Unverified70% confidenceFactExact time
推理型模型（如DeepSeek R1）强制要求格式化输出会干扰其内部推理过程导致性能下降，这是R1不支持Function Calling和JSON Output的根本原因
1
Sources
70%
Confidence
Long-term
Relevance
5/27/2026
First Seen
Sources
Why Qwen3 Is the Best Open-Source Model for MCP Agent Development
bilibili大模型姗姗5/27/2026
Related Entities
Related Claims
UnverifiedThe DeepSeek R1 reasoning model does not support Function Call, and Dify will automatically switch to ReAct mode.78% similarUnverifiedUsing DeepSeek R1 directly in agent development will likely produce errors such as 'Structured output not supported' or 'Function Calling not supported'.75% similarVerifiedDeepSeek R1（DeepSeek-Reasoner）不支持Function Calling、JSON Output和FIM（聊天补全）三个功能74% similarUnverifiedForcing reasoning models to output structured formats interferes with their internal reasoning process and degrades performance.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1748API
curl https://kongchang.com/api/v1/knowledge/claims/1748MCP
get_claim(id=1748)