Verified80% confidenceFactExact time
The 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.
8
Sources
80%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Otari：开源LLM控制平面工具全面解析
hackernewshackernews7/6/2026
Related Claims
VerifiedGPT-4 uses a vocabulary of approximately 100,000 tokens.84% 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).79% similarVerifiedOpenAI has used a variant of BPE since GPT-2, and GPT-4's cl100k_base vocabulary contains approximately 100,000 tokens.78% similarUnverifiedOpenAI's GPT series uses the tiktoken library, with vocabulary sizes typically ranging between 50,000 and 100,000 Tokens77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/217854API
curl https://kongchang.com/api/v1/knowledge/claims/217854MCP
get_claim(id=217854)