Understanding Message Credits with Examples
Message credits measure how many chatbot responses you can generate within your subscription.
1 Message Credit = 1 Chatbot Response
assuming the chatbot uses basic AI model for it’s responses (which is default)
Each response from the chatbot costs 1 message credit, while user messages are free. Below, we explain how message credits work, include function call features, live chat and show examples based on typical usage and subscription packages.
- Understanding Message Credits with Examples
- Basic Model Setup: GPT-4o-mini
- Subscription Packages
- AI Models and Message Costs
- Live Chat: Credit Usage
- Integrations with e-commerce/backend systems
- Example: Conversations and Function Calls with E-Commerce Integration
Basic Model Setup: GPT-4o-mini
- 1 chatbot response = 1 message credit
- User messages = free
- Average conversation = around 7 exchanges - 1 exchange = 1 user message + 1 chatbot response, resulting in 7 chatbot responses per conversation and use of 7 message credits
Subscription Packages
Here’s how many chatbot responses and conversations you can expect with each package:
Package | Message Credits | Conversations (avg. 7 exchanges) |
Basic Package | 2,400 credits | ~343 conversations |
Standard Package | 11,000 credits | ~1,571 conversations |
Premium Package | 50,000 credits | ~7,143 conversations |
AI Models and Message Costs
Different AI models consume varying amounts of credits per chatbot response. Here’s the breakdown:
AI Model | Credits per Response | Key Features |
GPT-3.5 Turbo | 1 credit | Older, reliable, and cost-effective |
GPT-4o-mini (default) | 1 credit | Balanced cost and performance |
GPT-4o | 5 credits | High performance and quality - currently top OpenAI model in terms of quality to price relation. The use of this model is highly suggested when using chatbot integrations with e-commerce & backend systems |
GPT-4 Turbo | 10 credits | High performance and faster responses |
GPT-4 | 20 credits | Advanced for complex tasks |
Google Gemini 1.5 Flash | 1 credit | Budget-friendly and fast |
Google Gemini 1.5 Pro | 10 credits | Enhanced features for demanding use cases |
Read more here:
Selecting AI modelLive Chat: Credit Usage
Live chat enables direct communication between users and human operators. Each message in a live chat, whether sent by the user or the operator, costs 1 message credit.
- User messages: Cost 1 credit per message.
- Operator responses: Cost 1 credit per message.
- Both sides of the conversation contribute to the total credit usage.
If a live chat conversation includes:
- 5 messages from the user
- 5 responses from the operator
The total credit usage will be 10 credits.
Read more here:
Integrations with e-commerce/backend systems
Integrations with e-commerce/backend systems also called Function Calls. These are advanced features designed for integrating your chatbot with backend (ie. e-commerce) systems, such as:
- Checking order statuses.
- Searching for products in your e-commerce store.
- Custom API requests for tailored operations.
Key details about function calls:
- Function calls are disabled by default. You need to enable them in the chatbot settings if required.
- GPT-4o is required for function calls.
- Credit usage for function calls:
- Predefined functions (e.g., checking orders): 1 credit per call.
- Custom API functions: 2 credits per request.
Read more here:
Integration with WooCommerceIntegration with ShopifyIntegration with BaseLinkerCustom API integrationsExample: Conversations and Function Calls with E-Commerce Integration
Using the Standard Package with 11,000 credits and GPT-4o (required for API calls, costing 5 credits per response), here’s how credits are used when integrating with an e-commerce backend:
- Average Conversation:
- 7 exchanges = 7 chatbot responses = 35 credits.
- 1 function call per conversation = 1 credit.
- Total per conversation = 36 credits.
- Total Conversations: ≈ 305 conversations.
This setup allows advanced functionality like checking order statuses or product searches while maintaining high-quality responses.