Transparent pricing
Choose your plan
Start free. Pay only for what you use.
Starter
$4
$5
/month
billed yearly
Great for individual developers
- 25,000 compressions/month
- 10 API keys
- 5 projects
- Email support
- +1K requests addon β $0.50
POPULAR
Pro
$8
$10
/month
billed yearly
For power users and growing projects
- 60,000 compressions/month
- 50 API keys
- 20 projects
- Priority support
- +1K requests addon β $0.40
Team
$16
$20
/user
billed yearly
For growing teams with per-seat billing
- 125,000 compressions/seat/month
- Team dashboard
- Priority support
- Min 3 / Max 15 seats
- +1K requests addon β $0.25
Agentic
Optimized for AI agents and high-volume automation
3,000,000 compressions/month
Optimized for AI agents
Lowest per-request cost
Priority support
SLA 99.5%
+1K addon β $0.15
$299
$239
/month
billed yearly
Enterprise
For large organizations with custom needs
On-premise option
24/7 support
Custom integrations
+1K addon β $0.20
Custom Pricing
Contact Us
Frequently Asked Questions
A token is a unit of text for LLMs. On average, 1 token β 4 characters in English. OpenAI and Anthropic charge per token for both input and output text.
TokenCompress uses the Qwen 1.5B model for semantic code compression. We remove comments, formatting, imports and keep only the essence β while preserving meaning for the LLM.
No. We don't store your code. Compression happens in real-time, data is not saved. For enterprise, On-Premise option is available β all processing within your infrastructure.
Yes, at any time. Subscription continues until the end of the paid period. Unused tokens expire at month end.
When you reach your limit, you'll receive a notification. You can purchase additional tokens at your plan's rate or upgrade. Service isn't cut off abruptly.