Quick answer
Quick answer: back up the original, pick the right format/settings, run a small batch, spot-check the output. Prompt caching can save money, but hit rules vary by provider.
Why it matters
Get the shortest path working before optimizing.
Stable prefixes hit more often.
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
- Stable prefixes hit more often.
- Caching does not change hard limits.
FAQ
What is the quick answer for Caching?
Quick answer: back up the original, pick the right format/settings, run a small batch, spot-check the output. Prompt caching can save money, but hit rules vary by provider.
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: Anthropic caching