🚀 New model available: DeepSeek-V3.1 🚀
deepseek-ai/
DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.
DeepSeek-V3-0324
Ask me anything
Settings
© 2025 Deep Infra. All rights reserved.