Meituan: LongCat 2.0

by Meituan Coding Agentic Open Weight Long Context

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.

Choose a model to compare against LongCat 2.0

Specifications

Specifications for LongCat 2.0
AttributeValue
Lab Meituan
Tags Coding Agentic Open Weight Long Context
Release Date 2026-07
Context Window 1,048,756 tokens
Input Price / 1M $0.30
Output Price / 1M $1.20
Input Modalities Text
Output Modalities Text

Strengths

  • Million-token context window for very long tasks
  • Low input pricing for cost-sensitive production workloads
  • Tool-use support for agentic workflows

Weaknesses

  • Newer listing with limited independent benchmark coverage
  • Text-only inputs limit multimodal application coverage

Best For

  • Agentic workflows and tool-using applications
  • Long-context document and codebase processing

In Depth: LongCat 2.0

Summary

LongCat 2.0 is an AI model from Meituan.

Released 2026-07. It supports Text input and produces Text output, with a context window of 1,048,756 tokens. Input pricing is $0.30 per 1M tokens and output is $1.20 per 1M tokens on OpenRouter.

Sources & Further Reading

Related Models