🚀 Usage Guide
- Click the 📁+ icon to create a new session and give it a descriptive name.
- Select your newly created session and load it.
- Click Add Files to upload data files (CSV, JSON, Excel, etc.).
- Ensure your LLM configuration is correct (Get API Key, Configure).
- That's it — start querying!
-
Ask natural language questions, e.g.:
- “What are the top 10 products by sales volume?”
- “Show me email campaigns with the highest open rates”
- Use the context box for formatting preferences (e.g., decimals to 2 places, sort ascending).
🔑 Getting Your LLM API Key
ZenQuery requires an API key from a compatible LLM provider. OpenRouter (recommended) or OpenAI both work seamlessly.
Using OpenRouter
- Visit openrouter.ai and create a new account.
- Add at least $5 in credits to your account. This amount supports tens of thousands of queries.
- Navigate to your API Keys page.
- Click "Create Key", enter a descriptive name, and click "Create".
- Copy the generated key (it starts with
sk-or-v1-...). Store this key securely.
Using OpenAI
- Visit platform.openai.com and log in.
- Go to your billing settings and set up a payment method.
- Visit your API keys page.
- Click "Create new secret key", give it a name, and copy it immediately.
⚙️ Configuring Your Key
- Open ZenQuery → Settings (gear icon).
- Paste your API key into the API Key field.
- Set the "Endpoint" field based on your provider:
- For OpenRouter: https://openrouter.ai/api/v1
- For OpenAI: https://api.openai.com/v1
🔒 Security Note
Your key stays encrypted on your device — never sent to ZenQuery servers.
🎥 ZenQuery Video Guides
Quickstart (2 mins)
Detailed Usage Guide
💰 Understanding Running Costs
| Model | Quality | Questions/$ | Best For |
|---|---|---|---|
| openai/gpt-4.1-mini ⭐ | Close to Best | ~4,500 | Daily queries |
| openai/gpt-4o | Best | ~300 | Complex questions |
| google/gemini-2.0-flash | Very Good | ~18,000 | Heavy usage |
| deepseek/deepseek-chat-v3 | Very Good | ~6,500 | Heavy usage up to moderately complex questions |
| openai/gpt-4o-mini | Good | ~12,000 | Very heavy usage up to low-moderately complex questions |
💡 Example
With our recommended openai/gpt-4.1-mini model, a $5 credit from your provider could answer roughly 25,000 questions of yours — enough for a complete year of regular data analysis! And remember, the size of files does NOT matter at all.
🔐 Data Privacy & Security
Your files are never uploaded to servers. By default, only the first 3 rows are shared with the LLM for schema context, and this is fully configurable to 0 in settings.
💬 Support
Need help? We’re here.
- Email: support@zenquery.app
- Response within 24 hours