SQL Explainer API

About the SQL Explainer API

A SQL explainer API that turns a query into plain English. Send a SELECT, INSERT, UPDATE, DELETE, CREATE or other statement and get back a readable explanation of what it does, the type of operation, and the list of tables it touches. Joins, filters, grouping and ordering are described in terms a non-specialist can follow.

It helps people learning SQL, reviewers reading an unfamiliar query in a pull request, analysts documenting saved reports, and internal tools that show a non-technical user what a query will do before it runs. The tables list is also handy on its own for tagging queries by the data they read or write.

The Free plan returns a short one- or two-sentence explanation, the operation type and the tables. Paid plans let you choose brief, standard, or detailed explanation depth, where detailed adds a step-by-step breakdown, and add a complexity rating of simple, moderate or complex for each query.

How it works

SQL Explainer sends the query you POST, up to 50,000 characters, to a Gemini language model with instructions to explain it in plain English and return structured JSON. The model runs at temperature 0, so the same query normally produces the same explanation. Output is always in English, whatever language the query's comments or identifiers use.

The detail parameter sets the length. brief, the default, asks for one or two sentences. standard asks for two to four. detailed asks for a step-by-step breakdown and allows the longest output. An unrecognised value falls back to brief.

explanation is the prose description. operation is the primary statement type, such as SELECT, INSERT, UPDATE, DELETE or CREATE. tables lists the table names the model identifies in the query. complexity is one of simple, moderate or complex.

The model also judges whether the input is SQL at all. If it is not, the call returns a 400 with an example of a valid query instead of an explanation. Input that fails the text safety check is rejected with a 400 before the model is called. The query is never executed or connected to a database, so the explanation describes intent from the text alone: it cannot know your schema, indexes or row counts, and complexity reflects the query's structure, not its run time. On the Free plan detail is ignored, so every explanation is brief, and complexity is removed.

What people use it for

Learning SQL

Understand complex queries while learning database concepts

Code Reviews

Quickly grasp what SQL queries do during reviews

Documentation

Generate explanations for query documentation

Debugging

Understand legacy or unfamiliar queries

Ways to call it

One endpoint, many ways in — REST with JSON, XML, YAML and CSV, plus GraphQL and an MCP interface for AI agents.

JSON

Default REST response

XML

Markup format

YAML

Human-readable

CSV

Tabular export

Beta

GraphQL

Query language

New

MCP

For AI agents

Request parameters — POST /v1/sqlexplainer

Sent as JSON in the request body. Premium parameters are accepted on every plan but only take effect on plans that include them. Anything not listed here is dropped rather than passed through.

Required

Optional

1
2
3
4

curl -X POST "https://api.apiverve.com/v1/sqlexplainer" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"SELECT u.name, COUNT(o.id) as order_count FROM users u LEFT JOIN orders o ON u.id = o.user_id WHERE u.created_at > '\''2024-01-01'\'' GROUP BY u.id HAVING COUNT(o.id) > 5 ORDER BY order_count DESC","detail":"standard"}'

Authentication

Send your key in the x-api-key header. That is the only auth step — no token exchange, and no per-endpoint scope to configure.

Response — POST /v1/sqlexplainer

Every APIVerve endpoint returns the same three top-level keys, so one response handler covers your whole integration: status, error and data. Only data changes shape.

1
2
3
4
5
6
7
8
9
10
11
12
13

{
  "status": "ok",
  "error": null,
  "data": {
    "explanation": "This SQL query retrieves the names of users and the number of orders they have placed. It filters users who were created after January 1, 2024. The query then groups the results by user ID and only includes users who have placed more than 5 orders, finally ordering the results by the order count in descending order.",
    "operation": "SELECT",
    "tables": [
      "users",
      "orders"
    ],
    "complexity": "moderate"
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Response headers

Every response carries your balance, so your own code always knows where it stands without polling anything. All four are exposed to browsers through CORS.

Errors

Read the HTTP status first, then error for the specific reason. The body names the parameter that has to change.

What a call costs — 10 credits per call

Credits are shared across every APIVerve API — one balance, one key, one bill. Failed requests never count against it, so a rejected input costs nothing.

Calls are what the credits buy at this API's rate — spend them here, on any of the other APIs, or across both. Nothing is reserved per endpoint.

Zero-code embed — one snippet, no backend

Drop an interactive SQL Explainer form onto any page. The widget calls the API for you, so no key ever appears in your markup and there is nothing to deploy.

Changelog — SQL Explainer API

Every change to this endpoint, newest first. Breaking changes ship as a new version and the previous one keeps serving — response fields are added, never removed or retyped in place, so an integration written against v1 keeps working.

Currently v1