Qwen2.5 72B Instruct vs GPT-6.1 Terra (US)
GPT-6.1 Terra (US) is cheaper on output tokens, while GPT-6.1 Terra (US) offers a larger context window. Choose Qwen2.5 72B Instruct or GPT-6.1 Terra (US) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen2.5 72B Instruct | GPT-6.1 Terra (US) |
|---|---|---|
| Provider | Alibaba | Amazon Bedrock |
| Input / 1M tokens | $1.40 | $1.10 |
| Output / 1M tokens | $5.60 | $5.50 |
| Context window | 131K | 1.1M |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Sep 2024 | Oct 2026 |
| LMArena (Chatbot Arena) Elo score | 1269 | — |
| GPQA Diamond score | 49.1 | — |
FAQ
Is Qwen2.5 72B Instruct or GPT-6.1 Terra (US) cheaper?
GPT-6.1 Terra (US) is cheaper on output tokens ($5.50 vs $5.60 per 1M).
Which has the larger context window, Qwen2.5 72B Instruct or GPT-6.1 Terra (US)?
GPT-6.1 Terra (US) has the larger context window (1.1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.