Sign in

v1

latestOpenAPI 3.1.0MIT2026-07-13174391.2 KB

Compress chat history and code context by removing irrelevant lines at 33,000 tok/s. Every surviving line is byte-for-byte identical to the original input. Accepts string input or message arrays.

post/v1/compact

Request body

inputstring

Text to compact. One of input or messages is required.

querystring

Focus query for relevance-based pruning. Lines relevant to this query are kept.

compression_rationumber

Fraction of input to keep. 0.3 = aggressive, 0.7 = light.

preserve_recentinteger

Keep last N messages uncompressed.

compress_system_messagesboolean

When true, system messages are also compressed. By default they are preserved verbatim.

include_line_rangesboolean

Include compacted_line_ranges in response.

include_markersboolean

Include (filtered N lines) text markers. When false, gaps become empty lines.

modelstring

Model ID.

Example request

{
  "input": "def hello():\n    return 1\n\ndef unused():\n    pass\n\ndef world():\n    return 2",
  "messages": [
    {
      "role": "user",
      "content": "Help me build a Node.js API with JWT auth"
    }
  ],
  "query": "hello function",
  "compression_ratio": 0.5,
  "include_line_ranges": true,
  "include_markers": true,
  "model": "morph-compactor"
}

Response

Compact response with compressed output and metadata

idstring required

Unique identifier for the compact request

objectstring required

Object type

modelstring required

Model used

outputstring required

All compacted messages joined into a single string

Example response

{
  "id": "cmpr-7373faf8af65",
  "object": "compact",
  "model": "morph-compactor",
  "output": "def hello():\n    return 1\n(filtered 3 lines)\ndef world():\n    return 2",
  "messages": [
    {
      "role": "user",
      "content": "def hello():\n    return 1\n(filtered 3 lines)\ndef world():\n    return 2",
      "compacted_line_ranges": [
        {
          "start": 4,
          "end": 6
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 101,
    "output_tokens": 65,
    "compression_ratio": 0.644,
    "processing_time_ms": 109
  }
}