Quick answer
Choose a Code tool by three things: local processing, controllable output and clear failures. Code indentation/symbols/identifiers add tokens.
Why it matters
A success/failure-only tool cannot help you isolate the cause.
JSON/HTML have many symbols.
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
- JSON/HTML have many symbols.
- Minifying/removing comments saves tokens.
FAQ
Which Code tool should I use?
Choose a Code tool by three things: local processing, controllable output and clear failures. Code indentation/symbols/identifiers add tokens.
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