Verified90% confidenceFactExact time
The 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).
6
Sources
90%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Codex配置实战：国内低成本接入GPT-5.5完整教程
bilibilidream黎6/7/2026
Related Claims
VerifiedGPT-4 uses a vocabulary of approximately 100,000 tokens.81% similarVerifiedOpenAI's GPT series increments by integer version numbers (GPT-3, GPT-4) and uses letter suffixes to distinguish variants, such as "o" representing the optimized version (GPT-4o) and "mini" representing the lightweight version80% 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.79% 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78% similarUnverifiedcl100k_base is the specific vocabulary used by models such as GPT-4 and text-embedding-ada-002.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/186578API
curl https://kongchang.com/api/v1/knowledge/claims/186578MCP
get_claim(id=186578)