DeepSeek V3.2 Thinking
by Vercel AI Gateway · family deepseek-thinking · listed Dec 2025RT
DeepSeek chat model for instruction following, coding, and analysis
Current rates USD per 1M tokens
Input$0.62
Output$1.85
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
deepseek/deepseek-v3.2-thinking- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Jul 2024
- Released
- 2025-12-01
- Last updated
- 2025-12-01
← All Vercel AI Gateway listings