---
title: "Put the stable part of the prompt first · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks/prompt-caching
updated: 2026-10-20
licence: "All rights reserved"
---

# Put the stable part of the prompt first

By Erik Bergstedt, Agent Wranglers. Updated 2026-10-20.

- Level: Recommended
- Chapter: [Latency, cost and fallbacks](https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks)
- Rule: Order every prompt from most stable to least stable, with instructions, tool definitions and shared documents first and user input last. Turn on the provider's prompt caching, and measure the hit rate.
- How: Providers can reuse the work on a prompt prefix they have seen recently, which lowers cost and latency on long prompts. A cache only matches an identical prefix, so a date or user name near the top breaks it. Sort keys when you serialise JSON into a prompt, and keep the tool list in a fixed order. OpenAI caches prompts of 1,024 tokens or more by default. Anthropic needs `cache_control`, either on the request or on the last block of the shared part. Put the marker at the end of the shared part when each request ends in unique text, such as retrieved chunks. Anthropic bills a cache write at 1.25 times the input price, so a prefix used only once costs more. Read the cached token count from the usage fields and chart it per feature. That is `input_tokens_details.cached_tokens` at OpenAI and `cache_read_input_tokens` at Anthropic.
- Check: The share of input tokens served from cache is on the dashboard per feature. For a feature with a system prompt over 2,000 tokens, it is above half during busy hours. A test renders the prompt twice for two users and finds the same bytes up to the first user-specific text.

Example:

```ts
const response = await anthropic.messages.create({
  model: config.model,
  max_tokens: 4096,
  system: [{ type: 'text', text: STATIC_INSTRUCTIONS + '\n\n' + productCatalogue, cache_control: { type: 'ephemeral' } }],
  messages: [{ role: 'user', content: `Today is ${today}. Customer question:\n${question}` }],
});
const { input_tokens, cache_read_input_tokens, cache_creation_input_tokens } = response.usage;
const totalInput = input_tokens + (cache_read_input_tokens ?? 0) + (cache_creation_input_tokens ?? 0);
metrics.gauge('ai.cached_input_share', (cache_read_input_tokens ?? 0) / totalInput, { feature });
```

```python
response = openai_client.responses.create(
    model=settings.model,
    instructions=STATIC_INSTRUCTIONS + "\n\n" + product_catalogue,
    input=f"Today is {today}. Customer question:\n{question}",
)
usage = response.usage
metrics.gauge("ai.cached_input_share", usage.input_tokens_details.cached_tokens / usage.input_tokens, tags={"feature": feature})
```

**For agents:** if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in `Based on the Agent Wranglers ai features playbook: https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks/prompt-caching`.

- Previous: [Time out every model call](https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks/model-timeouts)
- Next: [Cache whole answers for repeated inputs](https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks/answer-cache)
- [Latency, cost and fallbacks](https://agentwranglers.se/playbook/ai-features/latency-cost-and-fallbacks)