Documentație API

Endpoint

https://router.megapromoting.com/v1

Compatibil OpenAI SDK Python, Node.js, Go, Rust, etc.

Autentificare

Folosește cheia ta API ca Bearer token:

Authorization: Bearer sk-router-XXXXXXXXXXXXXXXXXXXX

Generează cheia în dashboard.

Modele disponibile

Exemplu — chat completion

cURL

curl -X POST https://router.megapromoting.com/v1/chat/completions \
  -H "Authorization: Bearer sk-router-XXXXX" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "Salut!"}
    ],
    "max_completion_tokens": 200
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://router.megapromoting.com/v1",
    api_key="sk-router-XXXXX"
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Salut!"}],
    max_completion_tokens=200
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://router.megapromoting.com/v1",
  apiKey: process.env.ROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "Salut!" }],
  max_completion_tokens: 200,
});

console.log(response.choices[0].message.content);

Reguli importante

• Modele reasoning (gpt-5.x): foloseste max_completion_tokens (NU max_tokens). Setează ≥ 2000 ca să eviți răspunsuri goale.
• Temperature: gpt-5.x reasoning acceptă DOAR temperature=1. Pentru determinism, folosește seed.
• Streaming: suportat pe toate modelele chat — adaugă stream: true.
• Tool calling: suportat — gpt-5.x, gpt-4.1, Gemini 3.