---
title: "Compress"
method: POST
path: "/compress/raw/"
---

# Compress

`POST /compress/raw/`

Compress a prompt and context to reduce token usage while preserving semantic meaning.

## Request body

- object
  - `context` string, required — Background information, instructions, or supporting text that provides context for the prompt.
  - `prompt` string, required — The main query or question to send to your AI model.
  - `scaledown` object, required
    - `rate` string, required — Compression aggressiveness. Use 'auto' or a number between 0 and 1 (e.g. '0.5').

## Response `200`

Successful compression

- object
  - `compressed_prompt` string
  - `original_prompt_tokens` number
  - `compressed_prompt_tokens` number
  - `successful` boolean
  - `latency_ms` number
  - `request_metadata` object
    - `compression_time_ms` number
    - `compression_rate` union
      - string
      - number
    - `prompt_length` number
    - `compressed_prompt_length` number

## Other responses

- `400` — Malformed request body or missing required fields.
- `401` — Missing or invalid x-api-key.
- `429` — Rate limit exceeded.
- `500` — Compression service unavailable.

---

[API](https://skmtc.dev/scaledown/apis/scaledown-api.md) · [All operations](https://skmtc.dev/scaledown/apis/scaledown-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/scaledown/scaledown-api/revisions/4289049c3ecd/schema)