Unverified50% confidenceFactExact time
OpenAI和Anthropic均明确指出，判断模型真实身份的唯一可靠方式是通过官方API返回的模型标识符（model ID），而非模型在对话中的自我描述
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Claude Fable 5是真的吗？深度分析与真伪辨别指南
bilibiliAI未来20306/11/2026
Related Claims
UnverifiedAnthropic and OpenAI follow a closed-source model where users can only access models through APIs without access to model parameters72% similarUnverified当模型ID已写入注册表但权限策略尚未对外开放时，外部用户的API调用会收到'模型未识别'的响应71% similarUnverifiedIn OpenCode, the Model ID must exactly match the model name on the platform for correct configuration71% similarUnverifiedOpenAI提供strict:true与response_format:json_schema参数，可从数学上保证模型不输出枚举值之外的意图结果68% similarUnverifiedOpenAI Agents只适配OpenAI自家模型，不支持其他模型的接入67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/61372API
curl https://kongchang.com/api/v1/knowledge/claims/61372MCP
get_claim(id=61372)