AI token counter
Count tokens and estimate the API cost of a prompt for GPT, Claude, and Gemini models.
Runs in browser
Use from your agent
Streamable HTTP at https://benchline.fabwaseem.com/mcp. No key. The tool name is count_tokens.
mcp.jsonjson
1{
2 "mcpServers": {
3 "benchline": {
4 "url": "https://benchline.fabwaseem.com/mcp"
5 }
6 }
7}
tools/calljson
1{
2 "jsonrpc": "2.0",
3 "id": 1,
4 "method": "tools/call",
5 "params": {
6 "name": "count_tokens",
7 "arguments": {
8 "text": "example",
9 "encoding": "o200k",
10 "modelIds": [
11 "gpt-6.1-sol",
12 "claude-sonnet-5-5",
13 "gemini-4-argon"
14 ],
15 "outputTokens": 0,
16 "cachedRatio": 0,
17 "requestsPerDay": 0
18 }
19 }
20}
Related tools
- JSON-LD schema generatorFill a form, get valid schema.org JSON-LD for Article, FAQ, Product, Organization, and more.SEOMCPNew
- llms.txt generatorRead a public sitemap and write an llms.txt index, plus an optional llms-full.txt.AI searchMCP
- JWT decoderPaste a JSON Web Token, read the claims, and verify the signature in the browser.Auth debuggingMCP
- Cron expression builderBuild or paste a cron schedule, read it in plain English, and see the next run times.CronMCPNew
How it works
Free LLM token counter and API cost calculator. Paste text to count tokens with OpenAI's tokenizers and estimate input and output cost across GPT, Claude, Gemini, and other models.
- 01
Paste your prompt or file
Drop a .txt, .md, or .json file, or paste the prompt. The count updates in the browser.
- 02
Pick models and expected output
Choose the models to compare, set the output tokens you expect back, and the cached-input share.
- 03
Compare cost per request and per month
The table prices input and output separately. Copy it as markdown when you want to keep the estimate.