Instructions to use meituan-longcat/LongCat-Flash-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meituan-longcat/LongCat-Flash-Thinking with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="meituan-longcat/LongCat-Flash-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("meituan-longcat/LongCat-Flash-Thinking", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meituan-longcat/LongCat-Flash-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meituan-longcat/LongCat-Flash-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meituan-longcat/LongCat-Flash-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meituan-longcat/LongCat-Flash-Thinking

SGLang

How to use meituan-longcat/LongCat-Flash-Thinking with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "meituan-longcat/LongCat-Flash-Thinking" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meituan-longcat/LongCat-Flash-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "meituan-longcat/LongCat-Flash-Thinking" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meituan-longcat/LongCat-Flash-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meituan-longcat/LongCat-Flash-Thinking with Docker Model Runner:
```
docker model run hf.co/meituan-longcat/LongCat-Flash-Thinking
```

Add Arxiv link and Citation

by wjn1996 - opened Sep 24, 2025

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+17

-3

Files changed (1) hide show

README.md +17 -3

README.md CHANGED Viewed

@@ -38,7 +38,7 @@ tags:
 </div>
 <p align="center">
-  <a href="https://github.com/meituan-longcat/LongCat-Flash-Thinking/blob/main/tech_report.pdf"><b>Tech Report</b>&nbsp;📄</a>
 </p>
@@ -77,7 +77,7 @@ After high-value query selection, we synthesize corresponding high-quality
 solution trajectories based on a versatile environment with diverse tool APIs,
 including MCP servers and simulated tools for both single and multi-turn interactions.
-For more details, please refer to the comprehensive [**LongCat-Flash-Thinking Technical Report**](https://github.com/meituan-longcat/LongCat-Flash-Thinking/blob/main/tech_report.pdf).
 ## Evaluation Results
@@ -210,7 +210,7 @@ Please reason step by step, and put your final answer within \\boxed{}. /think_o
 #### Formal Reasoning
-LongCat-Flash-Thinking also support formal reasoning, like automatic theorem proving (ATP). The specific template is:
 ```text
 [Round 0] USER:Think about and solve the following problem step by step in Lean 4.
@@ -245,6 +245,20 @@ It is the responsibility of developers and downstream users to understand and co
 Nothing in this Model Card should be interpreted as altering or restricting the terms of the MIT License under which the model is released.
 ## Contact
 Please contact us at <a href="mailto:longcat-team@meituan.com">longcat-team@meituan.com</a> or join our WeChat Group if you have any questions.

 </div>
 <p align="center">
+  <a href="https://arxiv.org/abs/2509.18883"><b>Tech Report</b>&nbsp;📄</a>
 </p>
 solution trajectories based on a versatile environment with diverse tool APIs,
 including MCP servers and simulated tools for both single and multi-turn interactions.
+For more details, please refer to the comprehensive [**LongCat-Flash-Thinking Technical Report**](https://arxiv.org/abs/2509.18883).
 ## Evaluation Results
 #### Formal Reasoning
+LongCat-Flash-Thinking also supports formal reasoning, like automatic theorem proving (ATP). The specific template is:
 ```text
 [Round 0] USER:Think about and solve the following problem step by step in Lean 4.
 Nothing in this Model Card should be interpreted as altering or restricting the terms of the MIT License under which the model is released.
+## Citation
+We kindly encourage citation of our work if you find it useful.
+```
+@misc{meituan2025longcatflashthinkingtechnicalreport,
+    title={LongCat-Flash-Thinking Technical Report},
+    author={Meituan},
+    year={2025},
+    eprint={2509.18883},
+    archivePrefix={arXiv},
+    primaryClass={cs.AI},
+    url={https://arxiv.org/abs/2509.18883},
+}
+```
 ## Contact
 Please contact us at <a href="mailto:longcat-team@meituan.com">longcat-team@meituan.com</a> or join our WeChat Group if you have any questions.