Cherry Studio Setup: GLM, Kimi, Qwen, Free Vision & Image Models (2026)

Published 2026-09-13 · NovAI Team

Cherry Studio is the power-user's open-source AI desktop client: multi-provider, multi-assistant, knowledge bases, MCP support, and mini-apps — all against any OpenAI-compatible endpoint. Pointing it at NovAI gives one interface for the entire Chinese model zoo: chat, vision, image generation, and translation assistants side by side.

Setup

  1. Install Cherry Studio from cherry-ai.com (or your package manager) and open Settings → Model Provider.
  2. Click Add Provider. Name it NovAI, choose type OpenAI.
  3. API URL: https://aiapi-pro.com/v1
  4. API Key: your NovAI key (create one in the dashboard).
  5. Click Manage Models → Add and register the ids you use, e.g. glm-5.3, kimi-k2.7-code, qwen3.8-max, glm-4.1v-thinking-flash, cogview-3-flash. (Cherry Studio can also pull the live list from /v1/models.)

Recommended assistant layout

AssistantModelWhy
Daily chatglm-4.7-flashFree forever, fast
Deep work / long docsglm-5.31M context
Codingkimi-k2.7-codeAgent-tuned, $0.67/1M in
Image analysis / OCRglm-4.1v-thinking-flashFree visual reasoning
Image generationcogview-3-flash / doubao-seedream-5.0Free tier or 2K quality at $0.027
Translationqwen3.5-flash$0.048/1M in, high volume

Knowledge bases and MCP

Cherry Studio's knowledge-base feature embeds documents against your chosen provider — use cheap qwen3.5-flash or deepseek-v4-flash ($0.08/$0.17) for embedding-heavy ingestion, then answer with glm-5.3. MCP servers configured in Cherry Studio work unchanged since tool-calling flows through the same OpenAI-compatible API.

Best NovAI models for coding agents

ModelInput $/1MOutput $/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.

One desktop client, 40+ Chinese models — $2 free credit, four free forever.

Get $2 Free Credit — No Credit Card →

Frequently Asked Questions

How do I add NovAI to Cherry Studio?

In Settings > Model Provider, add a provider of type OpenAI with API URL https://aiapi-pro.com/v1 and your NovAI API key, then add model ids manually or fetch them from the /v1/models endpoint.

Can Cherry Studio generate images through NovAI?

Yes. Add cogview-3-flash (free forever) or doubao-seedream-5.0 ($0.027/image) and use Cherry Studio's drawing assistants; note Chinese image models burn a visible AI-generated label into output.

Which models should I use for Cherry Studio knowledge bases?

Use a cheap model like qwen3.5-flash for ingestion and retrieval-heavy chats, and glm-5.3 with its 1M context for answering over large document sets.

Related guides: Codex CLI setup · Claude Code · Cline / Roo Code · Cursor · Chatbox · Cherry Studio