Unverified50% confidenceFactExact time
早期Codex模型（2021年）的上下文窗口仅有4K Token，约相当于200行代码
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedEarly Codex had a context window of only approximately 4K tokens, allowing it to handle only single-file-level code comprehension tasks.83% similarVerifiedEarly large language models only supported context windows of 4K–8K tokens, while current mainstream models have expanded to 100K or even 200K tokens.74% similarUnverified早期模型的上下文窗口限制为4K tokens73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/539021API
curl https://kongchang.com/api/v1/knowledge/claims/539021MCP
get_claim(id=539021)