Count tokens for Gemini 2.5 Pro, Flash, and Flash-Lite using Google's own token counting API, with a GPT comparison and cost estimate alongside.
We do not store your text. It is counted and discarded immediately.
-
-
0
Gemini 2.5 Flash
Through Google's official countTokens API, so the numbers match exactly what the Gemini API bills you for. The GPT column uses OpenAI's open o200k tokenizer for comparison.
Every model family uses its own tokenizer. The same text usually splits into a different number of tokens on Gemini than on GPT or Claude, which matters when you compare per-token prices across vendors.
Gemini 2.5 Flash bills $0.30 per million input tokens and Gemini 2.5 Pro bills $1.25 per million (rising to $2.50 for prompts over 200K tokens), per Google's published pricing. The tool shows the input cost of your pasted text for the selected model.
It is sent to Google's counting endpoint to get the exact number and discarded immediately. We store nothing.
MemoryPlugin gives Gemini, ChatGPT, Claude, and 20+ other AI tools one shared long-term memory and a searchable chat history. Tell one AI something once, and the rest have it from your next conversation.
Try MemoryPlugin free