DeepSeek V4 Flash 0423 vs Yi Lightning
DeepSeek V4 Flash 0423 is cheaper on output tokens, while DeepSeek V4 Flash 0423 offers a larger context window. Choose DeepSeek V4 Flash 0423 or Yi Lightning based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek V4 Flash 0423 | Yi Lightning |
|---|---|---|
| Provider | DeepSeek | NanoGPT |
| Input / 1M tokens | $0.09 | $0.20 |
| Output / 1M tokens | $0.18 | $0.20 |
| Context window | 1M | 12K |
| Parameters | 284B | — |
| Open weights | Yes | No |
| Released | Apr 2026 | Oct 2024 |
| LiveBench score | 65.5 | — |
| LMArena (Chatbot Arena) Elo score | 1432 | 1301 |
| LMArena WebDev Elo score | 1582 | — |
| GPQA Diamond score | 91.0 | — |
| Epoch Capabilities Index score | 154 | — |
| Aider Polyglot score | — | 12.9 |
FAQ
Is DeepSeek V4 Flash 0423 or Yi Lightning cheaper?
DeepSeek V4 Flash 0423 is cheaper on output tokens ($0.18 vs $0.20 per 1M).
Which has the larger context window, DeepSeek V4 Flash 0423 or Yi Lightning?
DeepSeek V4 Flash 0423 has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.