, requests are queued, rather than rejected.\n\n__Now available__\n\nOpenAI GPT models and Codex on Amazon Bedrock are available today: GPT-5.5 model in the US East (Ohio) Region, GPT-5.4 model in the US East (Ohio) and US West (Oregon) Regions. Check the [full list of Regions](https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) for future updates. To learn more, visit the [OpenAI on Amazon Bedrock](https://aws.amazon.com/bedrock/openai/?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) page and the [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/?trk=769a1a2b-8c19-4976-9c45-b6b1226c7d20&sc_channel=el) page.\n\nGive GPT-5.5, GPT-5.4 models, and Codex on Amazon Bedrock a try today and send feedback to [AWS re:Post for Amazon Bedrock](https://repost.aws/tags/TAQeKlaPaNRQ2tWB6P7KrMag/amazon-bedrock?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) or through your usual AWS Support contacts.\n\n— [Channy](https://twitter.com/channyun)\n\n**Updated on June, 1, 2026** – The GPT models now support the Responses API only on Amazon Bedrock, and console support is coming soon.", "url": "https://wpnews.pro/news/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock", "canonical_source": "https://aws.amazon.com/blogs/aws/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock/", "published_at": "2026-06-01 21:33:28+00:00", "updated_at": "2026-06-03 10:24:18.188444+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-agents", "ai-tools"], "entities": ["OpenAI", "Amazon Bedrock", "AWS", "GPT-5.5", "GPT-5.4", "Codex", "Visual Studio Code", "JetBrains"], "alternates": {"html": "https://wpnews.pro/news/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock", "markdown": "https://wpnews.pro/news/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock.md", "text": "https://wpnews.pro/news/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock.txt", "jsonld": "https://wpnews.pro/news/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock.jsonld"}}