Kimi K2.6 Thinking
by NanoGPT · family kimi-k2 · listed Apr 2026RTVW
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Current rates USD per 1M tokens
Input$0.50
Output$2.60
Cache read$0.125
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
moonshotai/kimi-k2.6:thinking- Context window
- 256K tokens
- Max output
- 66K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jan 2025
- Released
- 2026-04-21
- Last updated
- 2026-04-21
← All NanoGPT listings