---
格式版本: 2
标题: "Amazon Bedrock now supports OpenAI models in India"
原文链接: "https://aws.amazon.com/cn/about-aws/whats-new/2026/08/amazon-bedrock-openai-india-v1/"
发布日期: "2026-08-18"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-08-18T23:30:00Z"
发布时间校准原因: "页面脚本字段中的postDateTime为2026-08-18T23:30:00Z，是AWS官方公告的发布时间，且与URL日期一致，不涉及排除项。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-21T09:55:55+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 11798
发现时间: "2026-08-21T09:50:45+08:00"
入库时间: "2026-08-21T01:56:09.729Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  - "throughput"
相关厂家:
  - "AWS"
  - "OpenAI"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 30
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容为AWS Bedrock支持OpenAI模型跨区域推理的云服务公告，仅提及吞吐量，未涉及超节点、AI Rack、机柜级系统或相关硬件架构，与项目主题无关。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-21T09:56:57+08:00"
AI主题相关性: 0
AI来源权威性: 15
AI新颖性: 5
AI技术细节: 0
AI商业部署信号: 0
AI完整性: 10
AI摘要: "Amazon Bedrock 在印度推出 OpenAI GPT-5.6 模型（Terra 和 Luna），通过 India Geo 跨区域推理确保推理请求在印度境内处理，以满足数据驻留要求。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T02:13:28.264Z"
采集批次: "2026年8月21日9点50分40秒"
采集批次ID: "20260821-095040-035"
去重键: "https://aws.amazon.com/cn/about-aws/whats-new/2026/08/amazon-bedrock-openai-india-v1"
---

Amazon Bedrock now supports the OpenAI GPT-5.6 models (Terra and Luna) in India, with India Geo cross-Region inference. Customers with regulatory requirements of in-country inferencing can now use OpenAI models at scale ensuring that inferencing is processed within India.

Cross-Region inference automatically routes inference requests across multiple AWS Regions to give you higher throughput, without you needing to manage capacity across multiple Regions. The new India Geo inference profiles—in.openai.gpt-5.6-terra for Terra and in.openai.gpt-5.6-luna for Luna—route requests only within the India geography, across AWS Regions such as Asia Pacific (Mumbai) and Asia Pacific (Hyderabad), so you can scale to meet demand while keeping data processed within India to meet data residency requirements. The models run on the bedrock-runtime endpoint with support for the Responses, Chat Completions, and Converse APIs, and work with the same account-level controls you already use for other models on Bedrock, including model invocation logging (deliverable to Amazon S3 or Amazon CloudWatch Logs), Amazon CloudWatch metrics, and cost itemization in AWS Cost Explorer and the AWS Cost and Usage Report.

OpenAI models with India cross-Region inference are available in the Asia Pacific (Mumbai) and Asia Pacific (Hyderabad) Regions. To get started, review the model cards for GPT-5.6 (Terra and Luna) and the Cross-Region inference section in the [Amazon Bedrock User Guide.](https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html)