Skip to content

Allow Subagents to Use Different AI Models #519

Description

@Mohammed-Yasin-Mulla

Feature Description

Add support for configuring a different AI model for each subagent. This would allow users to assign the most appropriate model to a specific subagent based on its responsibilities, rather than requiring all subagents to use the same model as the parent agent.

For example, a lightweight and cost-effective model could be used for simple tasks such as file creating a report, analysing ,or documentation generation, while more capable models could be assigned to complex reasoning, architecture design, or debugging tasks.

Use Case

  • Optimized credit usage by reserving premium models for tasks that truly require them.
  • Improved task performance by matching each subagent with a model that excels at its specific workload.
  • Greater flexibility in designing agent workflows.
  • Better scalability when running multiple subagents in parallel.

Allowing per-subagent model selection would enable users to balance cost, speed, and quality more effectively, resulting in more efficient and capable multi-agent workflows.

Additional Context

No response

How important is this to you?

None

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels
    No fields configured for Feature.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions