Kimi K2.5 vs DeepSeek R1-0528
DeepSeek R1-0528 is cheaper on output tokens, while Kimi K2.5 offers a larger context window. Choose Kimi K2.5 or DeepSeek R1-0528 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Kimi K2.5 | DeepSeek R1-0528 |
|---|---|---|
| Provider | TensorX | TensorX |
| Input / 1M tokens | $0.50 | $0.66 |
| Output / 1M tokens | $2.80 | $2.60 |
| Context window | 262K | 164K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Jan 2026 | May 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.