The text AI model generates your chatbot's replies using its instructions, conversation and retrieved knowledge. ChatLab offers models from OpenAI, Google and Anthropic. The best fit depends on your actual questions and connected tools.
Choose a model
- Select your chatbot and navigate to Settings > Model & Advanced.
- Open Model and compare the available options and credit rates.
- Select a model and wait for Saved.
- Open Overview, start a new conversation and test the model before relying on it with visitors.
Available text models
The current selector includes these model families and options. Use the selector for availability and rates, as the catalog can change:
- OpenAI: GPT 4-o mini, GPT 4-o, GPT 4.1-mini, GPT 4.1, GPT 5.4-mini, GPT 5.4, GPT 5.5, GPT 5.6 Luna, GPT 5.6 Terra, GPT 5.6 Sol, GPT 6 Luna, GPT 6 Sol, GPT 6.1 Sol and GPT 6 Astra.
- Google: Gemini 3 Flash, Gemini 3.5 Flash, Gemini 3.7 Flash, Gemini 3.8 Flash, Gemini 3.1 Flash-Lite, Gemini 3.5 Flash-Lite and Gemini 3 Pro.
- Anthropic: Claude Haiku 4.5, Claude Sonnet 4.6, Claude Sonnet 5, Claude Opus 4.7, Claude Opus 4.8, Claude Haiku 5.5, Claude Sonnet 5.5, Claude Opus 5.5 and Claude Fable 5.1.
GPT 6.1 Sol and the Claude 5.5 models reason before they answer. That helps on complex questions and makes replies a few seconds slower.
GPT 5-mini, GPT 5, GPT 5.1 and Gemini 2.5 are being retired by their providers and are no longer in the selector. Chatbots that used them were moved to GPT 6 Luna, GPT 6 Sol and Gemini 3.5 Flash-Lite at the same credit rate.
These are ChatLab's text-model choices. A provider's other capabilities, such as image or audio input, do not automatically become available by choosing its text model here. Configure Voice Conversation separately.
Message credits and context
Each option shows its base credit cost at 8k context. The Chat context size setting multiplies that rate:
- 8,000 tokens: x1.
- 16,000 tokens: x2.
- 32,000 tokens: x4.
Connected actions can consume additional credits. Read What is a message credit? and Understanding chat context size before increasing the context. Do not equate the displayed model rate with a complete conversation's usage.
Feature compatibility
Dynamic suggested follow-ups and Offer Cards are unavailable in ChatLab for GPT-4o models and Gemini 3.1 Flash-Lite. Selecting an incompatible model disables those features and shows a notice. After switching to a compatible model, review Enable Offer Cards here and Dynamic suggested follow-ups in Settings > Chat Conversation. Follow-ups also require Hide suggested questions after first message to be off.
Compare with your own questions
Use the same test questions for each model: a common factual question, a question needing several facts, a question in another supported language and one the knowledge base cannot answer. If you use e-commerce or other integrations, also test the connected action and check that the answer uses the returned data correctly. Compare accuracy, useful references, response time and credits.
Changing models does not fix missing or outdated training data. Review incorrect answers and their sources before concluding that a more expensive model is needed.