LobeHub
LobeHub can add custom AI providers. Choose the OpenAI request format with the address up to /v1 and every KovAPI model is available; self-hosted instances can use environment variables instead.
Add a custom provider
- Open App Settings → AI Providers and click Add Custom Provider.
- Give a lowercase Provider ID (lowercase letters, digits,
-and_; it cannot be changed later), choose OpenAI as Request Format, enterhttps://kovapi.com/v1as Proxy URL and your key as API Key, then click Create. - On the provider page click Fetch models, or add models by hand with Add Model, setting the maximum context window and ticking tool calling and vision where the model has them.
- Enable the models you want and pick one in a chat.
https://kovapi.com/v1Keep Use Client Request Mode off (the KovAPI API does not accept cross-origin browser requests), and keep Use Responses API Specification off as well.
Claude (optional)
Add a second custom provider with Anthropic as Request Format and https://kovapi.com/anthropic as Proxy URL.
Self-hosted: environment variables
A self-hosted LobeHub can be pointed at KovAPI with environment variables:
OPENAI_API_KEY=YOUR_API_KEY OPENAI_PROXY_URL=https://kovapi.com/v1 OPENAI_MODEL_LIST=-all,+gemini-3.1-pro,+deepseek-v4.1-flash ANTHROPIC_API_KEY=YOUR_API_KEY ANTHROPIC_PROXY_URL=https://kovapi.com/anthropic
In OPENAI_MODEL_LIST, -all hides every built-in model, +model-id adds a KovAPI model, and +model-id=Display name also sets its display name.
Test
In Connectivity Check on the provider page, pick a model and click Check (it sends one short message); Check passed means you are done.
Troubleshooting
The proxy URL must include /v1: https://kovapi.com/v1.
Check the key and the proxy URL; you can also add models by hand with Add Model.
Switch Use Client Request Mode off so the requests go out from LobeHub's server.