DeepSeek API Pricing Update (Sept 2026): Off-Peak Halves and Cache Rates
Current Rates (per 1M tokens)
| Model | Input (off/peak) | Output (off/peak) | Cache |
|---|---|---|---|
| V4.1-Flash | $0.15 / $0.30 | $0.60 / $1.20 | $0.003 |
| V4-Flash (0731) | $0.14 | $0.28 | $0.0028 |
| V4 Pro (0813) | $0.66 / $1.32 | $1.98 / $3.96 | — |
Timeline: Aug 16 V4 Pro repriced; Sep 10 V4.1-Flash with ~70% output cut; Sep 14 routing switch.