Paste a prompt to count tokens and price it across GPT-4o, GPT-4.1, and the mini/nano models. See per-call and monthly cost, and the cheapest model for the job.
Want exact counts + auto-compression inside your editor? Install the free MCP server: npx -y mcp-token-optimizer — see how →
Paste it above for an instant estimate. Roughly, 1 token ≈ 4 characters or about ¾ of a word in English.
Approximate: GPT-4o ~$2.50 input / $10 output per 1M; GPT-4o-mini ~$0.15 / $0.60. The calculator prices your exact prompt — confirm on OpenAI's pricing page.
Trim prompts, cache repeated calls, and use mini/nano models where quality allows. The free mcp-token-optimizer server automates this in your editor.
More free calculators: Claude · Cursor · ChatGPT · guides · home