K2-Think
by NanoGPT · family kimi-thinking · listed Jul 2025
Kimi reasoning model for long-horizon research, planning, and tool use
Current rates USD per 1M tokens
Input$0.17
Output$0.68
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
LLM360/K2-Think- Context window
- 128K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-07-26
- Last updated
- 2025-07-26
← All NanoGPT listings