Message credits measure how many chatbot interactions you can generate within your subscription.
💡 1 Message Credit = 1 Chatbot Text Response (voice calls are billed per minute - see below)
Each text response from the chatbot costs 1 message credit, while user messages are free. Voice conversations are billed per minute regardless of provider. Below, we explain how message credits work for text, voice, function calls, live chat, and show examples based on typical usage.
Basic Model Setup: Mini Models
ChatLab uses efficient Mini models by default (e.g., GPT-4o-mini, GPT-4.1-mini, GPT-5-mini, Gemini 2.5 Flash) for cost-effective chatbot text responses:
-
1 chatbot text response = 1 message credit (when using Mini models)
-
User messages = free
-
Average conversation = around 5 exchanges - 1 exchange = 1 user message + 1 chatbot response, resulting in 5 chatbot responses per conversation and use of 5 message credits
Subscription Packages
Here's how many chatbot responses and conversations you can expect with each package:
| Package | Message Credits | Conversations (avg. 5 exchanges) |
|---|---|---|
| Basic Package | 2,400 credits | ~480 conversations |
| Standard Package | 11,000 credits | ~2,200 conversations |
| Premium Package | 50,000 credits | ~10,000 conversations |
AI Models and Message Costs (Text)
Different AI text models consume varying amounts of credits per chatbot response. ChatLab supports three main model categories:
Mini Models (1 credit per response)
- Optimized for speed and efficiency
- Perfect for general conversational tasks and high-volume chatbots
- Available models: GPT-4o-mini, GPT-4.1-mini, GPT-5-mini, Gemini 2.5 Flash
- Great for websites, customer support, and FAQ bots
- Default model for new chatbots
Reasoning Mini Models (3 credits per response)
- Lightweight reasoning-optimized model
- Better at multi-step questions than standard Mini, while staying cost-efficient
- Available models: GPT-5.4-mini, Gemini 3 Flash
Full Models (5 credits per response)
- Advanced reasoning and quality
- Required for function calls and integrations with e-commerce/backend systems
- Higher accuracy for complex queries and nuanced conversations
- Available models: GPT-4o, GPT-4.1, GPT-5, GPT-5.1, GPT-5.4, Claude Haiku 4.5
- Best for e-commerce integrations, order tracking, and sophisticated customer interactions
Premium Models (10 credits per response)
- Highest quality and specialized capabilities
- Exceptional performance for coding, mathematics, and complex reasoning tasks
- Available models: GPT-5.5, Gemini 3 Pro, Gemini 2.5 Pro, Claude Sonnet 4.6
- Recommended for technical support, developer tools, and advanced use cases
Top-Tier Models (15 credits per response)
- Anthropic's most capable model with deep multi-step reasoning
- Best when answer quality matters more than cost or speed
- Available models: Claude Opus 4.7
- Recommended for complex analysis, long-form responses, and demanding use cases
💡 Note: The specific models available may change over time as AI technology evolves. Check your chatbot settings in the ChatLab admin panel for the current list of supported models and their exact credit costs.
Voice Conversations: Per-Minute Billing
Voice calls are billed by call duration instead of per response - the same way for every voice model. Each voice provider has its own per-minute rate, a first-minute minimum charge, and an increment used after the first minute.
| Voice Model | Rate | First-Minute Minimum | After First Minute |
|---|---|---|---|
| GPT Realtime | 30 credits/min | 30 credits | 5 credits per 10 seconds |
| GPT Realtime Mini | 20 credits/min | 20 credits | 5 credits per 15 seconds |
| Gemini 3.1 Flash Voice | 20 credits/min | 20 credits | 5 credits per 15 seconds |
| ElevenLabs Voice | 30 credits/min | 30 credits | 5 credits per 10 seconds |
How billing works:
-
First-minute minimum - any call that starts is charged at least the first-minute floor (20 or 30 credits depending on the model). A call that ends after 10 seconds still costs the full first-minute minimum.
-
Increments after the first minute - additional time is rounded up to the next 10- or 15-second chunk (5 credits each), always in the operator's favor.
-
Pre-call check - to start a voice call, the chatbot must have at least the first-minute minimum credits available (20 or 30, depending on the voice model). Calls cannot start below this threshold unless overage is enabled.
-
Heartbeat-based billing - while a call is active, the widget sends checkpoint signals during the conversation. Billing finalizes on the last confirmed checkpoint, so dropped calls, closed tabs, or silent disconnections are never charged for the silent gap.
-
Mid-call termination - if remaining credits run too low to cover the next billing increment, the server signals the widget to end the call automatically and only the confirmed time is billed.
💡 Voice calls do not consume per-message credits anymore. All voice providers (GPT Realtime, GPT Realtime Mini, Gemini 3.1 Flash Voice, ElevenLabs Voice) use the unified per-minute model described above. The previous per-turn voice billing is no longer in effect.
Example: A 2-minute 25-second call on GPT Realtime is billed as: 30 credits (first minute) + 9 × 5 credits (90 seconds rounded up to nine 10-second chunks) = 75 credits.
Live 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.
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.
-
Full models are required for function calls (Mini models don't support this feature).
-
Credit usage for function calls:
- Built-in integrations (e.g., Shopify, WooCommerce): 1 credit per call.
- Custom API integrations: 1 credit per call.
Example: E-Commerce Integration Credit Usage
Using the Standard Package with 11,000 credits and a Full model (required for API calls, costing 5 credits per response), here's how credits are used when integrating with an e-commerce backend:
- Average Conversation:
- 5 exchanges = 5 chatbot responses = 25 credits.
- 1 built-in integration call per conversation = 1 credit.
- Total per conversation = 26 credits.
This setup allows advanced functionality like checking order statuses or product searches while maintaining high-quality responses.
Agency Partners: Function Call Pricing
For agency partners offering white-label ChatLab solutions to their clients, function call pricing differs from standard accounts. All function calls cost 2 credits per call (compared to 1 credit for standard accounts):
- Built-in integrations (Shopify, WooCommerce, etc.): 2 credits per call
- Custom API integrations: 2 credits per call
💡 This higher pricing applies to all chatbots created under agency partner accounts. The increased cost reflects the additional infrastructure and support required for multi-tenant white-label deployments.