Welcome back, Developer

Cortiqa Orchestration Console · Live Sync Active

Get API key (0)Test Workbench
Total API Requests
Inspect
Estimated Spend (30d)

...

based on active usage

Total Tokens Consumed Active

...

input + output tokens

Analytics

Avg API Latency

...

Ready for requests

Try a prompt

Cortiqa Models

Inference endpoints powered by Cortiqa LPU infrastructure.

Explore all models

GPT-OSS 120B

openai/gpt-oss-120b

Active

High-throughput open-weights reasoning model running on ultra-fast Cortiqa LPU infrastructure.

Cortiqa LPU Powered131K ContextUltra-Fast InferenceReasoning & Code
$0.15 / 1M in · $0.60 / 1M outLaunch in Playground →

Falin 1

falin-1

Coming Soon

Cortiqa's flagship proprietary multimodal reasoning architecture. Deep research and autonomous workflows.

ProprietaryMultimodalDeep ResearchComplex Planning
In Active DevelopmentComing Soon