Build with frontier multi-model LLMs

vipcloud.ai is an OpenAI-compatible gateway for Kimi, Qwen, DeepSeek, MiniMax, and GLM. One API key, USD billing, edge-routed via Cloudflare. Drop into any OpenAI SDK in 30 seconds.

Quickstart

Get a response in three steps.

1. 1.Get an API key

   Join the waitlist. We'll send you a key shaped vc-sk-... within 24h.

2. 2.Install the OpenAI SDK

   # Python
   pip install openai

   // Node
   npm install openai

3. 3.Make your first call
   Python

   from openai import OpenAI
   
   client = OpenAI(
       api_key="vc-sk-...",
       base_url="https://vipcloud.ai/v1",
   )
   
   resp = client.chat.completions.create(
       model="deepseek-chat",
       messages=[{"role": "user", "content": "Hello!"}],
   )
   print(resp.choices[0].message.content)

   Node.js

   import OpenAI from "openai";
   
   const client = new OpenAI({
     apiKey: "vc-sk-...",
     baseURL: "https://vipcloud.ai/v1",
   });
   
   const resp = await client.chat.completions.create({
     model: "deepseek-chat",
     messages: [{ role: "user", content: "Hello!" }],
   });
   console.log(resp.choices[0].message.content);

   curl

   curl https://vipcloud.ai/v1/chat/completions \
     -H "Authorization: Bearer vc-sk-..." \
     -H "Content-Type: application/json" \
     -d '{
       "model": "deepseek-chat",
       "messages": [{"role":"user","content":"Hello!"}]
     }'

Authentication

Send your API key as a Bearer token. Identical to OpenAI's auth scheme.

Authorization: Bearer vc-sk-...

Keys are scoped to your account. Rotate any time from your dashboard. Never commit them to git — use environment variables (VIPCLOUD_API_KEY) or a secret manager.

Chat Completions

POST /v1/chat/completions — fully OpenAI-compatible. Same request/response shape.

Request

Response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1745604000,
  "model": "deepseek-chat",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello!" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 2, "total_tokens": 11 }
}

Streaming (SSE)

Set stream: true for token-by-token delivery. Server-Sent Events frames are OpenAI-shaped — your existing SDK code works unchanged.

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

Frames look like data: {"choices":[{"delta":{"content":"Hello"}}]}. The stream ends with data: [DONE]. The final pre-DONE chunk includes usage when the upstream supports it.

Models

Pass any of these IDs as the model field. We route to the right upstream and translate where needed.

Live list: GET https://vipcloud.ai/v1/models

Errors

Errors return a JSON envelope matching OpenAI's shape.

{
  "error": {
    "message": "Invalid API key.",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Migrate from OpenAI

Two changes. That's it.

# Before
client = OpenAI(
    api_key="sk-openai-...",
)
client.chat.completions.create(model="gpt-4o", ...)

# After
client = OpenAI(
    api_key="vc-sk-...",
    base_url="https://vipcloud.ai/v1",  # NEW
)
client.chat.completions.create(model="deepseek-chat", ...)  # model swap

Streaming, function calling, JSON mode work without code changes — we translate provider quirks behind the scenes. Vision and audio are model-specific; check Models.

Rate Limits

Defaults below. Need higher? Email [email protected] with your use case.

429 responses include Retry-After in seconds. Use exponential backoff with jitter.

Pricing

Per 1M tokens, USD. Indicative — final rates locked when billing goes live (May 2026).

Markup: ~15% over upstream list price. Pre-paid credits, no monthly minimum.

Free demo on the homepage uses glm-4-flash. Token usage is reported in the usage object on every response.

FAQ