Classify support tickets
Turn sample ticket text into a category, urgency and summary. Review the result before routing a ticket.
Download workflow JSONINTEGRATIONS
Your first workflow.
One API connection.
Use Flonno from your server or automation tool. Start with a sample, select a model and inspect the response before connecting business systems.
Before your first request
- Create an account, then create a key in API keys with
chat:completionsand access to your chosen model. Addmodels:readif your client lists models. - Check current model prices and your wallet balance. Generation uses paid API capacity; these templates do not include free credit.
- Keep the key in your tool's credential store or your server environment. Base URL:
https://www.flonno.com/v1.
Three n8n starting points
Download a workflow, import it from a file in n8n and open the Call Flonno node. Select a Header Auth credential with name Authorization and value Bearer YOUR_FLONNO_KEY. Replace the sample input, then execute manually.
Draft product descriptions
Turn supplied product facts into a short description. Review every claim before publishing.
Download workflow JSONExtract document fields
Extract invoice fields from text you supply. This example uses text; it does not upload or read PDFs.
Download workflow JSONRead text from choices[0].message.content. JSON requested in a prompt still needs validation. The files contain no API secrets and start inactive. Your n8n version may require adapting node settings; live execution in n8n has not yet been verified.
Start from your existing client
Import the OpenAPI specification into your API client to explore the two documented endpoints. Add your own credential after importing.
A single HTTP call
A small server script using built-in fetch, a request timeout and a 128-token output cap.
Download Node.js example ↓Read the SDK guide →OpenAI SDK
Configure your Flonno key and base URL, then call Chat Completions with a supported model ID.
Download Python example ↓Add a model route
A configuration for an OpenAI-compatible route. The API key comes from your server environment.
Download LiteLLM configuration ↓Read the LiteLLM guide →Check the response and the activity log
HTTP 401: check your key. HTTP 403: check permissions, model access and IP restrictions. HTTP 402: check your available prepaid balance. HTTP 400: check the model ID and request fields. Review Activity logs after each test; avoid automatically retrying payments or failed generation.
Flonno receives request content and currently forwards model requests to an external inference service. Self-hosted inference and automatic overflow are target architecture. n8n and client tools may retain execution content according to their settings. Read the privacy notice before sending customer data.