Konnect.ai

Smart Chat

Free

Intelligent routing that automatically selects the best model for your query.

Overview

Smart Chat is the default and most efficient way to use Konnect.ai. Instead of manually selecting a model, our intelligent router analyzes your question and automatically sends it to the most appropriate model based on the query type.

Fast
Single model, no aggregation overhead
Smart
Auto-selects optimal model
Free
Included in all plans

How It Works

1

Query Analysis

Your question is analyzed to determine its type: coding, creative writing, factual Q&A, reasoning, math, etc.

2

Model Selection

Based on benchmarks and performance data, the router selects the model that excels at that particular task type.

3

Response Generation

Your query is sent to the selected model and the response is returned directly to you.

Model Routing Examples

Coding questionsclaude-3-sonnet

"Write a Python function to merge two sorted arrays"

Creative writinggpt-4o

"Write a short story about a robot learning to paint"

Factual Q&Agemini-pro

"What year was the Eiffel Tower built?"

Complex reasoningclaude-3-opus

"Analyze the implications of quantum computing on current encryption standards"

When to Use Smart Chat

Quick questions that don't require verification
When speed is more important than consensus
General conversations and brainstorming
When you want to conserve your query quota

API Usage

cURL
curl https://api.konnect.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "What is the capital of Japan?"}
    ],
    "stream": true
  }'

Need more reliability?

For important decisions where accuracy matters, consider using Ensemble mode to query multiple models and get a synthesized response.

Learn about Ensemble mode