DeepSeek V4.1 Flash vs DeepSeek V4.1 Flash (reka-ai)
DeepSeek V4.1 Flash is cheaper on output tokens. Choose DeepSeek V4.1 Flash or DeepSeek V4.1 Flash (reka-ai) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek V4.1 Flash | DeepSeek V4.1 Flash (reka-ai) |
|---|---|---|
| Provider | DeepSeek | LLM Gateway |
| Input / 1M tokens | $0.17 | $0.30 |
| Output / 1M tokens | $0.66 | $1.20 |
| Context window | 1M | 1M |
| Parameters | — | — |
| Open weights | — | Yes |
| Released | — | Sep 2026 |
| LMArena (Chatbot Arena) Elo score | 1464 | — |
| GPQA Diamond score | 93.2 | — |
| LMArena WebDev Elo score | 1664 | — |
| LMArena Vision Elo score | 1278 | — |
| Epoch Capabilities Index score | 156 | — |
FAQ
Is DeepSeek V4.1 Flash or DeepSeek V4.1 Flash (reka-ai) cheaper?
DeepSeek V4.1 Flash is cheaper on output tokens ($0.66 vs $1.20 per 1M).
Which has the larger context window, DeepSeek V4.1 Flash or DeepSeek V4.1 Flash (reka-ai)?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.