LongCat Flash Thinking 2601
by Vercel AI Gateway · family longcat · listed Jan 2026R
Efficient model for low-latency assistance, extraction, and routine automation
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
meituan/longcat-flash-thinking-2601- Context window
- 33K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-01-15
- Last updated
- 2026-03-13