Deepinfra via Requesty
DeepSeek V3
DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures.
- Context
- 128K
- Max output
- 8.2K
- Input / 1M
- $0.85
- Output / 1M
- $0.90
- Output speed
- —
Accepts
- Text input
Produces
- Text output