GPT-5.4 Mini vs GPT-5.4 Nano: which API costs less?
Averaged across three realistic workloads, GPT-5.4 Nano is about 73% cheaper than GPT-5.4 Mini. Below: raw rates and side-by-side monthly costs, computed from prices verified 2026-07-05 (we track what you are billed today, promos included).
Rates per 1M tokens
| Model | Input | Output | Cached input |
|---|---|---|---|
| GPT-5.4 MiniOpenAI | $0.750 | $4.50 | — |
| GPT-5.4 NanoOpenAI | $0.200 | $1.25 | — |
Monthly cost, side by side
| Workload | GPT-5.4 Mini | GPT-5.4 Nano | Difference |
|---|---|---|---|
Customer-support chatbot 2M input + 0.5M output tokens/month, 60% of input served from prompt cache | $3.75 | $1.02 | GPT-5.4 Nano −73% |
RAG / document Q&A 20M input + 1M output tokens/month, 70% cached (shared context) | $19.50 | $5.25 | GPT-5.4 Nano −73% |
Agentic coding assistant 50M input + 5M output tokens/month, 80% cached (long sessions) | $60.00 | $16.25 | GPT-5.4 Nano −73% |
Your traffic looks different? Run your own numbers in the calculator.
FAQ
Which is cheaper: GPT-5.4 Mini or GPT-5.4 Nano?
Across three realistic workloads (chatbot, RAG, agent), GPT-5.4 Nano works out about 73% cheaper than GPT-5.4 Mini on average. Raw rates: GPT-5.4 Mini $0.750/$4.50 per 1M tokens vs GPT-5.4 Nano $0.200/$1.25. Verified 2026-07-05.
Does prompt caching change the comparison?
Yes — cached input costs the full input rate on GPT-5.4 Mini (no cache discount listed) and the full input rate on GPT-5.4 Nano (no cache discount listed). Our scenario numbers already include realistic cache hit rates.
Is cheaper always better?
No. Price is one axis — model capability, context window and latency differ. This page answers only the cost question; benchmark quality on your own tasks before switching.