DeepSeek-V3.1 vs GPT-5.2 Codex
DeepSeek-V3.1 is cheaper on output tokens, while GPT-5.2 Codex offers a larger context window. Choose DeepSeek-V3.1 or GPT-5.2 Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek-V3.1 | GPT-5.2 Codex |
|---|---|---|
| Provider | Azure | Azure |
| Input / 1M tokens | $0.56 | $1.75 |
| Output / 1M tokens | $1.68 | $14.00 |
| Context window | 131K | 400K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Aug 2025 | Jan 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.