Prompt Compression

Shorten a prompt towards a requested reduction while aiming to preserve its meaning. Returns the shorter text and estimated savings.

Pay by wallet (x402) AI-generated prompt-compress

Example

Example answer

{
  "original_tokens": 14,
  "removed_content": [
    "This is a test",
    "for"
  ],
  "compressed_prompt": "Automated capability testing input.",
  "compressed_tokens": 9,
  "preserved_instructions": [
    "Identify this as test input",
    "Recognize it's for automated capability testing"
  ],
  "actual_reduction_percent": 36
}

Inputs

Field	Type	Required	What it is
`prompt_text`	string	Yes	—
`target_reduction_percent`	integer	No	Default 30

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`original_tokens`	integer	Always (present in every successful answer)
`compressed_prompt`	string	Always (present in every successful answer)
`compressed_tokens`	integer	Always (present in every successful answer)
`actual_reduction_percent`	integer	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "prompt-compress",
    "inputs": {
      "prompt_text": "You are a helpful AI assistant. Please help me write a comprehensive function that validates email addresses using a robust regex pattern, handling edge cases like internationalized addresses, plus-sign addressing, and subdomain TLDs."
    },
    "max_price_cents": 3
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "prompt-compress",
    "inputs": {
      "prompt_text": "You are a helpful AI assistant. Please help me write a comprehensive function that validates email addresses using a robust regex pattern, handling edge cases like internationalized addresses, plus-sign addressing, and subdomain TLDs."
    },
    "max_price_cents": 3
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "prompt-compress",
  inputs: {
    "prompt_text": "You are a helpful AI assistant. Please help me write a comprehensive function that validates email addresses using a robust regex pattern, handling edge cases like internationalized addresses, plus-sign addressing, and subdomain TLDs."
  },
  max_price_cents: 3,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="prompt-compress",
    inputs={
        "prompt_text": "You are a helpful AI assistant. Please help me write a comprehensive function that validates email addresses using a robust regex pattern, handling edge cases like internationalized addresses, plus-sign addressing, and subdomain TLDs.",
    },
    max_price_cents=3,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i 'https://api.strale.io/x402/v2/prompt-compress?prompt_text=You+are+a+helpful+AI+assistant.+Please+help+me+write+a+comprehensive+function+that+validates+email+addresses+using+a+robust+regex+pattern%2C+handling+edge+cases+like+internationalized+addresses%2C+plus-sign+addressing%2C+and+subdomain+TLDs.'

Limitations

Compression can remove important context
Compression may remove context that appears redundant but is semantically important for specific AI tasks
What to do instead: Test compressed prompts against your original to verify output quality is maintained before switching