Core Concepts

Models

Cortiqa offers a family of models optimized for different use cases. Choose the right model based on your needs for intelligence, speed, and cost.

Cortiqa Model Family

Cortiqa provides high-throughput AI reasoning endpoints optimized for agentic workflows and production inference:

Model	Identifier	Context	Speed	Status
GPT-OSS 120B	`openai/gpt-oss-120b`	131K tokens	Ultra-Fast (LPU)	Active
Falin 1	`cortiqa/falin-1`	200K tokens	High Throughput	Coming Soon

Model	Input (per 1M tokens)	Output (per 1M tokens)
GPT-OSS 120B (`openai/gpt-oss-120b`)	$0.15	$0.60
Falin 1 (`cortiqa/falin-1`)	To be announced	To be announced

Developer Credits

New accounts receive free developer credits to test API endpoints in Playground and production.

Use GPT-OSS 120B for production reasoning, autonomous tools, high-speed coding, and agent pipelines with ultra-low latency.
Use Falin 1 (releasing soon) for multimodal deep research, vision tasks, and large-scale document synthesis.

Use these model identifiers in your API requests:

Model IDs

# Active Flagship Model
openai/gpt-oss-120b

# Upcoming Multimodal Architecture
cortiqa/falin-1

Was this page helpful?