Introducing explicit prompt caching for OpenAI GPT-5.6 models on Amazon Bedrock

<p><i>This post is co-written with Chris Dickens from OpenAI.</i></p> <p>OpenAI GPT-5.6 Sol, Terra, and Luna are <a href="https://aws.amazon.com/blogs/machine-learning/openai-gpt-5-6-sol-terra-and-luna-are-now-generally-available-on-amazon-bedrock/" target="_blank" rel="noopener">now generally available on Amazon Bedrock</a>. With GPT-5.6 on Amazon Bedrock, you get the newest generation of OpenAI frontier models with pay-per-token pricing, AWS security and governance controls, and usage that counts toward your existing AWS commitments. The family covers three capability tiers: GPT-5.6 Sol for the most complex reasoning and agentic coding work, GPT-5.6 Terra for balanced everyday production workloads, and GPT-5.6 Luna for fast, high-volume tasks such as classification and summarization.</p> <p>Alongside the new models, GPT-5.6 introduces <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html" target="_blank" rel="noopener">explicit prompt caching</a> on Amazon Bedrock, a new capability that gives you precise control over which portions of your prompt are cached and reused across requests. Cached input is billed at a 90 percent discount (see the <a href="https://aws.amazon.com/bedrock/pricing/" target="_blank" rel="noopener">Amazon Bedrock pricing page</a>) and stays available for reuse for 30 minutes. You get the most value from this in agentic workflows, where system instructions, tool definitions, and reference documents repeat across many calls.</p> <p>In this post, we introduce explicit prompt caching for GPT-5.6 on Amazon Bedrock, a new capability that gives you control over which parts of your prompt are cached and reused across requests. We show how it differs from implicit caching and when to use each mode, how to set it up and verify that it is working, and how it performs in an agentic workflow. We also cover how to migrate workloads from earlier GPT models onto GPT-5.6, whether they run on Amazon Bedrock today or on another platform.</p> <h2 id="get-started-with-gpt-5.6-on-amazon-bedrock">Get started with GPT-5.6 on Amazon Bedrock</h2> <p>GPT-5.6 models are served through the OpenAI-compatible Responses API on the Amazon Bedrock <code>bedrock-mantle</code> endpoint.</p> <h3 id="set-up-the-client">Set up the client</h3> <p>The recommended way to authenticate is with short-term bearer tokens generated from your AWS credentials. Install the token generator alongside the OpenAI SDK:</p> <div class="hide-language"> <pre><code class="language-bash">pip install openai aws-bedrock-token-generator</code></pre> </div> <p>Then create a client. The token generator uses the standard AWS credential chain (IAM roles, environment variables, or your CLI profile), so your code stays free of long-lived secrets:</p> <div class="hide-language"> <pre><code class="language-python">from openai import OpenAI from aws_bedrock_token_generator import provide_token REGION = "us-east-2" client = OpenAI( base_url=f"https://bedrock-mantle.{REGION}.api.aws/openai/v1", api_key=provide_token(region=REGION), # short-term token from your AWS credentials )</code></pre> </div> <h3 id="make-your-first-request">Make your first request</h3> <p>GPT-5.6 models use the Responses API. A minimal request looks like this:</p> <div class="hide-language"> <pre><code class="language-python">response = client.responses.create( model="openai.gpt-5.6-terra", instructions="You are a concise technical assistant.", input="What is Amazon Bedrock?", max_output_tokens=500, ) print(response.output_text)</code></pre> </div> <p>The three model IDs are <code>openai.gpt-5.6-sol</code>, <code>openai.gpt-5.6-terra</code>, and <code>openai.gpt-5.6-luna</code>. GPT-5.6 Sol is available in US East (N. Virginia) and US East (Ohio). Terra and Luna are additionally available in US West (Oregon). For model availability by Region, refer to Supported models by AWS Region in Amazon Bedrock (<a href="https://docs.aws.a