longcat-2.0 · Meituan
Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.
Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.
Longcat 2.0 has a 1,000,000 token context window. It supports up to 131,072 output tokens.
On AIHubMix, Longcat 2.0 costs $0.775 per million input tokens and $3.098 per million output tokens. Cached input reads are billed at $0.015 per million tokens.
Longcat 2.0 accepts text input.
Longcat 2.0 supports thinking and tool calling. Per-protocol parameter support is listed in the capability table on this page.
Longcat 2.0 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to longcat-2.0 — no other code changes needed.
Longcat 2.0 is developed by Meituan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Longcat 2.0 was released on June 30, 2026 by Meituan.
Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an…
Use Longcat 2.0 via the AIHubMix unified API — one interface for every major LLM.