Bring your own key. Pay for tokens, not seats.
KLINCH does not resell model access. Connect any OpenAI-compatible endpoint, choose the model per task and see the cost on your provider's invoice.
Why bring your own key
With your own key there is no markup and no opaque credit system. You can use the newest model the day it ships, keep a cheaper model for simple edits and route through OpenRouter or your company gateway.
How your key is protected
Keys are encrypted with AES-256-GCM before they are stored and are bound to your account. Requests to the provider are made from the server; the browser only ever sees the last four characters.
Supported providers
Anything that implements the OpenAI Chat Completions API with streaming. Presets are included for the most common ones.
- OpenAI: api.openai.com/v1
- OpenRouter: openrouter.ai/api/v1
- DeepSeek: api.deepseek.com/v1
- Kimi (Moonshot): api.moonshot.ai/v1
- Any self-hosted or corporate OpenAI-compatible /v1 gateway
FAQ
How much does it cost?
KLINCH is free during the beta. Model usage is billed by your provider at their prices.
Can I add several providers?
Yes. Add several providers and several models per provider, then pick the model for each chat.