Original sourceRuntimeWireAdditional: Crypto Briefing
Summary
OpenAI has enabled cross-model delegation in Codex's Multi Agents v2, allowing Codex to assign tasks to cheaper, faster Luna workers in the GPT-5.6 family. Luna workers are 'pure subagents' used for simple, bounded tasks; they do not coordinate with other agents or spawn new agents. Sol remains the…
Key points
- Developers can leverage this feature to reduce costs and improve efficiency for agent tasks, especially for large volumes of simple tasks.
- This update marks cost-tiered management for AI agents, helping optimize development workflows.
- Developers can more finely control AI agent costs and enhance handling efficiency for high-load tasks.
Editorial note
This page is Code & Chain's editorial summary of public sources. It may be prepared with AI assistance and published through an automated workflow. Refer to the original sources; this content is not investment, legal, or tax advice.