Ask AI

POST /v2/rewriter/ask-ai

Ask AI

cURL

curl --request POST \
  --url https://api.velt.dev/v2/rewriter/ask-ai \
  --header 'Content-Type: application/json' \
  --header 'x-velt-api-key: <x-velt-api-key>' \
  --header 'x-velt-auth-token: <x-velt-auth-token>' \
  --data '
{
  "data": {
    "model": "<string>",
    "prompt": "<string>",
    "text": "<string>"
  }
}
'

import requests

url = "https://api.velt.dev/v2/rewriter/ask-ai"

payload = { "data": {
        "model": "<string>",
        "prompt": "<string>",
        "text": "<string>"
    } }
headers = {
    "x-velt-api-key": "<x-velt-api-key>",
    "x-velt-auth-token": "<x-velt-auth-token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'x-velt-api-key': '<x-velt-api-key>',
    'x-velt-auth-token': '<x-velt-auth-token>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({data: {model: '<string>', prompt: '<string>', text: '<string>'}})
};

fetch('https://api.velt.dev/v2/rewriter/ask-ai', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.velt.dev/v2/rewriter/ask-ai",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'data' => [
        'model' => '<string>',
        'prompt' => '<string>',
        'text' => '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-velt-api-key: <x-velt-api-key>",
    "x-velt-auth-token: <x-velt-auth-token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.velt.dev/v2/rewriter/ask-ai"

	payload := strings.NewReader("{\n  \"data\": {\n    \"model\": \"<string>\",\n    \"prompt\": \"<string>\",\n    \"text\": \"<string>\"\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-velt-api-key", "<x-velt-api-key>")
	req.Header.Add("x-velt-auth-token", "<x-velt-auth-token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.velt.dev/v2/rewriter/ask-ai")
  .header("x-velt-api-key", "<x-velt-api-key>")
  .header("x-velt-auth-token", "<x-velt-auth-token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"data\": {\n    \"model\": \"<string>\",\n    \"prompt\": \"<string>\",\n    \"text\": \"<string>\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.velt.dev/v2/rewriter/ask-ai")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-velt-api-key"] = '<x-velt-api-key>'
request["x-velt-auth-token"] = '<x-velt-auth-token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"data\": {\n    \"model\": \"<string>\",\n    \"prompt\": \"<string>\",\n    \"text\": \"<string>\"\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "result": {
    "success": true,
    "text": "The rewritten or processed text returned by the model."
  }
}

Use this API to send a text rewriting or processing request to an AI model. The model provider is resolved automatically from the model name prefix.

Customer API keys are stored encrypted in the workspace aiModelsConfig and decrypted server-side. Configure your provider API keys in the Velt Console before using this endpoint.

Endpoint

POST https://api.velt.dev/v2/rewriter/ask-ai

Headers

x-velt-api-key · string · required

Your API key.

x-velt-auth-token · string · required

Your Auth Token.

Body

Params

data · object · required

Show properties

model · string · required

Model name to use for processing. The provider is resolved from the name prefix:

• gpt-*, o1-*, o3-*, o4-* → OpenAI
• claude-* → Anthropic
• gemini-* → Gemini

prompt · string · required

System prompt or instruction describing how to process the text.

text · string · required

Input text to process.

OpenAI reasoning models (o1-*, o3-*, o4-*) use a user-only message format. The prompt is prepended to the text in a single user message rather than sent as a separate system prompt.

Supported models (non-exhaustive)

Provider	Example models
OpenAI	gpt-4o, gpt-4o-mini, gpt-4.1, o3, o3-mini, o4-mini
Anthropic	claude-sonnet-4-0, claude-opus-4-0, claude-haiku-4-5
Gemini	gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite

Example Requests

Rewrite text using Claude

{
  "data": {
    "model": "claude-3-5-sonnet-20241022",
    "prompt": "Rewrite the following text to be more concise and professional.",
    "text": "Hey so I was just thinking that maybe we could potentially look into making some changes to the way we do things around here."
  }
}

Rewrite text using GPT-4o

{
  "data": {
    "model": "gpt-4o",
    "prompt": "Fix the grammar and spelling in the following text.",
    "text": "Their going to the store to by some apples."
  }
}

Process text using a reasoning model

{
  "data": {
    "model": "o3-mini",
    "prompt": "Summarize the key points from the following text.",
    "text": "Long document text content goes here..."
  }
}

Response

Success Response

{
  "result": {
    "success": true,
    "text": "The rewritten or processed text returned by the model."
  }
}

Error Response

{
  "result": {
    "success": false,
    "error": "No API key configured for provider: OpenAI"
  }
}

Failure Response

{
  "error": {
    "message": "ERROR_MESSAGE",
    "status": "INVALID_ARGUMENT"
  }
}

{
  "result": {
    "success": true,
    "text": "The rewritten or processed text returned by the model."
  }
}