Pricing
All compression models are billed at the same rate.
$0.05per 1M saved tokens
Available models
| Model | Price | Released |
|---|---|---|
| bear-1 | $0.05 / 1M saved tokens | November 2025 |
| bear-1.1 | $0.05 / 1M saved tokens | January 2026 |
| bear-1.2 | $0.05 / 1M saved tokens | February 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$375.00/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.
More benchmarks coming soon
We are evaluating compression across additional domains and model families. Results will be published here as they are completed.
Meanwhile, try our API for freeStart saving on your LLM costs
Free to try. No credit card required.