GPT-5.6 Luna vs Phi-3.5-mini-instruct
Phi-3.5-mini-instruct is cheaper on output tokens, while GPT-5.6 Luna offers a larger context window. Choose GPT-5.6 Luna or Phi-3.5-mini-instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.6 Luna | Phi-3.5-mini-instruct |
|---|---|---|
| Provider | Azure | Azure |
| Input / 1M tokens | $0.20 | $0.13 |
| Output / 1M tokens | $1.20 | $0.52 |
| Context window | 1.1M | 128K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Jul 2026 | Aug 2024 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.