AI article
111, 133, 172: The Same 192 Characters in Three Tokenizers
Community description: The same 192-character prompt is 111 DeepSeek tokens, 133 o200k_base and 172 cl100k_base. Where the 55% spread comes from, and why Claude and Gemini counts are estimates.
Dev.to | Nov 3, 2026 | WGG
Automated excerpt
Same 192 characters: 111 tokens in DeepSeek V4, 133 in o200k_base, 172 in cl100k_base. Above 272,000 input tokens, gpt-5.5 and GPT-6 price the whole request at 2× input and 1.5× output; Gemini moves above 200,000. Four characters per token remains fine for English sanity checks.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.