Qwen3 Max vs Qwen2.5 72B
Qwen2.5 72B is cheaper on output tokens, while Qwen3 Max offers a larger context window. Choose Qwen3 Max or Qwen2.5 72B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3 Max | Qwen2.5 72B |
|---|---|---|
| Provider | Alibaba | NanoGPT |
| Input / 1M tokens | $1.20 | $0.36 |
| Output / 1M tokens | $6.00 | $0.40 |
| Context window | 262K | 131K |
| Parameters | 1T | 73B |
| Open weights | No | Yes |
| Released | Sep 2025 | Jul 2025 |
| GPQA Diamond score | 72.6 | — |
| Epoch Capabilities Index score | 142 | 129 |
| LMArena (Chatbot Arena) Elo score | 1413 | — |
FAQ
Is Qwen3 Max or Qwen2.5 72B cheaper?
Qwen2.5 72B is cheaper on output tokens ($0.40 vs $6.00 per 1M).
Which has the larger context window, Qwen3 Max or Qwen2.5 72B?
Qwen3 Max has the larger context window (262K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.