LongCat 2.0

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

ChatMeituan1M tokens$0.327 / $1.3081 · 1M

meituan/longcat-2.0

Context
1M tokens
Completion cap
262,144
Tools
Yes
JSON
No
Released
2026-07-20

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meituan/longcat-2.0",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is LongCat 2.0?
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows. LongCat 2.0 runs on the Geek Hub API (OpenAI-compatible). Model id: meituan/longcat-2.0.
Is LongCat 2.0 free?
No. Input is $0.327 per 1M tokens and output is $1.3081 per 1M tokens on Geek Hub (markup included).
What is the context length of LongCat 2.0?
LongCat 2.0 has a 1M tokens context window. It supports up to 262,144 completion tokens.
Does LongCat 2.0 support tool calling and structured outputs?
LongCat 2.0 accepts tools and tool_choice for function calling. Structured outputs are not listed for this endpoint.
When was LongCat 2.0 released?
LongCat 2.0 was released on 2026-07-20.