Unverified50% confidenceFactExact time
GPT-4所使用的cl100k_base词表包含约10万个Token单元，对中文单字的覆盖率相对较低
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
VerifiedGPT-4o supports a context window of 128K Tokens, capable of processing approximately 100,000 Chinese characters.83% similarVerifiedThe cl100k_base vocabulary used by GPT-4 contains approximately 100,000 token units, and the number of tokens in a text can be precisely calculated using the tiktoken library.81% similarVerifiedThe GPT-4 series uses the cl100k_base vocabulary (approximately 100,000 tokens), while the GPT-4o series upgrades to o200k_base (approximately 200,000 tokens).78% similarVerifiedGPT-4 uses a vocabulary of approximately 100,000 tokens.78% similarUnverifiedGPT-4 系列上下文窗口最高支持约 10 万汉字76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488710API
curl https://kongchang.com/api/v1/knowledge/claims/488710MCP
get_claim(id=488710)