GPT-4 vs Phi-3.5-mini-instruct
Phi-3.5-mini-instruct is cheaper on output tokens, while Phi-3.5-mini-instruct offers a larger context window. Choose GPT-4 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-4 | Phi-3.5-mini-instruct |
|---|---|---|
| Provider | Azure | Azure |
| Input / 1M tokens | $60.00 | $0.13 |
| Output / 1M tokens | $120.00 | $0.52 |
| Context window | 8K | 128K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Mar 2023 | Aug 2024 |
FAQ
Is GPT-4 or Phi-3.5-mini-instruct cheaper?
Phi-3.5-mini-instruct is cheaper on output tokens ($0.52 vs $120.00 per 1M).
Which has the larger context window, GPT-4 or Phi-3.5-mini-instruct?
Phi-3.5-mini-instruct has the larger context window (128K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.