What changed
OpenAI released GPT-5.4 mini through the API, Codex, and ChatGPT, and released GPT-5.4 nano through the API. The smaller models target subagents, coding, extraction, classification, and ranking, with mini supporting a 400,000-token context window at lower prices than GPT-5.4.
Why it matters
Frontier-model families now provide purpose-built smaller models that can take most routine agent steps while reserving expensive models for genuinely difficult decisions.
What to do
Route extraction, ranking, and bounded subagent work to mini or nano, then measure fallback rate and total cost per accepted result against an all-frontier baseline.
Caveat
OpenAI's benchmark and speed claims are vendor-reported, nano has materially lower capability, and mini usage in Codex consumes quota.