Connect an app
Other OpenAI-compatible apps
Point any OpenAI-compatible client at Kyara Intelligence with three values: base URL, API key, and model ID.
Kyara works as a drop-in replacement for OpenAI in compatible apps. Most clients ask for the same three things: a base URL, an API key and a model. Set them and your requests run on Kyara; nothing else in your setup changes.
There are dedicated guides for Open WebUI and SillyTavern. For everything else, use the values below.
The three values
| Setting | Value |
|---|---|
| Base URL | https://api.kyara-intelligence.com/v1 |
| API key | Your key from the dashboard |
| Model | A model ID from the catalog |
Check your credentials
Every integration sends the same HTTP request underneath. Export your key with export KYARA_INTELLIGENCE_API_KEY="your-api-key", then run one of these from the same terminal to confirm
it works before you configure an app.
curl https://api.kyara-intelligence.com/v1/chat/completions \
-H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'A response with a choices array means the key works. An invalid_api_key error means it is
missing or wrong.
Notes for common apps
The steps are the same everywhere: set the base URL, paste your key, and choose a model ID. Apps that list models read GET /v1/models, which works without a key.
- Cherry Studio: add an OpenAI-type provider and
enter the API host so that the request URL preview reads
https://api.kyara-intelligence.com/v1/chat/completions. Paste your key, then add model IDs from the catalog. - Continue (VS Code and JetBrains): add a model with
provider
openai, setapiBaseto the base URL andapiKeyto your Kyara key. - LibreChat: add a custom endpoint with the base URL, your key, and the model IDs you want to offer.
- Any OpenAI SDK: set
baseURL(JavaScript) orbase_url(Python) to the base URL and pass your key. No other code changes are needed.