HydraFusion updates and new Max option
Quick Answer
HydraFusion introduces an updated model pool and a new Max option, enhancing orchestration workflows with models like Claude Opus 5.5 and GPT-6.1.
Quick Take
Both HydraFusion and HydraFusion Max are available in research preview across VS Code, GitHub Copilot app, and CLI, targeting tasks requiring varying levels of reasoning effort.
Key Points
- HydraFusion now includes models like Claude Opus 5.5 and GPT-6.1 for improved task orchestration.
- Reasoning effort is tailored per task stage, enhancing efficiency in drafting and reviewing.
- HydraFusion Max is optimized for demanding tasks, applying higher reasoning efforts where needed.
- Both options are available across VS Code, GitHub Copilot app, and CLI for diverse user needs.
- Access requires Copilot Pro, Pro+, Business, or Enterprise plans with experimental features enabled.
DeepSignal Analysis
What happened
HydraFusion has been updated to include a new model pool and introduces HydraFusion Max. Both versions are currently in research preview and available across multiple platforms, including VS Code and the GitHub Copilot app. The updates enhance orchestration workflows by tailoring reasoning efforts for different tasks.
Key evidence
- HydraFusion now includes models such as Claude Opus 5.5 and GPT-6.1, expanding its capabilities for various tasks.
- The updated HydraFusion can tailor reasoning efforts, using medium effort for drafts and high effort for reviews, improving efficiency.
- HydraFusion Max is designed for more demanding tasks, applying higher reasoning efforts while considering token efficiency through orchestration.
Why it matters
These updates reflect a significant advancement in AI orchestration, allowing users to leverage multiple models without needing to select one for each task. The ability to adjust reasoning efforts based on task requirements could lead to improved outcomes in complex scenarios. As AI continues to evolve, such enhancements may set new standards for performance and efficiency in AI-assisted workflows.
📖 Reader Mode
~2 min readHydraFusion has an updated model pool, improved orchestration workflows, and introduces HydraFusion Max. Both HydraFusion and HydraFusion Max are available across VS Code, the GitHub Copilot app, and GitHub Copilot CLI and remain in research preview.
HydraFusion orchestrates multiple models to produce a single response, bringing together their strengths so you don’t have to choose an individual model for each task.
What’s new in HydraFusion
- Latest frontier models: HydraFusion and HydraFusion Max draw from a pool that now includes Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna. The models used for each task vary based on the orchestration workflow.
- Reasoning effort tailored to each step: Previously, HydraFusion only used each model’s default reasoning effort. With this update, it explicitly tailors effort to each stage, using medium effort for initial drafts and high effort for review. This keeps drafting efficient while dedicating deeper reasoning to checking and improving the work.
- Optimized Cascade and Critique workflows:
- Cascade: Previously used an initial model to solve the task, with escalation to a stronger model when needed. It can now include a judging step that inspects the initial work and requests a repair only when needed.
- Critique: Previously relied heavily on text summaries. It now relies more on tools to inspect the actual workspace directly. Critique now also uses parallel critic models to inspect work.
Introducing HydraFusion Max
HydraFusion Max is built on the same architecture and uses the same workflow techniques as HydraFusion, but is tuned for frontier capability on more demanding tasks. It applies higher reasoning efforts where depth and thoroughness matter most, while still using orchestration to consider token efficiency.
| Option | Description | Typical use case |
|---|---|---|
| HydraFusion | Balanced approach with moderate token savings. | Agentic tasks that require a balance of speed, cost, and performance. |
| HydraFusion Max | Frontier capability for more demanding tasks, with token efficiency considered through orchestration. | Tasks requiring the deepest possible reasoning and most thorough analysis. |
Both options are supported across all three clients, so you can access the latest HydraFusion experience whether you work in VS Code, the GitHub Copilot app, or the terminal.
HydraFusion and HydraFusion Max are available on Copilot Pro, Pro+, Business, and Enterprise plans with experimental or preview features enabled, subject to your organization’s model policies.
Learn more in the HydraFusion documentation.
Share your feedback in the HydraFusion discussion.
— Originally published at github.blog
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from GitHub Copilot Changelog
See more →GitHub Copilot for JetBrains adds improved OpenTelemetry configuration and model management
The latest GitHub Copilot for JetBrains update enhances workflow control with OpenTelemetry configuration, improved model management, and support for servers in Claude agent flows, facilitating better observability and cost control for enterprise users.
