GPT-6.1 Terra (US) vs DeepSeek-R1
DeepSeek-R1 is cheaper on output tokens, while GPT-6.1 Terra (US) offers a larger context window. Choose GPT-6.1 Terra (US) or DeepSeek-R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-6.1 Terra (US) | DeepSeek-R1 |
|---|---|---|
| Provider | Amazon Bedrock | Azure |
| Input / 1M tokens | $1.10 | $1.35 |
| Output / 1M tokens | $5.50 | $5.40 |
| Context window | 1.1M | 164K |
| Parameters | — | 671B |
| Open weights | No | Yes |
| Released | Oct 2026 | Jan 2025 |
| LMArena (Chatbot Arena) Elo score | — | 1428 |
| GPQA Diamond score | — | 76.3 |
| Epoch Capabilities Index score | — | 141 |
FAQ
Is GPT-6.1 Terra (US) or DeepSeek-R1 cheaper?
DeepSeek-R1 is cheaper on output tokens ($5.40 vs $5.50 per 1M).
Which has the larger context window, GPT-6.1 Terra (US) or DeepSeek-R1?
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.