Docs
cortecs.aiDedicated ModelsServerless ModelsLogin
  • Introduction
  • DEDICATED INFERENCE
    • Quickstart
    • Provisioning API
      • Authentication
      • User
      • Instances
      • Models
      • Hardware Types
    • Python client
      • Objects
      • Langchain integration
    • Examples
      • Batch jobs
      • Realtime streams
  • SERVERLESS INFERENCE
    • Quickstart
    • Serverless Routing
    • Playground
    • API Overview
      • Chat Completions
      • Embeddings
      • Models
  • Discord
Powered by GitBook
On this page
  • How to Access the Playground
  • Playground Configuration
  • Why Use the Playground?
  1. SERVERLESS INFERENCE

Playground

PreviousServerless RoutingNextAPI Overview

Last updated 6 days ago

The Playground is a quick, code-free way to interact with models and test their behavior in real time, perfect for experimenting before writing API requests.

How to Access the Playground

  1. Select a Model from the Catalog Browse the and choose a model that matches your use case or one you’d like to explore.

  2. Open the Model’s Detail Page Click the View Details button for more information about the model, including supported providers and configurations.

  3. Launch the Playground At the bottom of the model’s detail page, click the 💬 Chat button to open the Playground.

You can start chatting with the model immediately, no setup required.

Playground Configuration

The Playground is pre-configured with default parameter values (For more details, see the ).

You can adjust routing behavior directly in the Playground by selecting your preference from the interface:

  • Speed: Prioritizes the fastest available provider.

  • Cost: Prioritizes the most cost-efficient provider.

  • Balanced: Finds a smart balance between speed and cost.

The system will automatically route your requests based on the selected preference.

👉 Note: Currently, only routing preferences can be customized in the playground. More configuration options will be available soon.

Why Use the Playground?

  • Instant Testing: Explore model capabilities without writing code.

  • Quick Prototyping: See how different models respond to your prompts in real time.

  • Seamless API Transition: Once you’re confident, you can easily move to API-based workflows using the same model.

Model Catalog
Serverless Routing