LongCat 2.0
General purposeToolsMeituan · Released July 2026
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.
It is part of Meituan's open-weight LongCat line.
Facts and pricing
- Provider
- Meituan
- Context window
- 1.0M tokens
- Input price
- 3.6 credits / 1M tokens ($0.30 raw)
- Output price
- 14.4 credits / 1M tokens ($1.20 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try LongCat 2.0 now
What LongCat 2.0 is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a general purpose model like LongCat 2.0:
- Help me outline a talk about what I learned this year
- Compare these two paragraphs and tell me which is clearer and why
- Draft a polite reply declining this invitation
- Explain this concept with a concrete everyday analogy
Frequently asked questions
- What is LongCat 2.0?
- LongCat 2.0 is an AI model by Meituan. LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.
- How much does LongCat 2.0 cost on Zeplik?
- Input tokens cost 3.6 credits per million and output tokens 14.4 credits per million (1 credit = $0.10; the raw provider rates are $0.30 and $1.20 per million). New accounts start with free credits.
- How long can a conversation with LongCat 2.0 be?
- LongCat 2.0 has a 1.0M-token context window (1,048,756 tokens), which covers the conversation plus any documents you attach.
- Does LongCat 2.0 support images and tools?
- LongCat 2.0 is text-only and supports tool calling.
Related models
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks.
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
More you can do with LongCat 2.0
- 467 AI skillsReady-to-run expert methods for writing, data, code and more, each running on LongCat 2.0 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.