Navigation
DeepSeek V3 vs DeepSeek R1
DeepSeek V3 vs DeepSeek R1
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 R1 | $0.50 | $2.15 | 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 R1
Difficult reasoning, mathematics and code analysis.
- Native context
- 131,072 tokens
- Quantization
- Not verified
- License
- MIT
- Output speed
- No measurements yet