Point Cherry Studio at Pareto's OpenAI-compatible API to run GLM 5.3 Flash, DeepSeek V4.1 Flash and MiMo V2.6 Flash on Pareto GPUs. Pay per token from one prepaid balance.
Setup
Get an API key in the dashboard, then add this to your chat app.
Open Settings → Model Provider → Add Provider, then Sync models. Also set the Quick Model to Pareto, or titles go to Cherry's own service.
Cherry StudioProvider
- Name
- Pareto Inference
- API key
- Your Pareto API key
- OpenAI URL
https://api.paretoinference.com- Model
z-ai/glm-5.3-flash
Models