LongCat 2.5 Free - Free 1M Context Model on OpenCode, China-Hosted
LongCat 2.5 Free - Free 1M Context Model on OpenCode, China-Hosted
Model ID
opencode/longcat-2.5-free
OpenCode client only. This is an OpenCode free-tier model and cannot be called directly through a standard OpenAI-compatible API; direct requests to the inference endpoint return 403
FreeTierError.Model Information
| Attribute | Value |
|---|---|
| Context length | 1,000,000 tokens |
| Max output | 262,144 tokens |
| Input modalities | Text, image |
| Input price | $0 / 1M tokens |
| Output price | $0 / 1M tokens |
| Provider | Meituan LongCat |
| Status | Free for a limited time (OpenCode client only, 100 RPD) |
Description
LongCat 2.5 Free is a multimodal reasoning model from Meituan’s LongCat team, designed for long-horizon coding and agent tasks, with visual understanding and a 1 million token context. The model is suited to cross-file code understanding, long-document analysis, visual coding, and multi-step automation; the free tier is hosted in China with zero data retention and is not used for training.
Usage Example
Select it directly in OpenCode:
opencode run --model opencode/longcat-2.5-free "Analyze this architecture diagram and generate an implementation plan"Or pin it in opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"model": "opencode/longcat-2.5-free"
}Notes
- Client restriction: The free tier is only available inside the OpenCode client and cannot be called through the API directly
- Daily limit: The LongCat 2.5 free tier is limited to 100 requests per day; the OpenCode free tier also has a separate undisclosed shared cap
- Limited-time free: May become paid or be removed at any time
- Data terms: Zero retention, not used for model training; hosted in China
Related Links
📚 Related Free Models
These models are also available for $0 on OpenCode. Choose by context length and modality.
| Model | Context | Description |
|---|---|---|
| DeepSeek V4.1 Flash | 200K | DeepSeek V4.1 Flash free edition with 200K context, 32K |
| GLM-5.3-Flash | 200K | Zhipu AI’s GLM-5.3-Flash free edition with 200K context, |
| MiniMax M3.1 Flash | 1M | MiniMax M3.1 Flash free edition with 1M context, 512K |
📋 View all OpenCode free models →
🔗 Site Navigation
Last updated on
· Source: OpenCode official documentation and pricing pages. Quotas and prices may change at any time.