Model ID
meituan-longcat/LongCat-Flash-Thinking
Capabilities
LongCat Flash Thinking
LongCat Flash Thinking is a 560B-parameter MoE reasoning model with 512 experts, activating 18.6-31.3B parameters per token. It uses a 28-layer transformer with 6,144 hidden size, 64 attention heads, and 131K context length. The design includes zero-computation experts and MLA attention. Trained via a two-phase pipeline, Long CoT cold-start and large-scale RL on the DORA system, it emphasizes formal reasoning, theorem proving, and agentic tool use, with domain-parallel RL improving stability and cross-domain performance.
About this model
LongCat Flash Thinking is a 560B-parameter MoE reasoning model with 512 experts, activating 18.6-31.3B parameters per token. It uses a 28-layer transformer with 6,144 hidden size, 64 attention heads, and 131K context length. The design includes zero-computation experts and MLA attention. Trained via a two-phase pipeline, Long CoT cold-start and large-scale RL on the DORA system, it emphasizes formal reasoning, theorem proving, and agentic tool use, with domain-parallel RL improving stability and cross-domain performance.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (meituan-longcat/LongCat-Flash-Thinking). Released under MIT. Further reading: Paper
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
B200
1,440 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on B200 · SGLang. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
NVIDIA HGX B200
Unlock Next-Generation AI Power on Vultr Cloud GPU