Meituan LongCat 2.5 official release is free on OpenCode Zen, 100 requests a day!
LongCat 2.5 official release free for a limited time, 100 requests/day, ~1M context
OpenCode Zen added a free tier for Meituan LongCat 2.5, the official release. Input, output, and cache reads cost nothing, with a limit of 100 requests per day. It supports about one million tokens of context and image input. The provider keeps zero data and does not train on your requests. Free chat models must be used through OpenCode, and no end date has been announced.
- Eligibility
- Any OpenCode account; free chat models must be used through the OpenCode client
- Benefit duration
- Limited-time free, no end date announced yet
The briefing
OpenCode Zen added a free tier for Meituan LongCat 2.5 (model ID longcat-2.5-free), free for a limited time. This is the official release from November 2, not the earlier Preview.
What you can use
Anyone with an OpenCode account can pick it. Input, output, and cache reads are billed at $0, with a limit of 100 requests per day. It has about one million tokens of context and up to roughly 262K output tokens, takes text and image input, supports tool calls, and lets you toggle reasoning.
The provider follows a zero-retention policy and does not train on your data. The model is hosted in China. Free-tier chat models must be used through OpenCode. The free period has no published end date yet.
How to use it
- Open OpenCode, sign in, and switch to LongCat 2.5 Free with
/models, or set the model toopencode/longcat-2.5-freein your config. - For the API, use
https://opencode.ai/inference/openai/v1/chat/completionswith modellongcat-2.5-free.
More details: OpenCode Zen docs.