Qwen API: First request in five minutes

Base URL and Authentication

Our API follows the standard OpenAI format, making it easy to switch your existing client configuration. The base URL for all requests is https://api.qwenapis.com/v1. You will need an API key to authenticate your requests. If you haven't created one yet, visit the Get API key page to generate a key using just your email and password. No credit card is required to start with the trial credit.

Each account is limited to one active key at a time. You can regenerate your key at any time, which immediately revokes the previous one. This ensures that if your key is exposed, you can secure your account instantly without waiting for a monthly cycle. Keep your key secure in your environment variables or secret manager.

Make Your First Request

Verify your setup by sending a simple text completion request. The following example uses curl to send a prompt to the uncensored model. Replace YOUR_API_KEY with the key generated in the previous step. The model ID is set to uncensored, which is tuned to answer without content refusals for lawful adult use.

Copycurl https://api.qwenapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

If successful, you will receive a JSON response containing the generated text. If you receive a 401 error, check that your key is correct. A 402 error indicates your prepaid credit has been exhausted.

Python SDK Integration

For Python developers, the official OpenAI SDK works directly with our endpoint. Install the library using pip, then configure the client to point to our base URL. This allows you to use familiar methods like chat.completions.create() without changing your application logic significantly. The SDK handles JSON serialization and retry logic for you.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.qwenapis.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)

Remember to set the api_key and base_url correctly. The model name remains uncensored. This approach ensures compatibility with code written for other providers, making it easy to switch or test different endpoints.

Node SDK Usage

Node.js developers can use the @anthropic-ai/sdk or the official openai npm package. Configure the client with our base URL and your API key. The structure of the request is identical to other OpenAI-compatible services. This allows you to integrate uncensored Qwen into your existing Node.js applications with minimal code changes.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.qwenapis.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);

Ensure you handle the asynchronous response appropriately. The SDK will return the full completion object, including token usage statistics. This helps you monitor your prepaid credit consumption in real-time.

Enable Streaming

For lower latency and a better user experience, enable streaming in your requests. Streaming sends the response token by token as it is generated, allowing your application to display output progressively. Set the stream parameter to true in your request. The SDK will provide an iterable stream of chunks.

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)

This is particularly useful for long-form content generation or interactive applications. Each chunk contains partial text, which you can append to your display buffer. The stream ends when the model completes the response or hits the context limit.

Limits, Errors, and Context

Our API has specific limits to ensure fair usage. You are allowed 300 requests per minute per key. The maximum request body size is 8 MB. The context window is 100,000 tokens, covering both the prompt and the completion. If you exceed the rate limit, you will receive a 429 error. If your credit is insufficient, you will receive a 402 error. For invalid keys, you will receive a 401 error. These errors help you manage your application's flow and credit usage effectively.