Quick answer
Choose Tokens by use case and compatibility first, specs second; test locally when possible. A token is the model's basic text unit, not a character/word.
Why it matters
Stacked specs do not guarantee fit for your use case.
English is often ~4 chars/token.
Step by step
- Confirm the model context and output budget.
- Paste the prompt/document and estimate tokens/usage.
- Above 80-90%, split, summarize or retrieve.
- Count system prompts/tool schemas too.
- Verify billing/hard limits with the official tokenizer.
Common mistakes
- Treating character count as token count.
- Ignoring output/system prompt usage.
- Assuming all models use the same tokenizer.
- Stuffing a long document instead of retrieving/summarizing.
Checklist
- Model context confirmed.
- Output budget reserved.
- System/tool prompts counted.
- Long text retrieved/split.
- Critical cases checked with the official tokenizer.
Key facts
- English is often ~4 chars/token.
- Chinese is often 1-2 chars/token.
FAQ
How do I choose Tokens?
Choose Tokens by use case and compatibility first, specs second; test locally when possible. A token is the model's basic text unit, not a character/word.
How long does it take?
Usually 1-3 minutes; for intermittent issues, run 30 seconds and retest elsewhere.
Is data uploaded?
Runs locally and does not upload video/audio; extensions may still read the page.
Source: OpenAI tokenizer