Unverified50% confidenceFactExact time
The 128K in GPT-4 128K refers to a context window size of 128,000 tokens, roughly equivalent to 100,000 English words or 50,000–60,000 Chinese characters.
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGPT-4的上下文窗口从8K扩展到128K乃至百万级别，上下文窗口越大每次调用消耗的令牌越多75% similarUnverified早期Codex的上下文窗口约为4096个token，对应大约150-300行代码；GPT-4系列将这一限制扩展至128K token75% similarUnverified128K长度的序列所需的注意力计算量是4K长度序列的1024倍69% similarUnverifiedA 200K context window means approximately 150,000 lines of Python code can be input at one time.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/854273API
curl https://kongchang.com/api/v1/knowledge/claims/854273MCP
get_claim(id=854273)