Head to head
OpenAI: GPT-5.6 Luna vs Xiaomi: MiMo-V2.5
Live prices, context windows, capabilities, and measured quality — updated continuously.
Side by side
| Metric | OpenAI: GPT-5.6 Luna Openai | Xiaomi: MiMo-V2.5 Xiaomi |
|---|---|---|
| Input $/M tokens | $0.100 | $0.140 |
| Output $/M tokens | $0.600 | $0.280 |
| Context window | 1.1M | 1.1M |
| Max output | 128K | 131K |
| WM Score | 82 | 80 |
| Benchmark quality | 75.9 | 70.9 |
| Hosts serving it | 3 | 5 |
| Throughput (tok/s) | 122 | 33 |
| Latency (ms) | 889 | 1175 |
| Vision | ||
| Tools | ||
| Reasoning | ||
| JSON mode |
Which should you pick?
OpenAI: GPT-5.6 Luna costs less per million input tokens — about 1.4× cheaper than Xiaomi: MiMo-V2.5. OpenAI: GPT-5.6 Luna 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.