Chatbox is a free, open-source desktop AI client (Windows / macOS / Linux) that talks to any OpenAI-compatible endpoint. It's the fastest way to put NovAI's Chinese models into a polished chat app — with conversation history, prompt templates, and file uploads — without writing a line of code.
https://aiapi-pro.com/v1glm-5.3, kimi-k2.7-code, qwen3.8-max, deepseek-v4-pro — or fetch the full live list from the /v1/models endpoint if your Chatbox version supports it.glm-4.7-flash chat for daily questions and a glm-5.3 session for deep work.glm-4.1v-thinking-flash (free) or glm-4.6v.cogview-3-flash (free) or doubao-seedream-5.0 through the images endpoint.Every request deducts from your NovAI balance in real time. A typical heavy chat day on kimi-k2.7-code costs well under a dollar — check the dashboard usage panel any time.
| Model | Input $/1M | Output $/1M |
|---|---|---|
| kimi-k2.7-code (agent-tuned) | $0.67 | $3.40 |
| glm-5.3 (1M context flagship) | $1.25 | $4.00 |
| deepseek-v4-pro | $0.57 | $1.15 |
| doubao-seed-2.0-code | $0.448 | $2.24 |
| glm-4.7-flash (free forever) | $0 | $0 |
For long agent loops, kimi-k2.7-code and deepseek-v4-pro give the best cost-per-task; for repo-wide refactors that need the full codebase in context, glm-5.3's 1M window is unmatched. Use free glm-4.7-flash for planning and lightweight edits.
A desktop chat with 40+ Chinese models — $2 free credit, four models free forever.
In Chatbox Settings > Model Provider, add an 'OpenAI API Compatible' provider with API host https://aiapi-pro.com/v1 and your NovAI API key, then add model ids like glm-5.3 or kimi-k2.7-code.
Yes. glm-4.7-flash (chat), glm-4.1v-thinking-flash (vision), cogview-3-flash (images) and cogvideox-flash (video) are free forever - Chatbox works with all of them through the same configuration.
Chatbox stores conversations locally on your device. Only the active request content is sent to the model API - through NovAI's gateway to the official Chinese provider endpoint.