DeepSeek-V3
DeepSeekLanguage modeling/generationCode generationQuantitative reasoningQuestion answeringOpen weights
DeepSeek-V3 is language modeling/generation model published by DeepSeek in 2024 featuring 671000000000.0 parameters.
About DeepSeek-V3
We present 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) an
LLM pricing & performance
Full LLM page →DeepSeek-V3 is available via API — live cost, context, and benchmark data:
Input / 1M
$1.25
Output / 1M
$1.25
Context
131K
Tokens/sec
—
Details
- Provider
- DeepSeek
- Task
- Language modeling/generation,Code generation,Quantitative reasoning,Question answering
- Parameters
- 671000000000.0
- Released
- 2024-12-24
- Open weights
- Yes