Expired50% confidenceFactExact time
Domestically compliant large models such as Tongyi Qianwen, ERNIE Bot, Doubao, Kimi, and DeepSeek can all be accessed directly.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/19/2026(expired)
Sources
Related Claims
Unverified简单技术问答可直接用豆包或DeepSeek，操作浏览器等场景选MCP，工程级代码生成用Claude Code，本地化离线需求用Ollama等本地部署方案67% similarUnverifiedThe practical workflow in this article uses four MCP Servers—AutoNavi Maps, LeetCode, What to Eat Today, and Zhisou—corresponding respectively to the four scenarios of travel planning, study and problem-solving, dietary recommendations, and news information.62% similarUnverifiedA hands-on tutorial recommends the domestically available toolchain combination of VS Code + JRM + Qwen for use in China.62% similarUnverifiedThe training corpora of large language models typically include Common Crawl web data, books, academic papers, open-source code repositories, and content from Q&A platforms such as Stack Overflow, with knowledge compressed into parameters through self-supervised learning (predicting the next token).61% similarUnverified该工具提供Token用量查看功能，用户需自行配置对话模型和生图模型60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/575697API
curl https://kongchang.com/api/v1/knowledge/claims/575697MCP
get_claim(id=575697)