Get started with OpenAI GPT-5.6 Sol, Terra, and Luna on Amazon Bedrock

<p><em>This post is co-written with Chris Dickens from OpenAI.</em></p> <p>Developers building agentic coding, long-horizon reasoning, and high-volume inference workloads want frontier models they can call through familiar APIs, without operating separate model infrastructure. OpenAI <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">GPT-5.6</a> Sol, Terra, and Luna are now generally available on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>. The three models cover workloads from autonomous coding agents and long-horizon reasoning to high-volume, latency-sensitive inference, and they run with the security, Regional processing, and cost controls of AWS.</p> <p>You access all three models through the OpenAI Responses API on the bedrock-mantle endpoint. Sol is the flagship reasoning model, Terra balances performance and cost for everyday production work, and Luna is optimized for fast, low-cost inference, so you can right-size capability and cost for each workload. Pricing matches OpenAI first-party rates, and usage counts toward your existing AWS commitments.</p> <p>In this post, we show you how to select a model, run your first inference through the Responses API, reduce cost with prompt caching and measure cached-token usage, connect the OpenAI Codex coding agent, and plan for quotas and scaling. Your prompts and completions are not used to train any models, and are not shared with the model provider.</p> <h2 id="the-gpt-5.6-family-on-amazon-bedrock">The GPT-5.6 family on Amazon Bedrock</h2> <p>GPT-5.6 introduces a naming system from OpenAI where the number identifies the generation and the names Sol, Terra, and Luna identify durable capability tiers that can advance on their own cadence. The following table summarizes the key specifications for each model on Amazon Bedrock.</p> <table border="1px" width="100%" cellpadding="10px"> <tbody> <tr> <td><strong>Model</strong></td> <td><strong>Model ID</strong></td> <td><strong>Best suited for</strong></td> <td><strong>AWS Regions</strong></td> </tr> <tr> <td><strong>Sol</strong></td> <td>openai.gpt-5.6-sol</td> <td>Autonomous coding, security research, scientific analysis, and deep multi-step reasoning</td> <td>US East (N. Virginia), US East (Ohio)</td> </tr> <tr> <td><strong>Terra</strong></td> <td>openai.gpt-5.6-terra</td> <td>General-purpose production workloads that balance reasoning, performance, and cost</td> <td>US East (N. Virginia), US East (Ohio), US West (Oregon)</td> </tr> <tr> <td><strong>Luna</strong></td> <td>openai.gpt-5.6-luna</td> <td>High-volume, latency-sensitive workloads such as classification, summarization, and routing</td> <td>US East (N. Virginia), US East (Ohio), US West (Oregon)</td> </tr> </tbody> </table> <p>All three models support text and image input, text output, a 272K-token context window, and the Responses API. They also support <code>none</code>, <code>low</code>, <code>medium</code>, <code>high</code>, <code>xhigh</code>, and <code>max</code> reasoning effort, so you can switch models without changing your API integration.</p> <h2 id="accessing-gpt-5.6-through-the-bedrock-mantle-endpoint">Accessing GPT-5.6 through the bedrock-mantle endpoint</h2> <p>You access GPT-5.6 models through the OpenAI Responses API on the <code>bedrock-mantle</code> endpoint. The base URL is <code>https://bedrock-mantle.{region}.api.aws</code>, and the Responses API is served at <code>/openai/v1/responses</code>. Replace <code>{region}</code> with a supported AWS Region, such as <code>us-east-1</code>. This <code>openai/v1</code> path is specific to the OpenAI models. The endpoint works with the OpenAI Python and TypeScript SDKs. To run an existing OpenAI SDK application on Amazon Bedrock, replace the OpenAI