Your first request

This guide walks you through your first API call from scratch. Before starting, make sure:

1. You have created an API key and saved the full key.
2. You have the Base URL: sign in to the console, open the "Quick start" dialog, pick a protocol and copy it. The examples below use https://<your-base-url> as a placeholder — replace it with your own.

The platform speaks three native protocols; pick whichever fits — billing and balance are identical across all of them.

OpenAI-compatible protocol (default recommendation)

Fully compatible with the OpenAI SDK: point base_url at the platform and your existing code keeps working.

cURL

curl https://<your-base-url>/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://<your-base-url>",
)

completion = client.chat.completions.create(
    model="your-model",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)

Node.js (openai SDK)

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://<your-base-url>",
})

const completion = await client.chat.completions.create({
  model: "your-model",
  messages: [{ role: "user", content: "Hello" }],
})
console.log(completion.choices[0].message.content)

Anthropic protocol

Isomorphic to the Anthropic Messages API: authenticate with x-api-key and carry anthropic-version:

curl https://<your-base-url>/v1/messages \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Gemini protocol

Isomorphic to the Google GenAI API: the model ID goes into the path, and authentication uses x-goog-api-key:

curl "https://<your-base-url>/v1beta/models/your-model:generateContent" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Hello"}]}]
  }'

Verify the result

A successful request returns the model's reply (for the OpenAI protocol it is in choices[0].message.content). From there you can:

• Check the usage and balance change on the "Usage" page in the console;
• Replace your-model with a real model ID from the model marketplace (text, image, audio, video, and file modalities are supported).

Common first-call errors

Production tips: keep the key in an environment variable (e.g. OPENAI_API_KEY) instead of hard-coding it, and prefer the official SDK over hand-written HTTP calls — the SDK absorbs protocol compatibility details.