Sends the CompresLM token below + your provider key (header X-LLM-API-Key).
Compresses the request, then forwards it to your provider — your key is used once, never stored.
Answers as usual, billed to your own account. Response is relayed back unchanged.
Full setup guide with code samples: Quickstart docs →
Loading…
Free tier exhausted. Request more tokens to keep going.
# Generate a token first
Sends this prompt to gpt-4o-mini-smart using your token above +
the provider key you paste below (used once for this test, not stored). The reply shown
is exactly what your provider returned — CompresLM only edits what goes in, not what comes back.
Full docs · Billing · Terms · Privacy · Contact / on-prem
Self-serve card billing isn't wired up yet. Send us a note — we'll unlock more tokens for your account by hand, usually the same day.