Platform

Cortiqa Console Overview

The Cortiqa Console at platform.cortiqa.co is your control center for provisioning API credentials, monitoring real-time inference telemetry, testing prompts interactively, and managing team permissions.

Console Dashboard

When you sign in, the main dashboard provides high-level health indicators:

Total Inferences: Total chat completions processed today and over the last 30 days.
Token Consumption: Breakdown of input vs output reasoning tokens across your applications.
P95 / P99 Latency: Real-time inference latency from Cortiqa LPU clusters.
Error Rate: HTTP 4xx / 5xx error tracking to catch rate limits or format mismatches.

Key Sections

Section	URL	Description
Playground	/playground	Test Cortiqa model prompts in the browser, tweak temperature, and view token usage.
API Keys	/api-keys	Generate, name, revoke, and track usage per secret API key.
Logs	/logs	Inspect request IDs, status codes, timestamps, and latency for debugging.
Billing	/billing	Manage payment methods, view invoices, and set soft/hard budget limits.
Team & Settings	/settings	Invite team members, assign admin or developer roles, and configure SSO.

Interactive Playground

The built-in Playground allows you to prototype without writing code. You can switch between active models like openai/gpt-oss-120b, provide custom system instructions, adjust temperature from 0.0 to 2.0, and stream output responses in real-time.

Quick Navigation

You can access the console anytime via the top navigation pill: API Dashboard ↗ on docs.cortiqa.co or directly at platform.cortiqa.co.

Was this page helpful?

Errors

API Keys