For example, use Prompt optimization for sharing/archiving: back up, export to the target format and spot-check 2-3 files. Shorter prompts, less irrelevant context and capped output often cut cost faster than switching models.
Why it matters
Real scenarios expose problems better than abstract specs.
Remove irrelevant context.
Step by step
- Measure input, output and retry tokens per user/task.
- Separate cache, batch, embeddings and fine-tuning costs.
- Use 30 days of real requests for cost per user, then margin.
- Model prices change; baseline from official pricing pages and record the date.
Common mistakes
- Estimating from input tokens only; output often costs more.
- Forgetting retries, failures and tool calls.
- Assuming cache hits by default.
- Using stale prices for long-term margin.
Checklist
- Input/output/cache/retry tokens are tracked separately.
- Batch/async fit and latency requirements are clear.
- Embeddings/fine-tuning/image/audio are separate.
- Cost per user and margin use real usage.
- Price date and fallback model are documented.
Key facts
- Remove irrelevant context.
- Cap output.
- Cache repeated parts.
FAQ
Can you show a Prompt optimization example?
For example, use Prompt optimization for sharing/archiving: back up, export to the target format and spot-check 2-3 files. Shorter prompts, less irrelevant context and capped output often cut cost faster than switching models.
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