Navigation
DeepSeek V3 vs DeepSeek V4 Flash
DeepSeek V3 vs DeepSeek V4 Flash
Compare the exact deployment revisions, published rates and context limits.
Generated from the model catalogue
Values here, in pricing and in the machine-readable feed use the same model records.
| Model | Input / 1M | Output / 1M | Context | Type |
|---|---|---|---|---|
| DeepSeek V3 | $0.25 | $0.85 | 128K* | Text |
| DeepSeek V4 Flash | $0.09 | $0.18 | 128K* | Text |
DeepSeek V3
Code generation, complex instructions and structured tasks.
- Native context
- 131,072 tokens
- Quantization
- Not verified
- License
- MIT
- Output speed
- No measurements yet
DeepSeek V4 Flash
A text model for long-context reasoning, coding and tool workflows, with a configured 1,048,576-token window.
- Published context
- 1,048,576 tokens
- Quantization
- Not verified
- License
- MIT
- Output speed
- No measurements yet