LongCat-Flash-Chat

Overview

LongCat-Flash-Chat is documented in the meituan-longcat GitHub repository and is listed in the publisher API documentation. The model is the same entity referenced in both sources.

Documented capabilities

The statements below are described in the cited primary documentation. They describe what the cited documentation says the model is, not an independent performance evaluation.

• General conversational AI with 560B total parameters (MoE).
• Per-token dynamic activation of 18.6B–31.3B parameters (averaging ~27B).
• 256K context window (upgraded December 2025 from 128K).
• Strong agentic tool use performance: τ²-Bench 73.68, VitaBench 24.30.
• Instruction following: IFEval 89.65, COLLIE 57.10.
• 100+ tokens per second inference speed on H800 GPUs.
• Deployable via SGLang and vLLM; FP8 and BF16 precision variants available.
• Multilingual support across 9 languages including Spanish, French, Arabic, Portuguese, and Russian.

Access and license

MIT License. Permits commercial use, modification, redistribution, and model distillation.

Documented context window: 256,000 tokens (per the cited publisher API documentation).

Independent-site notes

This profile is a source-based summary. It does not contain any benchmark, evaluation, or quality claim produced by this site.

No independent testing has been published by this site.

Any performance figures attributed to the model in third-party materials are vendor-reported and have not been independently verified on this site.

Sources

• LongCat-Flash Technical Report (arXiv:2509.01322)

  Primary source · Published 2025-09-01 · Accessed 2026-07-26

  Technical report detailing the ScMoE architecture, Zero-Computation Experts mechanism, and training framework. Reports inference at >100 TPS on H800 and a training cost of $0.70 per million output tokens.

• LongCat-Flash-Chat GitHub Repository

  Primary source · Accessed 2026-07-26

  Primary repository under MIT License. Contains model configuration, chat template, and deployment instructions for SGLang and vLLM.

• LongCat-Flash-Chat on HuggingFace

  Primary source · Accessed 2026-07-26

  Model weights in BF16 and FP8 precision. Model card includes publisher-reported benchmark scores across general domains, coding, math, and agentic tool use.

• Meituan Official Announcement for LongCat-Flash-Chat

  Publisher documentation · Published 2025-08-29 · Accessed 2026-07-26

  Publisher press release confirming MIT License, H800 inference benchmark of >100 TPS, PID controller for expert bias, and output cost of approximately 5 RMB per million tokens.

Related guides

• LongCat API Quick Start

  A primary-source-based introduction to creating a LongCat API key and sending a basic chat completion request through the OpenAI-compatible endpoint.

FAQ

What is LongCat-2.0?

LongCat-2.0 is a model documented in the meituan-longcat GitHub organization and listed in the publisher API documentation.

Where can the primary source for LongCat-2.0 be found?

The meituan-longcat GitHub repository is the primary source. The repository contains the model code, configuration, and license file.

Does LongCat-2.0 have a documented API?

Yes. The publisher API documentation lists LongCat-2.0 as a supported model on both OpenAI-compatible and Anthropic-compatible endpoints.

Is this page an official LongCat or Meituan page?

No. This page is published by an independent third-party site that summarizes publicly-available primary documentation. It is not affiliated with, endorsed by, or sponsored by LongCat or Meituan.