Dokumentasi API

Panduan cepat

1. Buka Konsol API lalu buat kunci. Salin nilai cgw-sk-... — hanya ditampilkan sekali.
2. Isi saldo USDT Anda lewat Tagihan. Isi saldo pertama $10 menjadi $15, cukup untuk mencoba beberapa saat.
3. Kirim permintaan:
4. Contoh siap jalan (Python, Node.js, cURL, pengaturan Cursor/Cline) ada di repo publik <a href="https://github.com/mrhy7176/cloudgpu-examples" class="text-primary underline" target="_blank" rel="noopener">github.com/mrhy7176/cloudgpu-examples</a>.

cURL
curl https://cloudgpu.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CGW_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Say hi in one sentence."}
    ]
  }'

Autentikasi

Setiap permintaan ke /v1/* requires an Authorization: Bearer cgw-sk-<your_key> header. Keys are scoped to your CloudGPU account. Revoke any key any time from the console; revocation takes effect immediately.

The raw key is shown exactly once at creation time. We store only a sha256 hash; we cannot recover it if you lose it. Create a new key if that happens.

Endpoint

Embedding, function calling, vision, generasi gambar — ada dalam rencana, belum di v0.

Streaming

Sertakan "stream": true di body permintaan. Responsnya berupa Server-Sent Events format OpenAI. OpenAI SDK menanganinya secara transparan.

Python (streaming)
# Streaming — same client, stream=True
for chunk in client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Count to 5."}],
    stream=True,
):
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

SDK

Kami tidak menyediakan SDK sendiri — OpenAI SDK bisa langsung dipakai dengan base_url override.

Python
# pip install openai>=1.0
from openai import OpenAI

client = OpenAI(
    api_key="cgw-sk-...",                     # from /api/console
    base_url="https://cloudgpu.app/v1",
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Say hi."}],
)
print(resp.choices[0].message.content)
print(f"Used {resp.usage.total_tokens} tokens")

Node.js
// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CGW_API_KEY,
  baseURL: "https://cloudgpu.app/v1",
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Say hi." }],
});
console.log(resp.choices[0].message.content);

Harga & penagihan

Every model is priced terhadap tarif vendornya sendiri for the same model — most at or below it; the tabel harga shows the exact comparison. You pay per token, per image, per character or per second of audio depending on the model; nothing is metered by the hour and there is no monthly minimum.

Each request deducts from your prepaid balance. Successful calls show in your konsol within ~1 second with full token counts and dollar cost.

Tabel harga lengkap per model ada di halaman utama.

Instance GPU

Kunci API yang sama juga menyewa GPU: lihat yang tersedia, jalankan instance dari template, poll sampai berjalan, baca detail SSH dan endpoint API publik, hancurkan. Penagihan sama dengan konsol web — per menit, dari saldo yang sama.

Bagian ini hanya tentang REST API. Menyewa GPU dari konsol web tidak punya syarat minimum. API instance terprogram hanya aktif untuk akun dengan total isi saldo minimal $2.000; akun lain menerima 403 gpu_api_not_enabled beserta jumlah yang masih kurang.

curl -X POST https://cloudgpu.app/v1/gpu/instances \
  -H "Authorization: Bearer $CLOUDGPU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"gpu_model": "RTX 4090", "template": "ollama"}'

# 202 Accepted
{"id":"2096…","object":"gpu.instance","gpu_model":"RTX 4090","gpu_count":1,"template":"ollama",
 "status":"creating","hourly_usd":0.33,"ssh":null,"api_url":null, …}

# poll GET /v1/gpu/instances/{id} until status is "running";
# then ssh.host / ssh.port / ssh.password and api_url (for API templates) are filled in.

Bawaan: 10 instance berjalan atau dimulai sekaligus, 20 pembuatan per jam, 60 permintaan GPU API per menit per kunci. Hubungi support@cloudgpu.app untuk menaikkannya bagi beban kerja nyata.

Batas laju

Nilai bawaan ini untuk mencegah penyalahgunaan selama beta publik. Hubungi kami kalau perlu dinaikkan — dengan senang hati untuk beban kerja yang nyata, cukup beri tahu kasus penggunaannya.

Kesalahan

Respons kesalahan mengikuti bentuk OpenAI: kode status HTTP + body JSON { error: { type, code, message } }.