Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | JT-MINI | GPT-5.6 Luna (medium) |
|---|---|---|
| Input ($/M tokens) | $0 | $1 |
| Output ($/M tokens) | $0 | $6 |
Data from Artificial Analysis API — 12 benchmarks
JT-MINI is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $2.25/M for GPT-5.6 Luna (medium).
GPT-5.6 Luna (medium) wins 5 out of 12 benchmarks compared to 2 for JT-MINI. See the detailed benchmark chart above for per-category results.
GPT-5.6 Luna (medium) generates tokens faster at 198 tok/s vs 0 tok/s. JT-MINI also has lower time-to-first-token (0.00s vs 2.97s).
Choose based on your priorities: JT-MINI for lower cost, GPT-5.6 Luna (medium) for stronger benchmark performance, and GPT-5.6 Luna (medium) for faster generation. For latency-sensitive apps, check the TTFT comparison above.