Ultra-Fast LLM

Claude 3.5 Haiku API

Akses model Claude paling ringan dan cepat dari Anthropic. Dioptimalkan secara sempurna untuk task seketika, asisten chat, dan parsing data dengan time-to-first-token super rendah. API ini secara bawaan menggunakan SSE (Server-Sent Events) atau standard streaming untuk respons realtime.

POSThttps://stenly.org/api/overchat

Header & Payload

Parameter	Tipe Data	Deskripsi Node
messages *	Array	Riwayat percakapan dengan kombinasi objek user, assistant, atau system prompt.
chatId	String	UUID (Opsional). Digunakan untuk melanjutkan chain memory pada sesi chat sebelumnya.
deviceId	String	Identifikasi anonim perangkat untuk rate-limiting atau session tracking.

Full Integration Guide

Siapkan Request POST

Lakukan request ke endpoint kami menggunakan metode POST dengan format JSON.

Terminal / Bash (cURL)

curl -X POST "https://stenly.org/api/overchat" \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Hello"}]}'

Python (Requests)

import requests, json url = "https://stenly.org/api/overchat"payload = {[object Object]: [{"role": "user", "content": "Halo AI"}]}
response = requests.post(url, json=payload, stream=True)for chunk in response.iter_content(chunk_size=None):if chunk: print(chunk.decode('utf-8'), end='', flush=True)

Node.js (Streaming Fetch)

const response = await fetch("https://stenly.org/api/overchat", {method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ messages: [{ role: "user", content: "Hello" }] })});const reader = response.body?.getReader();while (true) {const { done, value } = await reader.read();if (done) break; process.stdout.write(new TextDecoder().decode(value));}

PHP (Native cURL)

<?php$ch = curl_init("https://stenly.org/api/overchat");curl_setopt($ch, CURLOPT, ['Content-Type: application/json']); curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["messages" => [["role" => "user", "content" => "Hello"]]])); curl_setopt($ch, CURLOPT_WRITEFUNCTION, function($ch, $data) {echo $data; return strlen($data);}); curl_exec($ch);

Go (Native)

import ( "bytes"; "io"; "net/http"; "os" )func main() {url := "https://stenly.org/api/overchat"jsonStr := []byte("{\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}")
 req, _ := http.NewRequest("POST", url,bytes.NewBuffer(jsonStr))
 req.Header.Set("Content-Type", "application/json") client := &http.Client{}resp, _ := client.Do(req)defer resp.Body.Close() io.Copy(os.Stdout, resp.Body)}

Hasil Yang Didapatkan (Response)

HTTP Headers

HTTP/1.1 200 OK

Content-Type: text/event-stream

X-Stenly-Engine: Claude-3.5-Haiku-Node

X-Chat-ID: ssn_...

Stream Output

Halo! Ada yang bisa saya bantu?

* Catatan: Data dikirimkan secara parsial melalui chunked transfer encoding. Gunakan parser SSE atau pembaca stream mentah di aplikasi Anda untuk menangani output realtime.

tty1 - bash

# User Input Message

# Prepared JSON Request

{
  "messages": [
    {
      "role": "user",
      "content": "Halo, ceritakan singkat tentang AI!"
    }
  ]
}