LongCat-Flash-Lite variant using LongCat Sparse Attention with native 1M-token context.
Released
Jul 31, 2026
Context window
1M tokens
Max output
Not disclosed
Parameters
69B 3B active
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Meituan
- Model type
- Text LLM
- Architecture
- MoE
- Parameters
- 69B (3B active)
- Input
- Text
- Output
- Text
- Knowledge cutoff
- Not disclosed
- License
- MIT License
- API access
- No first-party API
- Capabilities
- Long context