MeasureTokensContact

GPT-4o vs Claude Haiku 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-4o

OpenAI · 128k context
…tokens

Claude Haiku 4.5

Anthropic · 200k context
…tokens

At a glance

  • GPT-4o: 128k-token context, $2.5/1M input · $10/1M output.
  • Claude Haiku 4.5: 200k-token context, $1/1M input · $5/1M 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-4o token counter →Claude Haiku 4.5 token counter →Compare all models →