Multi-agent delegation to lower-cost models to save Codex limits

Melvin Vivas · X post · 2026-08-16 · Open on X

Topics: AI Agents, Tool Use & MCP, LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity · Level: intermediate

Summary

The creator points to a newly shipped multi agents v2 feature. It lets a model hand off work to any supported model, including a cheaper one called Luna. Sending specific tasks to lower-cost models could save usage and help with Codex limit problems.

Key points

Multi agents v2 lets a primary model hand off subtasks to any supported model.
Luna is named as one of the models it can delegate to.
Sending narrow tasks to cheaper models uses fewer expensive-model tokens and less of your limit.
This is a cost-optimization pattern for agentic coding systems.
The creator says the feature was not yet released in Codex.

Resources mentioned

OpenAI Codex · tool · openai.com · paid
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more
Luna · tool · openai.com · paid
The other model/agent the classifier routes tasks to; the post doesn't describe it further.
Also in: GPT-6.1 Sol May Beat Luna for Subagents (Melvin Vivas on X · notes), Picking models for orchestrator and subagent roles in Codex (Melvin Vivas on X · notes), GPT-6 Sol Ultra Subagents Use Up Limits Fast (Melvin Vivas on X · notes), GPT-6 Sol vs Opus 5.5 in a Livestream Comparison (Melvin Vivas on X · notes) and 14 more

Try this

Build an orchestrator agent that hands off simple subtasks to a cheaper model and keeps hard reasoning on a stronger model, then compare token cost.