March 2024 release of DeepSeek V3 with 671B parameters in MoE architecture. Enhanced reasoning, coding, and multilingual capabilities with 64K context length.
Generate high-quality code across multiple programming languages.
Solve complex mathematical problems with step-by-step solutions.
Pay per token with auto-scaling
Generate high-quality code across multiple programming languages.
Solve complex mathematical problems with step-by-step solutions.
Start with our serverless API or deploy on dedicated GPUs.
Excellent performance in English and Chinese language tasks.
Process and analyze documents up to 64K tokens.
Reserved GPU for consistent performance
Excellent performance in English and Chinese language tasks.
Process and analyze documents up to 64K tokens.