Head to head
OpenAI: GPT-5.4 vs OpenAI: GPT-5.6 Luna
Live prices, context windows, capabilities, and measured quality — updated continuously.
Side by side
| Metric | OpenAI: GPT-5.4 Openai | OpenAI: GPT-5.6 Luna Openai |
|---|---|---|
| Input $/M tokens | $1.25 | $0.200 |
| Output $/M tokens | $7.50 | $1.20 |
| Context window | 1.1M | 1.1M |
| Max output | 128K | 128K |
| WM Score | 85 | 82 |
| Benchmark quality | 83.9 | 75.9 |
| Hosts serving it | 3 | 3 |
| Throughput (tok/s) | 46 | 134 |
| Latency (ms) | 1962 | 1041 |
| Vision | ||
| Tools | ||
| Reasoning | ||
| JSON mode |
Which should you pick?
OpenAI: GPT-5.6 Luna costs less per million input tokens — about 6.3× cheaper than OpenAI: GPT-5.4. OpenAI: GPT-5.4 scores higher on measured quality. Prices here are live list prices; the same model can cost less on a different host, so check the model page for the cheapest offering.