API Documentation

Access DeepSeek, GLM, and China's top AI models through one OpenAI-compatible API.

Quick Start

1. Register at chinallm.dev/console
2. Create an API key in the Tokens tab — starts with sk-
3. Top up $5+ USDT to start making API calls
4. Use the key in any OpenAI-compatible client:

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

Authentication

Include your API key in the Authorization header:

CopyAuthorization: Bearer sk-YOUR_API_KEY

Your API key is found at Console → Tokens. Never share it. You can create multiple keys and revoke them at any time.

Models & Pricing

All prices per 1 million tokens. Pay only what you use.

More models coming soon: Qwen, Hunyuan, Moonshot, ERNIE.

Chat Completions

Request Body

Copycurl https://chinallm.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Copyimport requests

response = requests.post(
    "https://chinallm.dev/v1/chat/completions",
    headers={
        "Authorization": "Bearer sk-YOUR_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "deepseek-chat",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Explain quantum computing in simple terms."}
        ],
        "temperature": 0.7,
        "max_tokens": 500
    }
)

print(response.json()["choices"][0]["message"]["content"])

Copyconst response = await fetch("https://chinallm.dev/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer sk-YOUR_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "deepseek-chat",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Explain quantum computing in simple terms." }
    ],
    temperature: 0.7,
    max_tokens: 500
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Response

Copy{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-chat",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Quantum computing uses quantum bits..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 85,
    "total_tokens": 110
  }
}

Streaming

Set "stream": true to receive token-by-token responses via Server-Sent Events (SSE):

Copy// Python example with streaming
import requests, json

response = requests.post(
    "https://chinallm.dev/v1/chat/completions",
    headers={
        "Authorization": "Bearer sk-YOUR_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "deepseek-chat",
        "messages": [{"role": "user", "content": "Write a haiku about AI"}],
        "stream": true
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        line = line.decode("utf-8")
        if line.startswith("data: ") and line != "data: [DONE]":
            chunk = json.loads(line[6:])
            content = chunk["choices"][0].get("delta", {}).get("content", "")
            if content:
                print(content, end="", flush=True)

Error Codes

Copyfrom openai import OpenAI

client = OpenAI(
    api_key="sk-YOUR_KEY",
    base_url="https://chinallm.dev/v1"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}]
)