AI Models
Configure which AI models your organization uses, understand the main, low-cost and image models, compare provider pricing, and learn how AI credit usage is tracked and billed across all Yaplet features.
The Model Slots
Main model
Handles complex, resource-intensive tasks that require deep reasoning and longer outputs. Used for chatbot answer generation, AI suggestions, and content creation.
Low-cost model
Handles fast, lightweight tasks that need quick turnaround. Used for grammar correction, message rephrasing, conversation summaries, and supporting operations that make the main model more efficient.
Image model
Generates images — for example the visuals of AI social posts. Billed at a flat price per generated image rather than per token.
Which features use which model?
| Feature | Model | Examples |
|---|---|---|
| Yaplet streaming answers | Main | Generating real-time responses to visitor questions |
| AI content generation | Main | Writing knowledge base articles, generating suggestions |
| Inbox AI Tools | Low-cost | Grammar check, rephrase, translate |
| Conversation summaries | Low-cost | Summarizing chat history for context |
| Searching the brand's knowledge for an answer | Low-cost | Searching everything the brand owns — knowledge bases, documentation, products, and the files, text, Q&A and website pages added to it. |
| Choosing the claims that fit a question | Main | Decides which of the shop's claims really fit what the visitor wants. It runs only for brands with at least one claim switched on; other brands never pay for it |
| Image generation | Image | Cover visuals for AI social posts |
Configuring Your Models
Navigate to Settings → Workspace → AI Models to view and change your organization's model configuration. The models apply to every brand in the workspace.
Current Models
The page lists three settings — Main model, Low-cost model and Image model — each with a picker that shows the model's logo and name. Under the picker you see the model's price line, per million tokens:
- $X in · $Y out per 1M tokens — the cost of a million input (prompt) tokens and a million output (response) tokens
- $X per image — the flat cost per generated image, shown for the image model instead of token prices
A Recommended badge marks a setting that is left on Yaplet's recommended model. Prices are per 1M tokens; answers use credits in proportion.
Below the settings, Available models lists every model you can pick, grouped by maker with a model count. Tags show what each model does in your workspace now (Main, Low-cost or Images), and Recommended and Image badges mark the recommended and image models.
You can also change the main model from the Answers page of Brand → AI agent and from the Playground.
Changing Models
Select new models
Open the picker of the Main model, Low-cost model or Image model, or any combination, and choose a model. Models are grouped by maker (OpenAI, Anthropic, Google, xAI) with pricing shown for each option. The first option, Picked by Yaplet and upgraded automatically, is Yaplet's recommended model.
Review the cost change
When you select a different model, a badge under the picker shows the cost impact against the model in use now, for example 25% more per use or 25% less per use.
Save and confirm
Click Save changes at the top of the section (Discard undoes your picks) and confirm the Change your AI models? window. The new models take effect immediately for all AI tasks across your organization, and a Models saved message confirms it. If you leave the page with unsaved picks, Yaplet asks first.
Supported Providers
Yaplet integrates with leading AI providers through a unified interface. You don't need API keys or separate accounts — all provider access is managed through your Yaplet subscription.
| Provider | Strengths |
|---|---|
| OpenAI | Broad model range, strong general-purpose performance |
| Anthropic | Advanced reasoning, large context windows |
| Competitive pricing, multimodal capabilities | |
| xAI | Fast inference, latest research models |
Credit Usage & Billing
Every AI operation consumes tokens — small units of text that models process. Yaplet tracks usage across all features and bills using a unified currency called Yaplet Credits.
How credit billing works
Tokens are consumed
Each AI request uses input tokens (your prompt) and output tokens (the model's response). Some models also use cached input tokens and reasoning tokens.
Costs are combined
Because different token types have different prices, all usage is combined into a single, comparable number.
Billed as Yaplet Credits
That number is converted to Yaplet Credits, and all AI usage is paid in credits. This unified pricing makes it easy to understand costs regardless of which model or provider you use.
Token cost types explained
| Token Type | What It Is | When It Applies |
|---|---|---|
| Input | Tokens in your prompt and context | Every request |
| Output | Tokens the model generates | Every request |
| Cached Input | Repeated prompt tokens served from cache (lower cost) | When conversation context is reused |
| Reasoning | Internal thinking tokens used for complex problem-solving | Models with reasoning capabilities (e.g., OpenAI o-series) |
Image generation is the exception: it isn't measured in tokens at all. The image model carries a flat cost per image, shown on the settings page alongside the other models.
The free 14 days vs. the free plan
These are two different things, and it's easy to mix them up. Every new workspace starts a free 14 days at sign-up, with free AI credits that pay for AI first; they need no card and end with the 14 days. The free plan is what the workspace stays on afterward: it has no free AI answers, so AI is paid from the credit you bought. With no credit and nothing else that can pay, Yaplet's answers pause and new chats go to your team. Paid plans have no free answers either: every answer is billed from the first one, at a lower rate. See Plans & Pricing for details.
Where AI Is Used in Yaplet
AI models power features across the entire platform. Here's a quick overview of where your model choices have an impact:
AI agent
Your main model generates real-time streamed answers to visitor questions, using the brand's knowledge, products and API tools.
Inbox AI Tools
Your low-cost model powers grammar checking, rephrasing, and other message enhancement tools available to agents in the inbox.
Tips for Choosing Models
If budget is a priority, choose models with lower per-token pricing — especially for the low-cost model, which handles high-volume simple tasks. A cheaper low-cost model can significantly reduce your overall token spend.
For the best chatbot responses, select a premium main model with strong reasoning capabilities. The main model directly affects the quality of answers your visitors receive.
If you're unsure, keep every setting on Yaplet's recommended model. Yaplet regularly evaluates models across providers and updates the defaults to offer the best balance of quality and cost.