The #1 tool to optimize your LLM spend

A drop-in proxy that sends your model only the context it actually needs — for better answers, not just the same ones, at up to 90% lower cost per 1M tokens.

−70% cost
$3.00 / 1M tokens
$0.90 / 1M tokens

Estimate your own savings

Cost before$125.00/mo
Cost with CompresLM$37.50/mo
You save$87.50/mo

How it works

CompresLM sits in front of any LLM API. Before the request leaves, we strip noise and keep the parts that answer the task — then forward the leaner prompt to OpenAI, Claude, or your own model.

1. Point your SDK here

Change one line: the base URL. Keep your existing provider key.

2. We compress the context

Only the tokens that matter reach the model. Nothing else is stored.

3. Model answers as usual

Same response shape. Same tools. Lower bill — every single call.

Better than Netflix's internal tooling — on measured workloads

On a paired public-dataset benchmark (200+ cases, same document / same query / same model, run with and without compression), CompresLM matches the quality of uncompressed traffic while cutting the cost of the request — including on medical needle-fact retrieval, a shape of input where a leading internal compression stack showed ~0% savings.

New

RankAuto v2 is live — up to 90% lower cost on large, unstructured input: sprawling documents, log dumps, and tool-call results that otherwise flood the model's attention.

Cost per 1M input tokens

List price vs. price with CompresLM, same benchmark

Shorter indigo bar = you pay less for the same 1M tokens sent to that model.

Quality held

Across needle, negation, multi-hop & log-search categories — answer-quality score (0–1)

0.70Uncompressed
0.71CompresLM

The two rings are nearly identical — CompresLM answered at least as well, and edged slightly ahead on average, while cost dropped 7–31% on the same cases.

Compression by workload

Real per-category results, 200+ paired test cases

Indigo — quality held automatically, this is what you get by default.
Amber — a deeper-compression ceiling; the router only uses it when the safe path can't apply.

200+
paired test cases
Up to 90%
lower cost per 1M tokens
↑ quality
less attention noise

One line to install

Works exactly like calling OpenAI, Claude, or a local LLM directly.

# Python — OpenAI SDK
client = OpenAI(
    base_url="https://compreslm.com/v1",
    api_key="YOUR_COMPRESLM_TOKEN",
    default_headers={"X-LLM-API-Key": "YOUR_PROVIDER_KEY"},
)

We never store your provider key. It rides with each request and is discarded after the call.

Your data stays yours

CompresLM is a proxy. We process the request, forward it, and return the response. We do not keep your prompts or completions as a product dataset.

Pricing that can only save you money

Free to start

First 1 million tokens processed — free. No card required.

After that: pay 20% of what you saved. If we save you $100, you pay $20. You keep $80.

Local / self-hosted LLMs

When there is no public token price, we charge a flat $0.50 per 1M tokens saved. Transparent, written out on the billing page.

What it costs across providers

Measured on this benchmark's compression — actual savings scale with how compressible your traffic is, up to 90%.

ModelList price / 1M inWith CompresLM
GPT-4o mini$0.15$0.084
GPT-4o$2.50$1.41
Claude Sonnet$3.00$1.69
Self-hosted / local$0.50 per 1M tokens saved — no list price to compare against

Want on-prem or a custom plan? We help set it up — free. Talk to us.

Contact

On-prem setup, a custom plan, or a question — leave a note and we'll get back to you.

Start saving today

Try free. First 1M tokens on us. Then only 20% of what you save.

Create your account