GitHub Copilot Fusion GA：自动路由编排模型
Route and orchestrate models with GitHub Copilot Fusion
Copilot 核心交互范式从“手动选模”变为“自动路由”，直接影响所有重度使用者的日常编码效率与成本结构。建议立即在 IDE 中切换至 Fusion 模式测试效果，并通知管理员检查企业模型策略配置。
GitHub Copilot Fusion is generally available. Instead of picking a model for each task, choose Copilot Fusion and let Copilot intelligently route and orchestrate which models it uses for you.
GitHub Copilot Fusion 现已全面可用。您无需为每个任务单独选择模型，只需选择 Copilot Fusion，让 Copilot 智能路由并编排所使用的模型。
Copilot Fusion brings together Project HydraFusion’s multi-model orchestration and Copilot auto model selection’s fine-tuned model selection, leveraging the benefits of both to balance performance and cost efficiency.
Copilot Fusion 融合了 Project HydraFusion 的多模型编排能力与 Copilot 自动模型选择的微调模型选择功能，兼顾两者的优势，以平衡性能与成本效率。
Since Project HydraFusion launched, we’ve improved its performance. In the Artificial Analysis Coding Agent Index, Copilot Fusion Max scored 60, within two points of Claude Code with Opus 5.5 Max. It delivered that result at about half the average API cost per task, using about half as many tokens and taking about 40% less time per task.
自 Project HydraFusion 发布以来，我们已提升其性能。在 Artificial Analysis Coding Agent Index 中，Copilot Fusion Max 得分 60，仅比使用 Opus 5.5 Max 的 Claude Code 低两分。该结果的平均 API 成本约为后者的一半，使用的 Token 数量也减少约一半，且每项任务的耗时减少了约 40%。
Smarter choices for developers
为开发者提供更明智的选择
When you select Copilot Fusion in the model picker, you aren’t selecting a specific model. You’re choosing a system that routes and orchestrates models for each task. There’s no need to switch models during a task or decide which model suits each step. For each prompt, Copilot Fusion determines which models to use and how they work together, while you choose the right level of effort.
当您在模型选择器中选择 Copilot Fusion 时，并非选择一个特定模型，而是选择一个系统，该系统会为每个任务路由和编排模型。您无需在任务过程中切换模型，也无需决定哪个模型适合每个步骤。对于每个提示词，Copilot Fusion 会确定使用哪些模型以及它们如何协同工作，而您只需选择合适的投入程度。
To use it, select Copilot Fusion in the model picker, then choose the effort level.
要使用它，请在模型选择器中选择 Copilot Fusion，然后选择投入程度级别。
- Fusion Standard: Prioritizes versatile models for everyday coding.
- Fusion High: Prioritizes capable models for challenging tasks and deeper reasoning.
- Fusion Max: Prioritizes the most capable models for the most demanding tasks and complex reasoning.
- Fusion Standard：优先使用通用型模型进行日常编码。
- Fusion High：优先使用功能强大的模型处理挑战性任务和深度推理。
- Fusion Max：优先使用最强大的模型处理最复杂的任务和复杂推理。
Watch as Copilot Fusion analyzes each task and selects a model to complete it, orchestrating multiple models through the following workflows when needed.
观看 Copilot Fusion 如何分析每个任务并选择模型来完成它，并在需要时通过以下工作流程编排多个模型。
- Single: One model solves the task directly.
- Cascade: An efficient model drafts a response. A quality check determines whether to accept it or escalate to a stronger model.
- Critique: One model drafts an initial response, another model reviews it, and the original model revises.
- Single（单模型）：一个模型直接解决任务。
- Cascade（级联）：一个高效模型起草响应。质量检查决定是接受该响应还是升级到更强的模型。
- Critique（批判）：一个模型起草初始响应，另一个模型对其进行审查，原始模型随后进行修改。
More control for administrators
为管理员提供更多控制
Administrators control which models Copilot Fusion can use and whether Copilot Fusion is the default.
管理员控制 Copilot Fusion 可以使用哪些模型，以及 Copilot Fusion 是否为默认选项。
- Copilot Fusion only uses the models that are enabled in your enterprise and organization model policies. Enterprise administrators can view what models Copilot Fusion picks from, independently set each model’s effective policy state, and disable models for Copilot Fusion without disabling the model for everyone. See Manage availability of default models.
- Administrators can set Copilot Fusion, at any effort level, as the default model for Copilot users with Enterprise managed settings. To configure settings, see Enterprise managed settings.
- Copilot Fusion 仅使用在企业组织和组织模型策略中启用的模型。企业管理员可以查看 Copilot Fusion 从哪些模型中进行选择，独立设置每个模型的有效策略状态，并在不禁止所有人使用该模型的情况下，禁用 Copilot Fusion 对某些模型的使用。请参阅管理默认模型的可用性。
- 管理员可以将 Copilot Fusion 设置为具有企业托管设置的 Copilot 用户的默认模型，且可在任何努力级别下使用。要配置设置，请参阅企业托管设置。
“GitHub Copilot Fusion Standard has improved token efficiency across AT&T by automatically selecting the right model for the task, reducing unnecessary spend and preserving capacity for higher-value work. Previously, developers would often choose a more powerful model for a complex task and forget to switch back for everyday activities. Copilot Fusion eliminates that friction, optimizing model selection without requiring developers to manage it themselves. We’ve also seen its decision-making improve over time, giving developers greater confidence to focus on their work while Copilot handles model selection.”
“GitHub Copilot Fusion Standard 通过自动为任务选择最合适的模型，提高了 AT&T 的令牌效率，减少了不必要的支出，并为更高价值的工作保留了容量。以前，开发人员通常会为复杂任务选择更强大的模型，却忘记在日常活动中切换回来。Copilot Fusion 消除了这种摩擦，在无需开发人员自行管理的情况下优化了模型选择。我们还观察到其决策能力随着时间的推移而提升，使开发人员能够更有信心地专注于工作，同时由 Copilot 处理模型选择。”
Hari Pokhrel, Principal Software Engineer, AT&T
Hari Pokhrel，AT&T 首席软件工程师
Billing
计费
When you use Copilot Fusion you’re billed for each model it uses, at each model’s standard rate. For a limited time, users on paid Copilot plans will receive a 30% discount on model costs when using Copilot Fusion.
当您使用 Copilot Fusion 时，系统会根据其使用的每个模型的标准费率进行计费。在有限时间内，付费 Copilot 计划的用户在使用 Copilot Fusion 时将享受模型费用 30% 的折扣。
Get started
开始使用
Copilot Fusion is available on all Copilot plans in Visual Studio Code, the GitHub Copilot app, GitHub Copilot CLI, and JetBrains IDEs. Support for additional clients is coming soon.
Copilot Fusion 适用于 Visual Studio Code、GitHub Copilot 应用、GitHub Copilot CLI 和 JetBrains IDE 中的所有 Copilot 计划。对其他客户端的支持即将推出。
Update your client to try it out. Open the model picker, select Copilot Fusion, and choose an effort level.
更新您的客户端以试用。打开模型选择器，选择 Copilot Fusion，并选择一个努力级别。
Note for research preview participants: if you previously enabled auto, HydraFusion, or HydraFusion Max, your selections will automatically transition to the corresponding Copilot Fusion effort levels.
研究预览参与者注意：如果您之前启用了 auto、HydraFusion 或 HydraFusion Max，您的选择将自动过渡到相应的 Copilot Fusion 努力级别。
To learn more, see our documentation on GitHub Copilot Fusion and share your feedback in the GitHub Community.
要了解更多信息，请参阅我们关于 GitHub Copilot Fusion 的文档，并在 GitHub 社区中分享您的反馈。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力