Unverified50% confidenceFactExact time
The same Hindi sentence requires 21 tokens under GPT-4's tokenizer but only 5 tokens under GPT-4o (o200k_base).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/1/2026
First Seen
Valid until: 1/30/2027
Sources
Related Entities
Related Claims
VerifiedThe 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% 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 version77% similarVerifiedIn the GPT series of models, one token corresponds to approximately 4 English characters or 0.75 English words.75% similarUnverifiedThe context limit in the GPT-4 era was 8,192 tokens.74% similarUnverifiedGPT-4的tiktoken分词器中，一个英文单词平均对应1.3个token，每个汉字约占2-3个token74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124161API
curl https://kongchang.com/api/v1/knowledge/claims/1124161MCP
get_claim(id=1124161)