Lab
Lab summary is pending review.
DeepSeek chat model for instruction following, coding, and analysis
High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes
Classic open reasoning model for transparent math, coding, and deliberate problem solving
R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Open DeepSeek MoE chat model for coding, math, and general reasoning
March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Open MoE flagship with million-token context for coding and long agent runs
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes