OpenAI Models Integration

Available Models

GPT-4 (Recommended for Quality)

Model: gpt-4 or gpt-4-turbo

Capabilities:
- Advanced reasoning
- Complex problem-solving
- Multi-step thinking
- Best for critical tasks

Cost: ~$0.03-0.06 per 1K tokens
Speed: 1-3 seconds response time
Best For: Customer service, technical support, complex queries

When to Use GPT-4:

Legal or compliance-critical interactions
Technical troubleshooting
Complex negotiations
High-value customer interactions

GPT-3.5 Turbo (Recommended for Balance)

Model: gpt-3.5-turbo

Capabilities:
- Fast responses (< 1 second)
- Good reasoning
- Cost-effective
- Excellent for most use cases

Cost: ~$0.0005-0.002 per 1K tokens
Speed: < 1 second response time
Best For: General customer service, sales, lead generation

When to Use GPT-3.5 Turbo:

High-volume calling
Time-sensitive responses
Cost-conscious operations
Standard customer interactions

Setup

Step 1: Get Your API Key

Go to platform.openai.com
Sign in to your OpenAI account
Click “API keys” in the left menu
Click “Create new secret key”
Copy the key (you won’t see it again)

Example Key Format:
sk-proj-XXXXXxxxxxxxxxxxxxxxxxxxx

Step 2: Set up Billing

OpenAI charges per API usage:

Go to “Billing” in OpenAI dashboard
Set usage limits to prevent surprises
Add payment method
Review pricing page for current rates

Step 3: Add to CallIntel

For Super Admins:

Go to Settings → Developer Settings
Click “API Keys”
Select “OpenAI” from provider list
Paste API key
Click “Test Connection”
Save

For Organization Admins:

Go to Settings → AI Models
Click “Add OpenAI Model”
Paste API key (or use super admin configured key)
Select which models to enable
Save

Step 4: Configure Agent

Create or Edit an Agent
Under “Language Model”, select:
- gpt-4-turbo or
- gpt-3.5-turbo
Configure advanced settings:
- Temperature: 0.7 (default)
- Max Tokens: 150 (for responses)
- Frequency Penalty: 0 (no penalty)
- Presence Penalty: 0 (no penalty)
Save agent

Step 5: Test

Make a test call to verify:

Use Web Call feature
Speak to agent
Verify proper responses
Check call logs

Model Selection

Model Comparison

Feature	GPT-4	GPT-3.5
Quality	⭐⭐⭐⭐⭐	⭐⭐⭐⭐
Speed	⭐⭐⭐	⭐⭐⭐⭐⭐
Cost	⭐⭐	⭐⭐⭐⭐⭐
Reasoning	⭐⭐⭐⭐⭐	⭐⭐⭐⭐
Languages	⭐⭐⭐⭐⭐	⭐⭐⭐⭐

Cost Example (1000 calls/month)

GPT-4 Scenario:

1000 calls × 500 tokens average × $0.00003/token = $15/month
Cost per call: $0.015
Monthly cost: $15 (for 1000 calls)

GPT-3.5 Turbo Scenario:

1000 calls × 500 tokens average × $0.0000005/token = $0.25/month
Cost per call: $0.00025
Monthly cost: $0.25 (for 1000 calls)

60x cost difference for 1000 calls!

Configuration Options

Temperature

Controls response creativity (0-2):

0 = Deterministic (same response every time)
7 = Balanced (default - good for most uses)
5 = Creative (varied responses)
0 = Very creative (unpredictable)

Recommended Settings:

Customer Service: 0.3-0.5 (consistent)
Sales: 0.7-0.9 (engaging but helpful)
Creative Tasks: 1.2-1.5 (varied responses)

Max Tokens

Maximum response length (1-4096):

Short Responses: 50-100 tokens
Medium: 150-200 tokens
Long Responses: 300-500 tokens

Tip: Lower max tokens saves costs!

Max Tokens Example:
tokens: $0.0015 per call
tokens: $0.0045 per call
tokens: $0.009 per call

System Prompt

Define agent behavior (see Agent Setup Guide):

Example:
"You are a friendly customer service representative. 
Keep responses under 100 words. Be helpful and professional."

Advanced Features

Function Calling

Enable agents to call external functions:

{
  "name": "get_order_status",
  "description": "Get status of customer order",
  "parameters": {
    "type": "object",
    "properties": {
      "order_id": {
        "type": "string",
        "description": "The order ID"
      }
    }
  }
}

Agents can:

Look up information
Process transactions
Update systems
Trigger actions

Vision Capabilities

GPT-4V can analyze images:

Supported:
- Receipt analysis
- Document scanning
- Image description
- Quality inspection

Note: Requires image input in calls (enterprise feature).

Cost Optimization

1. Use GPT-3.5 Turbo for Most Tasks

GPT-4: Use sparingly for complex queries
GPT-3.5: Default for all other interactions
Savings: 10-20x cost reduction

2. Optimize Prompts

Bad (expensive):

"You are a helpful AI assistant in a contact center. 
You should be friendly, professional, and knowledgeable 
about our products. When customers call, listen carefully 
to their questions and provide helpful, accurate responses..."

Good (cheaper):

"You are a helpful customer service representative. 
Be friendly and professional."

Savings: 60% reduction in tokens!

3. Reduce Token Usage

Technique        | Savings
-----------------|-------
Shorter KB       | 30-50%
Concise prompts  | 20-40%
Lower max_tokens | 10-30%
No history       | 10-20%

Combined: 50-70% possible

4. Batch Processing

For scheduled calls, use batch API:

Standard: $0.002 per 1K tokens
Batch: $0.0005 per 1K tokens
Savings: 75% cheaper

How to Use:

Schedule calls for off-peak hours
Use batch endpoint (CallIntel handles this)
24-hour processing window
Save significantly on costs

Monitoring & Limits

Token Monitoring

Check usage in OpenAI dashboard:

Go to Usage Dashboard
View current usage
Check spending
View by model breakdown

Rate Limits

Default limits for standard accounts:

GPT-4: 200 requests/minute
GPT-3.5: 3,500 requests/minute

Increase limits in account settings
Contact OpenAI for higher limits

Budget Controls

Set spending limits to prevent surprises:

Go to Billing → Usage Limits
Set hard limit (e.g., $100/month)
Optional email alert at 50%
API requests blocked when limit reached

Best Practices

1. Start with GPT-3.5 Turbo

Phase 1: Use GPT-3.5 for all agents
Phase 2: A/B test GPT-4 on specific agents
Phase 3: Use GPT-4 only where needed
Result: Optimized cost and quality balance

2. Monitor Performance

Track key metrics:

- Average response time
- User satisfaction
- Cost per call
- Error rate
- Token usage

Review monthly and optimize.

3. Test Before Production

Create test agents with both models
Make identical calls
Compare responses
Evaluate cost/quality tradeoff
Choose best option for each use case

4. Use Lower Temperature for Consistency

Customer Service: 0.3-0.5
- Consistent responses
- Predictable behavior
- Better for compliance-critical tasks

Troubleshooting

Getting 'API key invalid' error

Verify key starts with sk- and is not truncated. Copy from OpenAI dashboard again and test.

Responses are slow

Switch to GPT-3.5 Turbo for faster responses. Also reduce max_tokens setting.

Costs are higher than expected

Check token usage in OpenAI dashboard. Reduce max_tokens, shorten KB, and simplify prompts.

Agent responses are inconsistent

Lower temperature setting to 0.3-0.5 for more deterministic responses.

Agent keeps making mistakes

Consider upgrading to GPT-4 for better reasoning, or improve system prompt and knowledge base.

AI Models Overview

Compare all AI providers

Agent Setup

Create and configure agents

Knowledge Base Guide

Build effective knowledge bases

Support

OpenAI API Docs

View OpenAI Documentation

Contact Support

Email: callintel01@gmail.com

​Available Models

​GPT-4 (Recommended for Quality)

​GPT-3.5 Turbo (Recommended for Balance)

​Setup

​Step 1: Get Your API Key

​Step 2: Set up Billing

​Step 3: Add to CallIntel

​Step 4: Configure Agent

​Step 5: Test

​Model Selection

​Model Comparison

​Cost Example (1000 calls/month)

​Configuration Options

​Temperature

​Max Tokens

​System Prompt

​Advanced Features

​Function Calling

​Vision Capabilities

​Cost Optimization

​1. Use GPT-3.5 Turbo for Most Tasks

​2. Optimize Prompts

​3. Reduce Token Usage

​4. Batch Processing

​Monitoring & Limits

​Token Monitoring

​Rate Limits

​Budget Controls

​Best Practices

​1. Start with GPT-3.5 Turbo

​2. Monitor Performance

​3. Test Before Production

​4. Use Lower Temperature for Consistency

​Troubleshooting

​See Also