Unverified50% confidenceFactExact time
o200k_base is the tokenizer OpenAI introduced for the GPT-4o series, with a vocabulary of about 200,000, and its compression efficiency for multilingual (especially non-English) text is clearly better than the earlier cl100k_base.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe international version of Coze has integrated OpenAI's GPT-4 128K model, supporting a context window of up to 128,000 tokens, which is approximately equivalent to 100,000 English words or 50,000–60,000 Chinese characters.76% similarPartially VerifiedOpenAI's tiktoken expanded from the 50,000-token vocabulary of the GPT-2 era to the 100,000-token vocabulary of GPT-4.73% similarUnverifiedOpenAI's GPT series uses the tiktoken library, with vocabulary sizes typically ranging between 50,000 and 100,000 Tokens72% 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).72% similarUnverifiedGPT-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72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021873API
curl https://kongchang.com/api/v1/knowledge/claims/1021873MCP
get_claim(id=1021873)