DeepSeek V3.1 Terminus (Thinking)
by NanoGPT · family deepseek-thinking · listed Sep 2025T
DeepSeek chat model for instruction following, coding, and analysis
Current rates USD per 1M tokens
Input$0.25
Output$0.70
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
deepseek-ai/DeepSeek-V3.1-Terminus:thinking- Context window
- 128K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-09-22
- Last updated
- 2025-09-22
← All NanoGPT listings