# Chinese AI Models in Claude Code and Cursor via MCP (2026)

Source: https://aiapi-pro.com/blog/chinese-ai-models-in-claude-code-cursor-mcp-2026

Remote MCP server (read-only, no auth): https://aiapi-pro.com/api/mcp
Tools: cheapest_models, model_price, list_categories.
Registry: io.github.vvvvking/novai-prices (official MCP Registry); listed under Aggregators in
punkpeye/awesome-remote-mcp-servers.

Claude Code:
    claude mcp add --transport http novai-prices https://aiapi-pro.com/api/mcp

Cursor (~/.cursor/mcp.json):
    {"mcpServers":{"novai-prices":{"url":"https://aiapi-pro.com/api/mcp"}}}

VS Code (.vscode/mcp.json):
    {"servers":{"novai-prices":{"type":"http","url":"https://aiapi-pro.com/api/mcp"}}}

Claude Desktop:
    {"mcpServers":{"novai-prices":{"command":"npx","args":["-y","mcp-remote","https://aiapi-pro.com/api/mcp"]}}}

Snapshot of cheapest paid options (list price, unit as published in the feed, 2026-10-23):
- Chat/LLM: Hunyuan MT2 Lite $0.043 flat
- Image: Wan 2.2 T2I Flash $0.0215 per generation
- Video: Seedance 2.0 Fast $0.054 flat
- 3D: Hunyuan 3D Motion $0.185 per generation
- Audio: Qwen3 TTS Flash $0.0145 flat
- Embedding: Kinfra Text Embedding 0.6B $0.0769 flat

Free models: GLM-4.7-Flash, GLM-4.6V-Flash, GLM-4.1V-Thinking-Flash, CogView3-Flash, CogVideoX-Flash
(free tier: 10 free-model calls/day, 5 req/min, no card).

Inference: OpenAI-compatible endpoint https://aiapi-pro.com/v1 with a key from /free.
Policy: /transparency.json (0% platform fee, 1.0x multiplier). Feed: /china-ai-leaderboard.json (daily).