Kimi K2 0711 Instruct FP4
by NanoGPT · family kimi-k2 · listed Jul 2025
Kimi model for long-context chat, coding, and agentic reasoning
Current rates USD per 1M tokens
Input$0.10
Output$2.00
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
baseten/Kimi-K2-Instruct-FP4- Context window
- 128K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-07-11
- Last updated
- 2025-07-11
← All NanoGPT listings