Setup
Kyma works with n8n’s built-in OpenAI node since the API is OpenAI-compatible.
In n8n, go to Credentials > New Credential
Select OpenAI API
Set:
- API Key: Your Kyma API key (
ky-...)
- Base URL:
https://kymaapi.com/v1
Add an OpenAI node to your workflow
Select the credential you just created
Set Model to any Kyma model ID (e.g., qwen-3.6-plus)
Configure your prompt
Run the workflow to verify the connection works.
Example Workflows
Email Classifier
- Email Trigger → receives incoming email
- OpenAI (Kyma) → classify as
support, sales, spam
- Switch → route based on classification
- Slack/Email → notify the right team
Set the model to gemini-2.5-flash or qwen-3-32b for fast classification.
Content Pipeline
- Schedule Trigger → runs daily
- HTTP Request → fetch trending topics from an API
- OpenAI (Kyma) → generate article outline with
qwen-3.6-plus
- OpenAI (Kyma) → write full article with
deepseek-v3
- WordPress → publish draft
Support Auto-Reply
- Webhook → receives support ticket
- OpenAI (Kyma) → draft reply with
qwen-3.6-plus
- If → check confidence score
- Email → send auto-reply or escalate to human
Recommended Models
| Use Case | Model | Why |
|---|
| Classification | gemini-2.5-flash | Cheap active alias + long context |
| Content writing | qwen-3.6-plus | Best quality |
| Data extraction | qwen-3-32b | Fast + structured |
| Complex reasoning | deepseek-r1 | Deep reasoning |
Since Kyma is OpenAI-compatible, you don’t need a custom n8n node. The built-in OpenAI node works perfectly — just change the base URL.
