Generate text
curl --request POST \
--url https://flowra.dev/api/v1/ai/llm/generate \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"prompt": "Summarize this meeting in three bullets.",
"model": "openai/gpt-4o-mini",
"temperature": 0.7,
"maxTokens": 1024,
"systemPrompt": "You are a concise meeting assistant."
}
'import requests
url = "https://flowra.dev/api/v1/ai/llm/generate"
payload = {
"prompt": "Summarize this meeting in three bullets.",
"model": "openai/gpt-4o-mini",
"temperature": 0.7,
"maxTokens": 1024,
"systemPrompt": "You are a concise meeting assistant."
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: 'Summarize this meeting in three bullets.',
model: 'openai/gpt-4o-mini',
temperature: 0.7,
maxTokens: 1024,
systemPrompt: 'You are a concise meeting assistant.'
})
};
fetch('https://flowra.dev/api/v1/ai/llm/generate', 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://flowra.dev/api/v1/ai/llm/generate",
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([
'prompt' => 'Summarize this meeting in three bullets.',
'model' => 'openai/gpt-4o-mini',
'temperature' => 0.7,
'maxTokens' => 1024,
'systemPrompt' => 'You are a concise meeting assistant.'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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://flowra.dev/api/v1/ai/llm/generate"
payload := strings.NewReader("{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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://flowra.dev/api/v1/ai/llm/generate")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://flowra.dev/api/v1/ai/llm/generate")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"message": "Operation completed successfully",
"data": ""
}LLM
Generate text
Send a prompt and receive generated text from the configured LLM. Use for one-off completions, chat replies, or any task that needs AI-generated text. Supports long prompts.
POST
/
api
/
v1
/
ai
/
llm
/
generate
Generate text
curl --request POST \
--url https://flowra.dev/api/v1/ai/llm/generate \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"prompt": "Summarize this meeting in three bullets.",
"model": "openai/gpt-4o-mini",
"temperature": 0.7,
"maxTokens": 1024,
"systemPrompt": "You are a concise meeting assistant."
}
'import requests
url = "https://flowra.dev/api/v1/ai/llm/generate"
payload = {
"prompt": "Summarize this meeting in three bullets.",
"model": "openai/gpt-4o-mini",
"temperature": 0.7,
"maxTokens": 1024,
"systemPrompt": "You are a concise meeting assistant."
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
prompt: 'Summarize this meeting in three bullets.',
model: 'openai/gpt-4o-mini',
temperature: 0.7,
maxTokens: 1024,
systemPrompt: 'You are a concise meeting assistant.'
})
};
fetch('https://flowra.dev/api/v1/ai/llm/generate', 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://flowra.dev/api/v1/ai/llm/generate",
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([
'prompt' => 'Summarize this meeting in three bullets.',
'model' => 'openai/gpt-4o-mini',
'temperature' => 0.7,
'maxTokens' => 1024,
'systemPrompt' => 'You are a concise meeting assistant.'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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://flowra.dev/api/v1/ai/llm/generate"
payload := strings.NewReader("{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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://flowra.dev/api/v1/ai/llm/generate")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://flowra.dev/api/v1/ai/llm/generate")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"prompt\": \"Summarize this meeting in three bullets.\",\n \"model\": \"openai/gpt-4o-mini\",\n \"temperature\": 0.7,\n \"maxTokens\": 1024,\n \"systemPrompt\": \"You are a concise meeting assistant.\"\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"message": "Operation completed successfully",
"data": ""
}Authorizations
Project API key. Create and manage keys in the dashboard under Project → API Keys. Send as header: x-api-key:
Body
application/json
Prompt for text generation
Maximum string length:
400000Example:
"Summarize this meeting in three bullets."
Model ID (e.g. openai/gpt-4o-mini)
Example:
"openai/gpt-4o-mini"
Temperature (0-2)
Example:
0.7
Max tokens in response
Example:
1024
System prompt to set context
Example:
"You are a concise meeting assistant."
Was this page helpful?