Resources

Frequently Asked Questions

Common questions about the Cortiqa API, pricing, models, and platform.

General

What is Cortiqa?

Cortiqa is an AI platform that provides state-of-the-art language models through a developer-friendly API. Our models can generate text, analyze data, write code, process images, and more.

How do I get started?

Create a free account at platform.cortiqa.co, generate an API key, and follow our Quickstart guide.

Pricing

Is there a free tier?

Yes, new accounts receive free developer credits to test API endpoints. No credit card required.

How is pricing calculated?

Pricing is based on tokens processed (input + output). See the Models page for current pricing ($0.15/1M in · $0.60/1M out on GPT-OSS 120B).

Are there volume discounts?

Yes, enterprise customers can negotiate custom throughput quotas and dedicated LPU nodes. Contact team@cortiqa.co for details.

Technical

What is the maximum context window?

GPT-OSS 120B supports a 131,072 token context window, with Falin 1 expanding to 200,000+ tokens.

Do you store my prompts or data?

By default, we retain API inputs and outputs for 30 days for abuse monitoring. Enterprise customers can opt out of data retention entirely. See Data Privacy.

What is the API uptime SLA?

We target 99.9% uptime for all API endpoints. Enterprise plans include a 99.99% SLA with financial credits for downtime.

Safety

How do you prevent harmful outputs?

We use multi-layered content filtering including trained classifiers, rule-based filters, and human review for edge cases. See Content Filtering.

Can I use Cortiqa for my specific use case?

Review our Usage Policy for allowed and prohibited uses. Contact us if your use case is not clearly covered.