---
id: "meituan/longcat-2.0"
also: ["meituan/longcat-2.0-20260720", "meituan-longcat/LongCat-2.0"]
cheapest_list_usd_per_m: "0.3 in, 1.2 out, at atlas-cloud/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.0253 in, 1.1998 out, at atlas-cloud/fp8 on openrouter"
context: 1048756
max_output: 262144
input: ["text"]
output: ["text"]
released: "2026-07-20"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 1
coding: 45.3000
agentic: 14
---
# Meituan: 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...