Quick start

Get your first AI response in under 5 minutes. ChengQiu AI is fully OpenAI-compatible — if your code works with OpenAI, just change the base URL.

1

Get your API key

Sign in to the console with your API key. Don't have one? Contact us to get one.

2

Set your base URL

Point your OpenAI SDK or HTTP client to our API endpoint.

Base URL: https://api.chengqiukeji.com/v1

3

Make your first request

Use curl or any OpenAI SDK:

curl https://api.chengqiukeji.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "deepseek-r1:7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

4

That's it!

You'll receive a JSON response in OpenAI format. Try the Playground to test interactively.

Authentication

All API requests require a Bearer token in the Authorization header:

Authorization: Bearer sk-your-api-key

Your API key starts with sk-. Keep it secure — do not expose it in client-side code or public repositories.

Note: Admin tokens start with sk-admin- and have access to key management endpoints. Regular API keys can only make inference requests.

Base URL

https://api.chengqiukeji.com/v1

All endpoints listed below are relative to this base URL. For example, /chat/completions becomes https://api.chengqiukeji.com/v1/chat/completions.

Chat completions

Creates a model response for the given chat conversation. Fully compatible with OpenAI's chat completions API.

POST /v1/chat/completions

Request body

Parameter	Type	Required	Description
model	string	Yes	Model ID, e.g. `deepseek-r1:7b`
messages	array	Yes	Array of message objects with role and content
max_tokens	integer	No	Max tokens to generate (default: 500)
temperature	float	No	Sampling temperature 0-2 (default: 0.7)
stream	boolean	No	Stream response via SSE (default: false)
top_p	float	No	Nucleus sampling parameter (default: 0.9)

Example response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "model": "deepseek-r1:7b",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 8,
    "total_tokens": 18
  }
}

List models

GET /v1/models

Returns a list of available models.

{
  "object": "list",
  "data": [
    { "id": "deepseek-r1:7b", "object": "model" }
  ]
}

Streaming

Set "stream": true to receive Server-Sent Events (SSE). Each chunk is a JSON object ending with data: [DONE].

data: {"choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"choices":[{"delta":{"content":"!"},"index":0}]}

data: {"choices":[{"delta":{},"index":0,"finish_reason":"stop"}]}

data: [DONE]

Code examples

🐍 Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chengqiukeji.com/v1",
    api_key="sk-your-api-key"
)

# Non-streaming
response = client.chat.completions.create(
    model="deepseek-r1:7b",
    messages=[{"role": "user", "content": "What is the capital of Vietnam?"}],
    max_tokens=100
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="deepseek-r1:7b",
    messages=[{"role": "user", "content": "Write a haiku about Singapore"}],
    stream=True
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

🟨 JavaScript (Node.js)

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://api.chengqiukeji.com/v1",
    apiKey: process.env.CQ_API_KEY
});

const response = await client.chat.completions.create({
    model: "deepseek-r1:7b",
    messages: [{ role: "user", content: "Explain quantum computing simply" }],
    max_tokens: 200
});

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

🐘 PHP (Guzzle)

$client = new GuzzleHttp\Client();

$response = $client->post('https://api.chengqiukeji.com/v1/chat/completions', [
    'headers' => [
        'Authorization' => 'Bearer sk-your-api-key',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'model' => 'deepseek-r1:7b',
        'messages' => [['role' => 'user', 'content' => 'Hello!']],
    ],
]);

$data = json_decode($response->getBody(), true);
echo $data['choices'][0]['message']['content'];

☕ Java (OkHttp)

OkHttpClient client = new OkHttpClient();

RequestBody body = RequestBody.create(
    "{\"model\":\"deepseek-r1:7b\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}]}",
    MediaType.parse("application/json")
);

Request request = new Request.Builder()
    .url("https://api.chengqiukeji.com/v1/chat/completions")
    .addHeader("Authorization", "Bearer sk-your-api-key")
    .post(body)
    .build();

Response response = client.newCall(request).execute();
System.out.println(response.body().string());

Error codes

Status	Meaning	How to fix
200	Success	All good!
401	Unauthorized	Check your API key is valid
402	Payment required	Your balance is empty — recharge in console
422	Validation error	Check request body format
429	Rate limited	Slow down — check your rate limit
500	Server error	Retry after a few seconds

FAQ

Is it really OpenAI-compatible?

Yes. We implement the same /v1/chat/completions and /v1/models endpoints with identical request/response formats. If your code uses the OpenAI SDK, just change base_url and api_key.

How am I billed?

You're billed per 1,000 tokens (prompt + completion combined). The rate is $0.002/1K tokens for the Starter plan. Each request's cost is deducted from your balance in real-time.

Where is the server located?

Our GPU server is in Singapore (Tencent Cloud HAI). Average latency from Southeast Asian cities is under 50ms.

Do you store my data?

No. We log token counts and costs for billing, but we do not store the content of your requests or responses. Your data is processed in memory and immediately discarded.

Can I pay in my local currency?

Billing is in USD. You can settle via bank transfer, Wise, or cryptocurrency. Contact us for local payment options in SGD, MYR, IDR, THB, or VND.

What's the rate limit?

Starter plan: 30 requests/minute. Business plan: 200 requests/minute. Enterprise: unlimited. Rate limits are per API key.

How do I get support?

Email support@chengqiukeji.com or message us on Telegram. Enterprise customers get priority response within 1 hour.