gpt-5.4-mini · OpenAI
The 5.4 small tier at $0.75/$4.50 — the workhorse for chat and RAG before the 5.6 Luna price reset.
Last checked Aug 16, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Note: Context/max-output not separately published; family defaults shown. Confirm the current rate at the official provider source.
Input
$0.75
per 1M tokens
Output
$4.50
per 1M tokens
Cached input
$0.075
per 1M tokens
Context window
1.1M
max output 128K
GPT-5.4 mini cost calculator
What GPT-5.4 mini costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.002546 | $76.387 |
| RAG / search-augmented answers | 8,000 | 500 | $0.00555 | $166.50 |
| AI coding assistant | 12,000 | 2,000 | $0.0131 | $394.20 |
| Document summarization | 25,000 | 600 | $0.0198 | $592.875 |
| Agentic workflow | 40,000 | 1,500 | $0.0192 | $576.00 |
| Content generation | 800 | 1,200 | $0.005838 | $175.14 |
| Data extraction & tagging | 2,000 | 250 | $0.002355 | $70.65 |
| Translation | 5,000 | 5,500 | $0.028 | $839.813 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| GPT-5.4 mini | $0.75 | $4.50 | 1.1M | $0.00525 |
| GPT-5.6 Luna | $0.20 | $1.20 | 1.1M | $0.0014 |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1M | $0.00266 |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | $0.0062 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
GPT-5.4 mini costs $0.75 per 1M input tokens and $4.50 per 1M output tokens, with cached input at $0.075 per 1M tokens. Verified Aug 16, 2026 against https://developers.openai.com/api/docs/pricing.
GPT-5.4 mini supports a 1,050,000-token context window with up to 128,000 output tokens per request, tokenized with o200k_base.
At $0.75/M input and $4.50/M output, GPT-5.4 mini sits above GPT-5.6 Luna ($0.20/M in, $1.20/M out) — see the comparison table for full-workload differences.