LongCat 2.0
LongCat 2.0 is a language model from Meituan. It is currently free at 1 provider with up to 1M tokens of context. The model supports step-by-step reasoning, supports tool calling. Its weights are open, so it can also run locally.
- Developer
- Meituan
- Context
- 1M tokens
- Type
- Text
- License
- Open weights
Where to use LongCat 2.0 for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
Nous Portal meituan/longcat-2.0:free |
1M | The $0 Portal plan includes free models with standard rate limits. Model availability can change. | No | Open |
Quick start
curl https://inference-api.nousresearch.com/v1/chat/completions \
-H "Authorization: Bearer $NOUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meituan/longcat-2.0:free",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://inference-api.nousresearch.com/v1",
api_key="YOUR_NOUS_API_KEY",
)
reply = client.chat.completions.create(
model="meituan/longcat-2.0:free",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://inference-api.nousresearch.com/v1",
apiKey: process.env.NOUS_API_KEY,
});
const reply = await client.chat.completions.create({
model: "meituan/longcat-2.0:free",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for Nous Portal. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · LongCat 2.0
Similar free models
FAQ
Is LongCat 2.0 free?
Yes. As of September 26, 2026, LongCat 2.0 is free at Nous Portal. Each provider has its own limits — see the table above.
What is the context window of LongCat 2.0?
The largest context among free routes is 1,048,756 tokens. Some providers cap it lower.
How do I call LongCat 2.0 via API?
Use any OpenAI-compatible client with base URL https://inference-api.nousresearch.com/v1, model ID meituan/longcat-2.0:free, and a Nous Portal key.
How good is LongCat 2.0?
Artificial Analysis Intelligence Index: 19.1, GPQA Diamond: 78%. For comparison, the strongest free model in the catalog right now is GLM 5.3.
Is LongCat 2.0 open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.