Feature 05 · Any model, any time
Run any model. Switch the moment a better one ships.
Built on LLM Gateway, the model behind your bot is a setting — pick one 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.
Use a frontier model for complex products, a cheaper one for simple FAQs, or bring your own — without touching a line of integration code.
What you get
Model-agnostic
GPT, Claude, or a custom model — they're interchangeable behind the same support experience.
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 bot stays on-topic and admits when it doesn't know.
03Escalates to humans
When the bot can't help, 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.
Ship support today