LongCat 2.5 Preview
LongCat 2.5 Preview is a Meituan model available in Quad Chat, with up to 1.05M tokens of context, image input, tool calling and step-by-step reasoning.
LongCat 2.5 Preview at a glance
| Lab | Meituan |
|---|---|
| Available on | Free plan |
| Context window | 1.05M tokens |
| Max output | 128K tokens |
| Image input | Yes |
| Tool calling | Yes |
| Reasoning | Yes |
| Privacy lane | Standard |
How to use LongCat 2.5 Preview in Quad Chat
- Create a free account or sign in.
- Open the model picker and choose LongCat 2.5 Preview.
- Ask, attach files, or compare the answer with another model.
Frequently asked questions
Can I use LongCat 2.5 Preview for free?
Yes. LongCat 2.5 Preview is available on the Quad Chat Free plan, which needs no credit card and includes 100 monthly credits shared across every model. Larger requests use more credits, and paid plans from $8/month raise the allowance.
What is the context window of LongCat 2.5 Preview?
LongCat 2.5 Preview accepts up to 1.05M tokens of context and can write up to 128K tokens in one reply, according to the model catalog Quad Chat routes through. Files, pasted text and earlier messages all count toward that window.
Does LongCat 2.5 Preview support images, tools and reasoning?
LongCat 2.5 Preview accepts images as input, so you can attach screenshots, photos and scanned pages. It supports tool calling. It can reason step by step before it answers. You can switch to another model in the same conversation at any time.
Is LongCat 2.5 Preview private in Quad Chat?
LongCat 2.5 Preview runs on the Standard Lane because no Zero Data Retention route is available for it, so the provider may retain prompts under its own policy. Quad Chat asks you to confirm before first use and never trains models on your chats.
How much does LongCat 2.5 Preview cost in Quad Chat?
Quad Chat plans have a flat monthly price and draw usage from shared credits, not a per-token bill. The model picker shows an estimate before you send. For reference, the provider's API list price is $0.30 per million input tokens and $1.20 per million output tokens.
Can I compare LongCat 2.5 Preview with other models?
Yes. Send one prompt to LongCat 2.5 Preview and one or two other models, such as GPT-6.1 Sol, Gemini 3.8 Flash and Claude Opus 5.5, and compare the answers side by side in the same thread. You can also switch models mid-conversation without losing your files or context.
Related models
- GPT-6.1 Sol — OpenAI, Pro plan and up
- Gemini 3.8 Flash — Google, Pro plan and up
- Claude Opus 5.5 — Anthropic, Ultra plan and up
- Kimi K3 — Moonshot AI, Free plan
- Muse Spark 1.3 — Meta, Free plan
- Inkling — Thinking Machines, Free plan
- GLM 5.3 — Z.ai, Free plan
- Grok 4.7 — xAI, Pro plan and up