Requesty
thecontinuitylayer.com/tools/routers/requestyBuilders who want an OpenRouter-style router with routing and spend controls
Router · Requesty
Requesty is a hosted LLM router: one API key and one OpenAI-compatible endpoint that sends your requests to many model providers. It adds features for teams such as fallbacks between providers and spend tracking.
Pricing works much like OpenRouter's, with 5% added to the provider's per-token price instead of 5.5% on credit purchases, so a model listed at $10 per million tokens costs $10.50. There is a free tier of 200 requests a day on free models with no credit card, and traffic that uses your own provider keys has no markup.
Specs
| Fees | 5% added to model cost on pay-as-you-go |
|---|---|
| Routes to | 600+ models from many providers through one OpenAI-compatible endpoint (vendor figure) |
| Fee | 5% on model cost |
| Free tier | 200 requests/day on free models |
| Models | 600+ (vendor figure) |
| Bring your own key | 0% markup |
| API format | OpenAI-compatible |
| Hosting | Hosted only |
Good for
- Swapping in for OpenRouter with a similar fee
- Teams wanting fallbacks and spend tracking
Not for
- Self-hosting
- Anyone who wants zero markup
See also
- Kilo Gateway · Developers, especially Kilo Code users, who want provider prices with no markup
- Eden AI · Builders who need LLMs plus other AI services (OCR, speech, translation) behind one API
- LiteLLM · Developers and teams who want to run their own router with no per-request fee
We last reviewed Requesty on 31 October 2026. Prices and specs change; check requesty.ai before you buy or sign up. Figures we could not confirm on the vendor's own page read “not published” or “varies”.
Vendor source: https://www.requesty.ai/pricing