Expired50% confidenceFactExact time
OpenAI's GPT series uses the tiktoken tokenizer, while Anthropic's Claude uses a proprietary tokenizer.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Cursor Pay-Per-Use Billing Explained: How Account Pool Scheduling Reduces Usage Costs
bilibiliyoyo自动化6/23/2026
Related Claims
UnverifiedClaude uses the tool_use format defined by Anthropic, the GPT series uses OpenAI's function_calling protocol, and there is no unified industry standard for tool calling in large language models.78% similarUnverifiedThe GPT series (OpenAI) and Claude (Anthropic) are closed-source models.74% 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% similarUnverifiedGPT系列使用tiktoken分词器，LLaMA系列使用SentencePiece分词器72% similarUnverifiedThe GPT series is trained by OpenAI primarily on English internet corpora using an autoregressive architecture72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41671API
curl https://kongchang.com/api/v1/knowledge/claims/41671MCP
get_claim(id=41671)