Meituan: LongCat Flash Chat

Text input Text output
Author's Description

LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce...

Key Specifications
Cost
$$$
Context
131K
Parameters
560B (Rumoured)
Released
Sep 09, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Seed Structured Outputs Min P Response Format Temperature Presence Penalty Tools Frequency Penalty Top P Stop Tool Choice Max Tokens Logit Bias
Features

This model supports the following features:

Structured Outputs Response Format Tools
Performance Summary

Meituan's LongCat Flash Chat, a 560B parameter Mixture-of-Experts model, demonstrates competitive response times, ranking in the 43rd percentile for speed across benchmarks. It offers cost-effective solutions, placing in the 67th percentile for price. Notably, the model exhibits exceptional reliability with a 99% success rate, indicating minimal technical failures. The model excels in foundational knowledge and ethical reasoning, achieving perfect 100% accuracy in Hallucinations, General Knowledge, and Ethics benchmarks, often at competitive price points and speeds. It also shows strong performance in Mathematics (96% accuracy) and Email Classification (99% accuracy). For more complex tasks, LongCat Flash Chat demonstrates solid capabilities in Instruction Following (75% accuracy) and Reasoning (80% accuracy), aligning with its optimization for conversational and agentic tasks. Its coding performance is moderate at 84% accuracy. Key strengths include its robust reliability, strong performance in knowledge-based and ethical tasks, and efficient handling of long context windows up to 128K tokens, making it well-suited for complex multi-step interactions and tool use.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $0.8
Input Cache Read $0.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AtlasCloud
AtlasCloud | meituan/longcat-flash-chat 131K $0.2 / 1M tokens $0.8 / 1M tokens
Chutes
Chutes | meituan/longcat-flash-chat 131K $0.2 / 1M tokens $0.8 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration