Created
May 7, 2026 18:34
-
-
Save joswr1ght/8d0f3b1b604c4d4f83bd20ce47465ee8 to your computer and use it in GitHub Desktop.
Count tokens for one or more files
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| # /// script | |
| # dependencies = [ | |
| # "tiktoken", | |
| # ] | |
| # /// | |
| import sys | |
| import tiktoken | |
| def count_tokens(filepath, model="gpt-4"): | |
| """Count tokens in a file using the specified model's encoding.""" | |
| encoding = tiktoken.encoding_for_model(model) | |
| with open(filepath, 'r') as f: | |
| text = f.read() | |
| tokens = encoding.encode(text) | |
| return len(tokens) | |
| if __name__ == "__main__": | |
| if len(sys.argv) < 2: | |
| print("Usage: python counttokens.py <file> [file]", file=sys.stderr) | |
| sys.exit(1) | |
| total = 0 | |
| for filepath in sys.argv[1:]: | |
| try: | |
| token_count = count_tokens(filepath) | |
| total += token_count | |
| except FileNotFoundError: | |
| print(f"Error: File '{filepath}' not found, skipping", file=sys.stderr) | |
| continue | |
| except Exception as e: | |
| print(f"Error: {e}, skipping file", file=sys.stderr) | |
| continue | |
| print(f"\nTotal token count: {total}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment