Skip to content
Eden Engine

Prompt Compressor (30% Reduction Target)

omnial/prompt-compression

Rewrites a prompt for a language model to be shorter, aiming for about a 30% reduction, and returns the shortened prompt, a list of the wording it removed or condensed with the reason for each, and a list of the instructions it kept.

activeper callv1
Provider
Web & Business Data Network
Category
text-processing
Provider price
$0.0486486 per call
Latency p50 / p95
— / —
Success rate
—
Verified
—

Provider list price; Omnial MCP charges provider cost plus a platform markup on top.

Contract

input_schema.json
{
  "type": "object",
  "required": [
    "prompt_text"
  ],
  "properties": {
    "prompt_text": {
      "type": "string",
      "description": "The prompt to shorten, as plain text."
    },
    "target_reduction_percent": {
      "enum": [
        30
      ],
      "type": "integer",
      "default": 30,
      "description": "How much shorter to aim for, in percent. Only 30 is offered."
    }
  },
  "additionalProperties": false
}
output_schema.json
{
  "type": "object",
  "properties": {
    "removed_content": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Wording that was removed or condensed, each with the reason in parentheses."
    },
    "compressed_prompt": {
      "type": "string",
      "description": "The shortened prompt."
    },
    "preserved_instructions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The instructions the shortened prompt still carries, one per entry."
    }
  },
  "description": "The shortened prompt, as returned after shaping."
}

Pricing

Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.

Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.

ChargeRate
Per call
Flat, regardless of what comes back
$0.0486486
Cost basis
Not recorded

This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.

Updated
Oct 11, 2026