DeepSeek V3.1 vs GPT-4o-mini
GPT-4o-mini is cheaper on output tokens, while DeepSeek V3.1 offers a larger context window. Choose DeepSeek V3.1 or GPT-4o-mini based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek V3.1 | GPT-4o-mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Input / 1M tokens | $0.25 | $0.15 |
| Output / 1M tokens | $0.95 | $0.60 |
| Context window | 164K | 128K |
| Parameters | — | — |
| Open weights | — | No |
| Released | — | Jul 2024 |
| Epoch Capabilities Index score | 140 | 127 |
| LMArena (Chatbot Arena) Elo score | 1420 | 1286 |
| Aider Polyglot score | — | 3.6 |
| GPQA Diamond score | — | 37.7 |
| LMArena Vision Elo score | — | 1066 |
FAQ
Is DeepSeek V3.1 or GPT-4o-mini cheaper?
GPT-4o-mini is cheaper on output tokens ($0.60 vs $0.95 per 1M).
Which has the larger context window, DeepSeek V3.1 or GPT-4o-mini?
DeepSeek V3.1 has the larger context window (164K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.