Generative AI
Kvery integrates OpenAI models so you can write and understand SQL faster. You can ask the assistant to draft a query from a plain-language request, explain an existing query, or generate a description for it — all from inside the editor.
Bring your own key
The AI features use your own OpenAI API key. You add it once on your profile (see OpenAI key); Kvery then calls OpenAI on your behalf and the usage is billed to your OpenAI account. Without a key, the AI features are unavailable.
Available models
Kvery exposes three OpenAI models, each suited to a different need:
| Name in Kvery | Model | Best for | OpenAI price (USD / 1M tokens) |
|---|---|---|---|
| o3 (SQL PRO) | o3 | Hardest SQL, deep reasoning | input $10 · output $40 |
| GPT-5 mini (FAST) | gpt-5-mini | Quick everyday help, low cost | input $0.40 · output $1.60 |
| GPT-5 | gpt-5 | High-quality general SQL | input $10 · output $40 |
Pick GPT-5 mini for fast, inexpensive iterations and o3 when a query is genuinely complex. Pricing shown is OpenAI's per-million-token rate and may change on OpenAI's side.
What the assistant can do
- Generate SQL from a natural-language description of what you want.
- Explain an existing query so you understand it before running it.
- Generate a description for a query to keep your workspace documented.
How the conversation is bounded
To keep requests efficient and predictable, Kvery caps each AI interaction:
- Up to 3,000 completion tokens per chat response (1,500 for a generated description).
- The conversation history forwarded to OpenAI is limited to 20 user/assistant turn pairs and 50,000 characters in total.
These limits keep responses fast and your OpenAI costs in check; longer back-and-forths simply forget the oldest turns.
Tips
- Give the assistant context — table and column names, what you're trying to achieve — for better SQL.
- Always review generated SQL before running it, especially write statements.
- Use drafts to test AI-generated changes safely before publishing.