GPT-5.1 Codex mini (Azure) vs DeepSeek V4.1 Flash (Tencent)
DeepSeek V4.1 Flash (Tencent) is cheaper on output tokens, while DeepSeek V4.1 Flash (Tencent) offers a larger context window. Choose GPT-5.1 Codex mini (Azure) or DeepSeek V4.1 Flash (Tencent) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.1 Codex mini (Azure) | DeepSeek V4.1 Flash (Tencent) |
|---|---|---|
| Provider | Eden AI | Eden AI |
| Input / 1M tokens | $0.25 | $0.15 |
| Output / 1M tokens | $2.00 | $0.60 |
| Context window | 272K | 1M |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Nov 2025 | Sep 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.