Meituan: Longcat-Flash-Lite
Longcat-Flash-Lite is a language model from Meituan released on Feb 6, 2026. It reads text and writes text, with a 256K token context window and up to 320K tokens per reply.
Show moreShow less
It supports tool calling.
- Modalities
- In / out price
- n/a
- Context
- 256K
- Max output
- 320K
- Released
- Feb 6, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Supported request parameters
What you can set when you call Longcat-Flash-Lite through an OpenAI compatible API.
- Tools
tools - Temperature
temperature
More from Meituan
- 1M context
Reads text and images. Tool calling, reasoning. Served by 2 providers.
by meituanSep 25, 2026$0.75/M input tokens$2.95/M output tokens2 providers
- 1M context
Reads text. Tool calling. Served by 5 providers.
by meituanJun 30, 2026$0.75/M input tokens$3/M output tokens5 providers
- 131K context
Reads text.
by meituanNov 5, 2025
Longcat-Flash-Lite questions
What is the context window of Longcat-Flash-Lite?
256,000 tokens of input, and it can write up to 320,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Does Longcat-Flash-Lite support tool calling?
Yes. It accepts tool definitions, which is what an agent needs to call your APIs.
Is Longcat-Flash-Lite open source?
No. Meituan serves it through an API only, so you cannot download the weights or host it yourself.
When was Longcat-Flash-Lite released?
Feb 6, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.