AWS 这条官方动态围绕「AWS 官方更新：AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances」展开，英文标题为 “AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances”。正文重点落在智能体工作流、工具调用和任务执行稳定性，需要结合官方发布内容理解它对模型使用和开发者接入的影响。
官方摘要提到：AWS Lambda now supports a 90-minute function timeout for asynchronous and event source mapping (ESM) invocations on Lambda Managed Instances (LMI) , a 6x increase from the previous 15-minute limit. You can now run data processing, media transcoding, financial calculations, AI inference, and batch workloads on Lambda for jobs that require longer continuous execution, without re-architecting your applications. Customers use Lambda to build serverless applications like event-driven processors, API backends, and data processing pipelines. For data-intensive workloads like media transcoding, financial calculations (such as Monte Carlo simulations), and AI inference that need longer continuous execution, Lambda's 15-minute function timeout limit required customers to adopt architectural workarounds. With today's launch, you can configure a function timeout of up to 90 minutes for asynchronous and ESM invocations on Lambda Managed Instances. Lambda Managed Instances lets you process multiple concurrent requests per instance, access specialized compute configurations, and drive cost efficiency through EC2 pricing advantages, without managing infrastructure. The increased function timeout also applies to invocations within Lambda durable functions , which allow you to checkpoint and replay steps for longer-running invocations. When invoked asynchronously, a multi-step durable execution can run for up to 1 year. You can configure up to a 90-minute function timeout for asynchronous and ESM invocations via the AWS Lambda Console, AWS CLI, Lambda APIs, Infrastructure as Code tooling, or the Agent Toolkit for AWS . Synchronous invocations retain the existing 15-minute maximum timeout. This feature is available in all AWS Regions where Lambda Managed Instances is available. To learn more about configuring the 90-minute function timeout, see the Lambda developer guide . For combining extended timeouts with checkpoint-and-replay resilience, see the durable functions documentation . For pricing details, see AWS Lambda Pricing . To learn more about AWS Lambda, visit aws.amazon.com/lambda .。对用户来说，这类信息最有价值的部分是判断新能力是否已经可用、适合哪些任务，以及调用时可能受到哪些版本或权限限制。
AWS 这条内容关注《AWS 官方更新：AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances》，英文标题为“AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances”，适合从智能体、插件、工具调用和自动化工作流角度阅读。对正在选择 AI API 服务的用户来说，重点不是又多了一条新闻，而是它会不会影响模型选择、调用方式、使用成本和稳定性判断。
原文信息可先概括为：AWS 这条官方动态围绕「AWS 官方更新：AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances」展开，英文标题为 “AWS Lambda now supports 90-minute function timeout on Lambda Managed Instances”。正文重点落在智能体工作流、工具调用和任务执行稳定性，需要结合官方发布内容理解它对模型使用和开发者接入的影响。。原文摘要可以作为线索，但仍要回到官方页面和实测结果核对。如果后续页面内容继续更新，应优先看官方说明中的版本、时间、适用对象和限制条件。
官方动态通常先说明产品方向或能力变化，真正落地还要看账号权限、可用区域、模型版本、接口返回、上下文限制和价格口径。把它当成选型线索，比只看标题更有价值。
放到 API 中转站评测场景中，这条动态最需要转化为可验证的问题：服务商是否真的支持相关模型或能力，模型 ID 是否一致，调用返回是否符合官方行为，延迟、错误信息、上下文长度、工具调用和价格说明是否能相互印证。
实际测试时可以这样做：准备长任务拆解、工具调用、文件处理和连续对话场景，观察任务是否能持续推进，失败后是否给出清楚的错误信息。同一组任务最好多跑几次，并记录时间、返回内容、失败原因和扣费情况，这样才能区分真实能力、临时波动和页面宣传。
智能体场景会放大接口稳定性、上下文长度和并发限制，不能只看单轮问答是否能返回内容。尤其是充值前的新手用户，建议先用低成本任务确认模型列表、基础对话、长文本、代码或生图等核心场景，再决定是否长期使用。
这类资讯更适合作为一张实操清单：先看官方来源，再看服务商是否跟进，最后用小额任务做验证。能被验证的内容，才真正有助于判断一个 API 服务是否可靠。