Pricing

You save money every single time. At $0.05 per 1M saved tokens, compression always costs a fraction of what your LLM charges — so every API call is cheaper with us.

$0.05per 1M saved tokens

You only pay for done work

You send in 500 tokens. We remove 200 redundant ones and return 300 compressed tokens. You only pay for the 200 tokens we removed — at $0.05 per 1M tokens.

Available models

All models are priced the same — pick the one that fits your needs.

ModelReleased
bear-1November 2025
bear-1.1January 2026
bear-1.2February 2026

Example

Acme Corp sends 10B tokens per week to Gemini 3 Pro Preview ($2 / 1M input tokens) and achieves 75% compression with bear-1.1.

LLM cost before compression$20,000/wk
LLM cost after compression$5,000/wk
Compression API cost$375/wk
Net savings$14,625/wk · $63,326/mo

Estimate your savings

Adjust the inputs to match your usage.

LLM cost before compression$80,000
LLM savings from compression−$52,800
Compression API cost+$1,320
Total cost after compression$28,520
You save64%$51,480/mo

Performance benchmarks

Compression doesn't just save money — it improves accuracy and latency.

financial QA

Making LLMs understand financial documents better

Compression improved financial QA accuracy by 2.7 percentage points on 150 SEC filing questions — while reducing input tokens by up to 20%.

February 2026

E2E latency

Reducing LLM response times through compression

Up to 37% faster on Claude Opus 4.6 and 30% on GPT-5.2 — saving seconds per request across 5 input sizes.

February 2026

reading comprehension

Improving LLM reading comprehension with compression

Compression improved SQuAD 2.0 accuracy by 4.0 percentage points on 150 reading comprehension questions — with 17% fewer tokens.

March 2026

conversational QA

Zero accuracy loss on conversational QA with 14% fewer tokens

Compression maintained 87.3% accuracy on 150 multi-turn CoQA questions across 4 domains — with 14% fewer tokens.

March 2026

More benchmarks coming soon

We are evaluating compression across additional domains and model families. Results will be published here as they are completed.

Start compressing

Start saving on your LLM costs

Free to try. No credit card required.

Start compressingTalk with us