GPT-5.4 vs GPT-5.4 Mini: which API costs less?
Averaged across three realistic workloads, GPT-5.4 Mini is about 70% cheaper than GPT-5.4. Below: raw rates and side-by-side monthly costs, computed from prices verified 2026-10-17 (we track what you are billed today, promos included).
Rates per 1M tokens
| Model | Input | Output | Cached input |
|---|---|---|---|
| GPT-5.4OpenAI | $2.50 | $15 | $0.250 |
| GPT-5.4 MiniOpenAI | $0.750 | $4.50 | $0.075 |
GPT-5.4: Prompts up to 272K tokens; longer prompts cost more.
Monthly cost, side by side
| Workload | GPT-5.4 | GPT-5.4 Mini | Difference |
|---|---|---|---|
Customer-support chatbot 2M input + 0.5M output tokens/month, 60% of input served from prompt cache | $9.80 | $2.94 | GPT-5.4 Mini −70% |
RAG / document Q&A 20M input + 1M output tokens/month, 70% cached (shared context) | $33.50 | $10.05 | GPT-5.4 Mini −70% |
Agentic coding assistant 50M input + 5M output tokens/month, 80% cached (long sessions) | $110 | $33.00 | GPT-5.4 Mini −70% |
Your traffic looks different? Run your own numbers in the calculator.
FAQ
Which is cheaper: GPT-5.4 or GPT-5.4 Mini?
Across three realistic workloads (chatbot, RAG, agent), GPT-5.4 Mini works out about 70% cheaper than GPT-5.4 on average. Raw rates: GPT-5.4 $2.50/$15 per 1M tokens vs GPT-5.4 Mini $0.750/$4.50. Verified 2026-10-17.
Does prompt caching change the comparison?
Yes — cached input costs $0.250 on GPT-5.4 and $0.075 on GPT-5.4 Mini. 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.