Platform
Cortiqa operates on a transparent, pay-as-you-go token model with no upfront seat fees. You only pay for the exact input prompt and output reasoning tokens you consume.
Track real-time token volume, daily burn rate, and latency breakdowns directly from the Billing & Usage Dashboard. New accounts receive starter developer credits to experiment and build immediately.
| Model | Context Window | Input Tokens (per 1M) | Output Tokens (per 1M) | Status |
|---|---|---|---|---|
GPT-OSS 120B (openai/gpt-oss-120b) | 131K tokens | $0.15 | $0.60 | Active / Live |
Falin 01 (falin-01) | 128K tokens | Free / Starter Tier | Free / Starter Tier | Coming Soon |
Falin Pro (falin-pro) | 200K tokens | Pro Tier | Pro Tier | Coming Soon |
Protect against runaway recursive agent loops or unexpected traffic surges by configuring hard and soft budget caps in the console:
429 RateLimitExceeded / BudgetExceeded error once the monthly cap is reached.For organizations processing high token volumes, Cortiqa provides dedicated LPU node leasing, custom discount tiers, and monthly invoicing (ACH, wire transfer, net-30 payment terms).
Contact our engineering team directly at team@cortiqa.co to request dedicated throughput provisioning.