Feature 05 · Your model, any time
Pick the right model. Switch the moment a better one ships.
Built on LLM Gateway, the model behind your bot is a setting — pick from a curated, web-search-capable catalog per project and change it whenever you like.
Hard-wire one model and you're stuck with it — every upgrade becomes a migration.
You shouldn't have to re-architect your support stack every time a better model ships. Clanker Support runs on LLM Gateway, so the model behind your bot is a setting you control, not a dependency baked into your code.
The catalog is curated to web-search-capable models — GPT, Claude, Gemini and more. Use a frontier model for complex products or a lighter one for simple FAQs, without touching a line of integration code. Growth and Scale unlock the full catalog.
What you get
A curated, multi-provider catalog
GPT, Claude, Gemini and more via LLM Gateway — interchangeable behind the same support experience, every one of them web-search-capable.
Per-project choice
Different bots can run different models, so each project gets the right cost-to-quality trade-off.
Swap without a rewrite
Changing models is a config update in the dashboard — no redeploy, no code change, no migration.
What it means in practice
- ✓Start on one model and upgrade the moment a better one lands.
- ✓Match model cost to each project's complexity.
- ✓Avoid lock-in — your support layer outlives any single provider.
Explore the rest
Drop-in widget
One script tag. Loads in a shadow DOM so your styles never leak — and theirs never leak into you.
02Answers from your docs
Paste your knowledge base or system prompt. The agent stays on-topic and admits when it doesn't know.
03Escalates to humans
Customers reach a human in one tap — the conversation lands in your inbox with full context. No lost threads.
04Email threading
Replies go out as email and customer responses thread back into the same conversation automatically.
06Self-hostable
Open architecture on serverless edge infra. Run the whole stack on your own account. No surprise vendors.
Frequently asked questions
Which AI models can I use with Clanker Support?
A curated catalog of web-search-capable models served through LLM Gateway — GPT, Claude, Gemini and more. Starter includes the lighter model class; Growth and Scale unlock the full catalog. The model is a per-project setting you control, so you're never tied to one provider's roadmap.
How do I switch models?
Change a setting in the dashboard. Swapping models is a config update — no redeploy, no code change, and no migration. You can upgrade to a better model the moment it ships instead of re-architecting your support stack.
Can different projects run different models?
Yes. Each project picks its own model, so you can run a frontier model for a complex product and a cheaper one for simple FAQs — giving every project the right cost-to-quality trade-off.