| MODEL VERSION | DeepSeek-V4-Flash | DeepSeek-V4-Pro | |
|---|---|---|---|
| THINKING MODE | Supports both non-thinking and thinking (default) modes | | |
| CONTEXT LENGTH | 1M | | |
| MAX OUTPUT | MAXIMUM: 384K | | |
| FEATURES | Json Output | ✓ | ✓ |
| Tool Calls | ✓ | ✓ | |
| Chat Prefix Completion(Beta) | ✓ | ✓ | |
| FIM Completion(Beta) | Non-thinking mode only | Non-thinking mode only | |
| PRICING | 1M INPUT TOKENS (CACHE HIT) | $0.0028 | $0.003625 (75% off) |
| 1M INPUT TOKENS (CACHE MISS) | $0.14 | $0.435 (75% off) | |
| 1M OUTPUT TOKENS | $0.28 | $0.87 (75% off) |