Pick a winner in each dimension — change your vote anytime.
Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).
Choose GPT-5.4 Mini if you want high-volume, low-complexity agent steps on a budget. Choose GPT-5.6 Luna if you want cheap, fast subtasks, routing, and subagents in OpenAI-based stacks.
In our editorial scoring, GPT-5.6 Luna leads in 5 of five dimensions (output quality, agentic ability, speed, value for $ and reliability), while GPT-5.4 Mini leads in 0. On price, GPT-5.4 Mini runs about $1.88 per 1M tokens (blended) and is proprietary; GPT-5.6 Luna is about $2.50 and proprietary.
The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.