# JEGA LLM Token Shrinker

> JEGA LLM Token Shrinker is a paid API for AI agents from api.jega.digital, paid per call via x402, $0.001/call, status down (last checked 2026-09-15).

Deterministically compresses raw text to reduce token count for LLM context windows

## Facts

- Endpoint: POST https://api.jega.digital/api/compress
- Price: $0.001/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-jega-digital-99649da8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_g7q0DWkO8_0qoOz1Xcsfx

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability api-jega-digital-99649da8 -d '<json body>'
```

Example prompt: Can you compress this text to shrink its token count before I send it to the LLM: 'The quarterly earnings report for fiscal year 2024 demonstrates significant revenue growth across all major business segments, particularly in the cloud infrastructure and enterprise software divisions, which together accounted for nearly sixty percent of total consolidated revenue'?

## When to prefer this

Use this endpoint when you need to deterministically reduce token usage before sending text to an LLM, especially in cost-sensitive pipelines, RAG ingestion workflows, or when fitting content into tight context windows. Prefer this over semantic summarization when you need consistent, repeatable compression rather than AI-generated paraphrasing.

## Known failure modes

- Missing or empty raw_text field returns validation error
- Extremely long input may exceed processing limits
- Non-text or binary input may produce unexpected output
- Payment failure via x402 protocol results in 402 response

## How this service works

Deterministic LLM Token Shrinker.

## Output

Returns a compressed version of the input text with reduced token count, preserving semantic meaning while minimizing characters and tokens consumed in an LLM context window.

## Example request

```json
{
 "raw_text": "The quarterly earnings report for fiscal year 2024 demonstrates significant revenue growth across all major business segments, particularly in the cloud infrastructure and enterprise software divisions, which together accounted for nearly sixty percent of total consolidated revenue"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "raw_text": {
   "type": "string",
   "description": "The raw text string to compress"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "engine",
  "status",
  "metrics",
  "compressed_text"
 ],
 "properties": {
  "engine": {
   "type": "string"
  },
  "status": {
   "type": "string"
  },
  "metrics": {
   "type": "object",
   "required": [
    "savings_percentage",
    "original_estimated_tokens",
    "compressed_estimated_tokens"
   ],
   "properties": {
    "savings_percentage": {
     "type": "string"
    },
    "original_estimated_tokens": {
     "type": "number"
    },
    "compressed_estimated_tokens": {
     "type": "number"
    }
   }
  },
  "compressed_text": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-jega-digital-99649da8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.jega.digital](https://www.zero.xyz/host/api.jega.digital/llms.txt)