DeepSeek / Deepseek V3
Released: 3/24/2025texttext
Input: $0.27 / Output: $1.10
Deepseek V3 is a 671B LLM that excels in complex reasoning, code generation, and mathematical reasoning while maintaining efficient inference through its innovative Mixture-of-Experts architecture.
Some other noteworthy features of Deepseek V3 include its ability to process and understand extensive input sequences effectively for long-form content and its enhanced performance through advanced Multi-Token Prediction.
Metric | Value |
---|---|
Parameter Count | 671 billion |
Mixture of Experts | Yes |
Active Parameter Count | 37 billion |
Context Length | 128K tokens |
Multilingual | Yes |
Quantized* | Yes |
Precision* | FP8 |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
DeepSeek models available on Oxen.ai
Modality | Price (1M tokens) | ||||
---|---|---|---|---|---|
Model | Inference provider | Input | Output | Input | Output |
![]() | text | text | $3.00 | $8.00 | |
text | text | $0.55 | $2.19 | ||
text | text | $7.00 | $7.00 | ||
![]() | text | text | $0.59 | $0.79 | |
text | text | $0.27 | $1.10 | ||
![]() | text | text | $0.75 | $3.00 | |
text | text | $1.25 | $1.25 |