Usage-based pricing

Pay for usage, not overhead

Transparent pay-as-you-go pricing based on your raw token consumption. Pay the direct provider model cost plus a simple service fee only when routing requests.

5%

flat service fee

Scale dynamically with pay-as-you-go billing. Pay only for active traffic, with no subscription plans or procurement drag.

  • All models & providers
  • Zero fixed monthly costs
  • Full compliance from day one
  • Enterprise-grade SLAs

One Fee to unlock everything

5%service fee

No subscription plans, setup fees, or paywalls. One flat rate unlocks our entire suite.

EUR native billing
Pre-paid or Invoice
Auto Top-up

Compliance by default

Route requests through a secure, EU-sovereign gateway. We handle data residency, GDPR, and provider policies so you don't have to.

Spend clarity

Track token usage and request cost metadata directly. Control spend with dedicated budgets instead of guessing across separate provider dashboards.

No feature gating

The standard tier includes routing, provider selection, fallback, budgets, integrations, and all available model endpoints from day one.

Enterprise ready

For larger annual token spend, Cortecs provides procurement support, priority technical support, SLA coverage, and more upon request.

Models & Providers

150+ AI models
10+ EU providers

Routing & Reliability

Routing policies
Automatic fallbacks
Load balancing
Latency routing
Prompt caching

Security & Compliance

EU sovereign routing
EU data residency
GDPR compliance
SSO
Full RBAC
End-to-end ISO-27001

Teams & Access

Spend management
Groups & team management
Key management API

Developer Tooling

OpenAI compatible
Antrophic compatible
Embedding support
Audio support

Operational Support

Community support
Email support
Dedicated support
Upon Request
Support Level Agreement
Upon Request

Frequently Asked Questions

Do you support Support Level Agreements?

Enterprise SLAs are available on request for eligible customers above EUR 10K annual token spend, especially when procurement, invoicing, onboarding, contract review, or SLA coverage is needed. Please contact enterprise@cortecs.ai.

How is token usage priced?

Usage is based on the underlying provider and model cost, with the flat Cortecs service fee added on top. The model catalog remains the source for concrete token rates.

How exactly is service fee calculated?

The flat 5% fee is applied to the underlying cost of the tokens you consume from the provider. Cortecs does not mark up the base token prices, ensuring transparent pay-as-you-go pricing based purely on raw usage.

How do payments and the Auto Top-up system work?

Cortecs uses native EUR billing. Users can pre-pay via credit card and enable an "Auto Top-up" threshold to automatically add funds before the balance runs out, preventing unexpected API failures.

Can I set hard limits on how much my team spends?

Yes. The platform includes spend management features that allow you to set strict, dedicated budgets. This prevents cost overruns without requiring you to manually track spending across multiple separate AI provider dashboards.