Gemma 3 27B vs Qwen2.5 72B
Qwen2.5 72B is cheaper on output tokens. Choose Gemma 3 27B or Qwen2.5 72B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Gemma 3 27B | Qwen2.5 72B |
|---|---|---|
| Provider | NanoGPT | |
| Input / 1M tokens | $0.08 | $0.36 |
| Output / 1M tokens | $0.45 | $0.41 |
| Context window | 131K | 131K |
| Parameters | — | 73B |
| Open weights | — | Yes |
| Released | — | Jul 2025 |
| Epoch Capabilities Index score | 130 | 129 |
FAQ
Is Gemma 3 27B or Qwen2.5 72B cheaper?
Qwen2.5 72B is cheaper on output tokens ($0.41 vs $0.45 per 1M).
Which has the larger context window, Gemma 3 27B or Qwen2.5 72B?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.