Text Compressor
TextCompressor compresses LLM prompts automatically before they reach your model — removing stop words, filler phrases, and redundant tokens while preserving meaning. Works as a drop-in proxy: point your existing OpenAI client at api.textcompressor.unmutedlive.com and add your X-TC-Key header. No other code changes needed. Tested across 11,760 prompts: - Light: 16.7% token savings, -2.7pp…
2 subscribers
413 ms avg latency
8% success rate
5 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Text Compressor endpoints
| Method | Endpoint | Description |
|---|---|---|
| compress | ||
| POST |
compressText /compress |
Compress a string or OpenAI message list. Returns the compressed text with token savings statistics. No LLM call is made. |
| v1 | ||
| GET |
getUsage /v1/usage |
|
| POST |
chatCompletions /v1/chat/completions |
Drop-in replacement for OpenAI /v1/chat/completions. Compresses user messages before forwarding to your upstream LLM. Your LLM API key goes in the standard Authorization header… |
| GET |
listModels /v1/models |
Forwards the models list request to the upstream API unchanged. |
| health | ||
| GET |
healthCheck /health |
Returns server status. No authentication required. |
Text Compressor pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO Recommended | $29 / month | — |
|
| ULTRA | $99 / month | — |
|
| MEGA | $499 / month | — |
|
