MeasureTokensContact

GPT-5.1 vs Claude Sonnet 4.5

Same prompt, two tokenizers: see live token counts, cost per request, and token boundaries side by side.

Try:

Counts include each model's own chat-template overhead.

128 chars

GPT-5.1

OpenAI · 400k context
…tokens

Claude Sonnet 4.5

Anthropic · 200k context
…tokens

At a glance

  • GPT-5.1: 400k-token context, $1.25/1M input · $10/1M output.
  • Claude Sonnet 4.5: 200k-token context, $3/1M input · $15/1M output.
  • Token counts differ between models because each vendor trains its own tokenizer vocabulary — the same text can split into more or fewer pieces. Prices as of 2026-07-07.

GPT-5.1 token counter →Claude Sonnet 4.5 token counter →Compare all models →