Feature

Multi-Model Support

Choose the AI model that fits your needs and budget

kaag.ai is not locked to a single AI provider. The platform lets you choose from leading AI models and connect custom API-compatible endpoints. You can bring your own model API key for full control over model selection and costs, or use our included AI for a zero-configuration setup. Switch models per tenant without changing any code.

The kaag.ai admin panel model configuration screen showing dropdown selection for the AI model with a choice of leading models and a custom option, alongside an API key input field.

Key benefits

Why Multi-Model Support earns its place

1

Choose from a wide range of leading AI models to match your needs

2

Bring your own model API key for full control over billing, rate limits, and model selection

3

Included AI access in paid plans for a zero-configuration setup

4

Switch models per tenant from the admin panel without touching code or redeploying

5

Custom endpoint support lets you connect to self-hosted or fine-tuned models via a standard API

Model Choice

Choose from a wide range of leading AI models, from fast and cost-efficient to high-capability
Access hundreds of models from many providers through a single integration
Bring your own model key to use whichever model your account already has access to
Custom: connect any endpoint that implements a standard chat-completions API spec, including self-hosted and enterprise deployments

Bring Your Own Key vs Included AI

kaag.ai gives you two options for AI access. With bring-your-own-key, you enter your own model API key in the admin panel and all AI usage is billed directly to your provider account. This gives you full control over model selection, rate limits, and costs. Alternatively, paid plans include our managed AI with a daily token budget, so you can get started without setting up any provider accounts. The included AI is tuned for cost-efficiency by default, roughly a cent per conversation.

Per-Tenant Model Configuration

In a multi-tenant setup, each tenant can use a different AI model. Your marketing site agent might run on a higher-end model for creative responses, while your technical support agent runs on a fast, cost-efficient model for factual answers. Model changes take effect immediately with no downtime and no redeployment required.

FAQ

Frequently Asked Questions

Common questions about Multi-Model Support.

Which AI model does kaag.ai use by default?

The included AI is tuned for cost-efficiency by default, with an excellent balance of quality and cost at roughly one cent per conversation. You can choose a different model at any time in the admin panel.

Can I use a fine-tuned model with kaag.ai?

Yes. If your fine-tuned model is accessible via a standard chat-completions API endpoint, you can configure it as a custom model in the admin panel. This works with self-hosted models running on common inference servers.

Is there a token budget or usage limit?

When using the included AI, each tenant has a configurable daily token budget (default 500K tokens per day) to prevent runaway costs. When using your own model key, there is no platform-side token limit since billing goes directly to your provider.

Works with