Getting Started
Cortiqa is a powerful AI platform that provides state-of-the-art language models through a simple, developer-friendly API. Build intelligent applications with natural language understanding, generation, and reasoning capabilities.
Cortiqa provides access to a family of large language models (LLMs) designed for a wide range of tasks including text generation, analysis, code writing, reasoning, and multimodal understanding. Our models are available through a REST API that can be integrated into any application.
Whether you are building a chatbot, automating document processing, generating code, or creating content, Cortiqa models deliver high-quality results with industry-leading safety and reliability.
Generate human-quality text for any use case from creative writing to technical documentation.
Write, debug, and explain code in 20+ programming languages with high accuracy.
Analyze complex data, documents, and scenarios with advanced reasoning capabilities.
Process and understand images, documents, and mixed media inputs alongside text.
Connect models to external tools, APIs, and databases for real-time information access.
Stream responses token-by-token for real-time, responsive user experiences.
To start using the Cortiqa API, you will need to:
# Python
pip install cortiqa
# TypeScript / Node.js
npm install @cortiqa/sdk
# Go
go get github.com/cortiqa-ai/cortiqa-sdk-goHere is a minimal example of making an inference request using the official Cortiqa Python SDK:
1from cortiqa import Cortiqa23# Initialize client (reads CORTIQA_API_KEY environment variable)4client = Cortiqa()56response = client.chat.completions.create(7 model="openai/gpt-oss-120b",8 messages=[9 {"role": "system", "content": "You are a helpful AI assistant created by Cortiqa."},10 {"role": "user", "content": "Explain quantum computing in simple terms."}11 ]12)1314print(response.choices[0].message.content)This sends a message to the openai/gpt-oss-120b model and prints the response. The API supports streaming, system prompts, function calling, and high-throughput inference.