Qwen api documentation: quickstart

Base URL and authentication

Use https://api.qwenapidocumentation.com/v1 as your base URL. Authenticate by passing your API key in the Authorization header.

Sign up via Google or email to receive your key immediately.

Chat completions endpoint (/v1/chat/completions)

Send POST requests to /v1/chat/completions with your model ID uncensored. The endpoint accepts standard chat messages and returns text.

• Input: JSON body with messages array.
• Output: Tokenized text response.

Our model is tuned to answer without content refusals for lawful adult use.

Python SDK integration

Install the official OpenAI Python package. Set the base URL and API key before initializing the client.

• Context Window: 100,000 tokens total.
• Max Output: 16,000 tokens per request.

This setup ensures your client code works exactly as it would for other major vendors.

Node.js SDK usage

Use the openai Node.js package. Configure the client with your unique API key and our base URL.

• Rate Limit: 300 requests per minute per key.
• Concurrent: 8 simultaneous requests.

This allows for high-throughput applications without complex retry logic.

Streaming responses with SSE

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE).

• Token Usage: Included in the last chunk.
• Real-time: Tokens arrive as they are generated.

This is ideal for chat interfaces where users expect instant feedback.

Error handling and limits

Handle standard HTTP errors. 401 indicates an invalid key. 402 means no credit. 429 is a rate limit.

• Request Body: Max 8 MB.
• Refusals: Free if content violates the hard limit.

Errors do not consume your prepaid credit. Context window is 100,000 tokens.

cURL

Copycurl https://api.qwenapidocumentation.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the area of a circle with radius five"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.qwenapidocumentation.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node.js

Copyimport OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)