All models
Meituan

LongCat 2.0

meituan/longcat-2.0

LongCat 2.0 is a sparse mixture-of-experts model from Meituan with 48B active parameters out of 1.6T total, built for coding, repository-level changes, long-horizon problem solving, and agentic workflows.

Pricing

Input$0.3per 1M tokens
Output$1.20per 1M tokens

Specifications

Context window1.05Mtokens
Max output66Ktokens
ProviderMeituan
CapabilitiesReasoning · Function calling
Input typestext

Use LongCat 2.0

Point your existing OpenAI SDK at xKiro and pass meituan/longcat-2.0 as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="meituan/longcat-2.0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

Call LongCat 2.0 through the same endpoints you already use.

Get an API key