How billing works

Transparent by design. You never pay more than you save on priced models.

Free tier

Every account gets 1,000,000 tokens processed free (counted as tokens we see before compression). No card required to start. When the limit is hit, API calls return 402 free_tier_exhausted. Self-serve payment is on the way — until then, open your dashboard and tell us you'd like to keep going and we'll unlock more tokens manually.

Hosted models with a known price

OpenAI, Anthropic, and other priced APIs:

our_fee = 20% × (cost_without_compression − cost_with_compression)

Example: without CompresLM a call would cost $1.00; with CompresLM it costs $0.60. You saved $0.40. Our fee is $0.08. You keep $0.32.

Local / self-hosted LLMs

When there is no public token price (vLLM, Ollama, private endpoints), we cannot compute a dollar delta from the provider. Instead:

our_fee = $0.50 × (tokens_saved / 1,000,000)

This rate is shown in the dashboard and in the setup instructions whenever you choose a local upstream (X-LLM-API-Base).

What we never do

Store provider keys

Your upstream key is per-request only.

Charge before savings

Fee is a share of measured savings.

Hide the formula

Numbers on the dashboard use these rules.

On-prem & custom plans

Want CompresLM inside your VPC, or a compression profile tuned to your traffic? We help set that up for free. Prefer a personal plan? Same form.

Contact us

Self-serve payment

Card checkout isn't wired up yet. Once the free tier runs out, the dashboard shows a short form instead — tell us you'd like to keep going and we'll unlock more tokens for your account by hand. Card billing is next.