LongCat Flash

meituan

LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce communication overhead and achieve high throughput while maintaining training stability through advanced scaling strategies such as hyperparameter transfer, deterministic computation, and multi-stage optimization. This release, LongCat-Flash-Chat, is a non-thinking foundation model optimized for conversational and agentic tasks. It supports long context windows up to 128K tokens and shows competitive performance across reasoning, coding, instruction following, and domain benchmarks, with particular strengths in tool use and complex multi-step interactions.

Try Now

Example Use Cases

Agentic multi-step interaction

Long-context conversational task

Tool use with large moe model

Technical Specifications

Context Window

131,072 tokens

Max Output

32,768 tokens

Cache Miss Cost

$0.20 per 1M tokens

Non-Reasoning Cost

$0.80 per 1M tokens

Cache Read Cost

$0.20 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus