DeepSeek V4 Pro vs DeepSeek V4 Flash
30-second takeaway
- DeepSeek V4 Flash has the cheaper input: $0.15 vs $0.66 (per 1M tokens, 77% less)
- Same context window (1.049M tokens)
| DeepSeek V4 Pro DeepSeek | DeepSeek V4 Flash DeepSeek | |
|---|---|---|
| Input | $0.66 | $0.15 |
| Output | $1.98 | $0.6 |
| Context | 1.049M | 1.049M |
More specs (max output / capabilities)
| max output | 393,216 | 393,216 |
| Reasoning | ✓ Yes | ✓ Yes |
| Tool calls | ✓ Yes | ✓ Yes |
| Open weights | ✓ Yes | ✓ Yes |
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.