by 0G Foundation
DeepSeek-V3.2 is a 671B-parameter mixture-of-experts LLM with hybrid thinking mode, excelling at coding, math, and multi-step reasoning. Supports native function calling and context caching.
131K
131,072 tokens
66K
65,536 tokens
0.5900 0G
per 1M tokens
0.8900 0G
per 1M tokens
1
chatbot